Image processing method and system

Abstract

The application discloses an image processing method and system. The method comprises the following steps: obtaining a description page of a target object, wherein the description page contains an original image corresponding to the target object and description information of the original image; determining whether the original image is a target image based on the original image or the description information, wherein the target image is an image that causes visual discomfort; obtaining a target replacement image corresponding to the original image in the case that the original image is the target image; and replacing the original image with the target replacement image to obtain a processed description page. The application solves the technical problem that the original image that causes visual discomfort is directly displayed to a user in the related art, thereby affecting the user's browsing experience.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of image processing, in particular to an image processing method and system. BACKGROUND

[0002] Currently, in an e-commerce platform or a website of encyclopedic knowledge, in order to enable a user to accurately obtain relevant information, a relevant introduction picture is often attached, for example, for a sold insect repellent, an introduction picture that the insect repellent can kill or repel insects is often attached, and for example, for an introduction of skin diseases in an encyclopedic knowledge, an introduction picture of a disease form is often attached. However, the above introduction pictures cause visual discomfort to the user, resulting in a decrease in the user's browsing experience.

[0003] At present, no effective solution has been proposed for the above problems. SUMMARY

[0004] Embodiments of the present application provide an image processing method and system to at least solve the technical problem that a user's browsing experience is affected by directly showing the user an original image that causes visual discomfort to the user.

[0005] According to an aspect of an embodiment of the present application, an image processing method is provided, comprising: obtaining a description page of a target object, wherein the description page contains an original image corresponding to the target object and description information of the original image; determining whether the original image is a target image based on the original image or the description information, wherein the target image is an image that visually causes discomfort; in a case where the original image is the target image, obtaining a target replacement image corresponding to the original image; and replacing the original image with the target replacement image to obtain a processed description page.

[0006] According to another aspect of an embodiment of the present application, an image processing method is also provided, comprising: obtaining a description page of a target object, wherein the description page contains an original image corresponding to the target object and description information of the original image; in a case where it is determined that the original image is a target image based on the original image or the description information, obtaining a target replacement image corresponding to the original image, wherein the target image is an image that visually causes discomfort; and displaying a processed description page, wherein the processed description page is a page obtained by replacing the original image with the target replacement image.

[0007] According to another aspect of the embodiments of the present application, a method for image processing is also provided, including: receiving a description page of a target object, wherein the description page contains an original image corresponding to the target object and description information of the original image; determining whether the original image is a target image based on the original image or the description information, wherein the target image is an image that is visually uncomfortable; obtaining a target replacement image corresponding to the original image in a case where the original image is the target image; replacing the original image with the target replacement image to obtain a processed description page; and outputting the processed description page.

[0008] According to another aspect of the embodiments of the present application, a method for image processing is also provided, including: receiving a description page of a target object, wherein the description page contains an original image corresponding to the target object and description information of the original image; determining whether the original image is a target image based on the original image or the description information, wherein the target image is an image that is visually uncomfortable; obtaining a target replacement image corresponding to the original image in a case where the original image is the target image; replacing the original image with the target replacement image to obtain a processed description page; and outputting the processed description page.

[0009] According to another aspect of the embodiments of the present application, a method for image processing is also provided, including: receiving a description page of a target object, wherein the description page contains an original image corresponding to the target object and description information of the original image; determining whether the original image is a target image based on the original image or the description information, wherein the target image is an image that is visually uncomfortable; obtaining a target replacement image corresponding to the original image in a case where the original image is the target image; replacing the original image with the target replacement image to obtain a processed description page; and outputting the processed description page.

[0010] According to another aspect of the embodiments of the present application, a method for image processing is also provided, including: receiving a description page of a target object, wherein the description page contains an original image corresponding to the target object and description information of the original image; determining whether the original image is a target image based on the original image or the description information, wherein the target image is an image that is visually uncomfortable; obtaining a target replacement image corresponding to the original image in a case where the original image is the target image; replacing the original image with the target replacement image to obtain a processed description page; and outputting the processed description page.

[0011] According to another aspect of the embodiments of the present application, a computer readable storage medium is also provided, which includes a stored program, wherein the program controls a device where the computer readable storage medium is located to perform the image processing method when the program is running.

[0012] According to a further aspect of the embodiments of the present application, a computer terminal is also provided, comprising a memory and a processor, the processor being configured to execute a program stored in the memory, wherein the program, when executed, performs the image processing method described above.

[0013] According to a further aspect of the embodiments of the present application, an image processing system is also provided, comprising a processor, and a memory connected to the processor and configured to provide the processor with instructions for processing the following steps: obtaining a description page of a target object, wherein the description page comprises an original image corresponding to the target object and description information of the original image; determining whether the original image is a target image based on the original image or the description information, wherein the target image is an image that is visually uncomfortable; obtaining a target replacement image corresponding to the original image in the case that the original image is the target image; and replacing the original image with the target replacement image to obtain a processed description page.

[0014] In the embodiments of the present application, first, a description page of a target object is obtained, wherein the description page comprises an original image corresponding to the target object and description information of the original image, then it is determined whether the original image is a target image that is visually uncomfortable based on the original image or the description information, in the case that the original image is the target image, a target replacement image corresponding to the original image is obtained, the original image is replaced with the target replacement image to obtain a processed description page, and the target image that is visually uncomfortable is processed to improve the browsing experience of the user. It is easy to note that after obtaining the description page of the target object, it can be determined according to the image content of the original image and the description information whether the original image will affect the user's visual experience, in the case that it is determined that the original image will affect the user's visual experience, the original image is replaced by the target replacement image corresponding to the original image, which can avoid the original image causing the user's visual discomfort, since the target replacement image and the original image express the same content but have different forms, therefore, the user's browsing experience can be improved, and the user can understand the information expressed by the original image by using the target replacement image display mode, thereby solving the technical problem that the original image that will cause the user's visual discomfort is directly displayed to the user, thereby affecting the user's browsing experience. BRIEF DESCRIPTION OF DRAWINGS

[0015] The accompanying drawings, which are included to provide a further understanding of the present application and are incorporated in and constitute a part of this application, illustrate embodiments of the present application and serve to explain the present application. In the drawings:

[0016] Figure 1 is a hardware structure block diagram of a computer terminal (or mobile device) for implementing an image processing method according to an embodiment of the present application;

[0017] Figure 2 is a flowchart of an image processing method according to the embodiment 1 of the present application;

[0018] Figure 3 is a schematic diagram of an interactive interface according to the embodiment 1 of the present application;

[0019] Figure 4 is a flowchart of an optional image processing method according to the embodiment 1 of the present application;

[0020] Figure 5 is a schematic diagram of a display interface according to the embodiment 1 of the present application;

[0021] Figure 6 is a structural block diagram of an image processing according to the embodiment 1 of the present application;

[0022] Figure 7 is a flowchart of an image processing method according to the embodiment 2 of the present application;

[0023] Figure 8 is a flowchart of an image processing method according to the embodiment 3 of the present application;

[0024] Figure 9 is a flowchart of an image processing method according to the embodiment 4 of the present application;

[0025] Figure 10 is a flowchart of an image processing method according to the embodiment 5 of the present application;

[0026] Figure 11 is a flowchart of an image processing device according to the embodiment 6 of the present application;

[0027] Figure 12 is a flowchart of an image processing device according to the embodiment 7 of the present application;

[0028] Figure 13 is a flowchart of an image processing device according to the embodiment 8 of the present application;

[0029] Figure 14 is a flowchart of an image processing device according to the embodiment 9 of the present application;

[0030] Figure 15 is a flowchart of an image processing device according to the embodiment 10 of the present application;

[0031] Figure 16 is a flowchart of an image processing method according to the embodiment 11 of the present application;

[0032] Figure 17 is a flowchart of an image processing device according to the embodiment 12 of the present application;

[0033] Figure 18 is a structural block diagram of a computer terminal according to Embodiment 14 of the present application. DETAILED DESCRIPTION

[0034] In order to make the personnel in the technical field better understand the scheme of the present application, the technical scheme in the embodiments of the present application will be clearly and completely described below in combination with the drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, not all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by the person of ordinary skill in the art without creative labor should belong to the protection scope of the present application.

[0035] It should be noted that the terms "first", "second", and the like in the specification and claims of the present application and the above-described drawings are used to distinguish similar objects, and do not necessarily have to be used to describe a specific order or sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "include" and "have" and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product or device including a series of steps or units does not have to be limited to only those steps or units clearly listed, but can include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0036] First, some nouns or terms appearing in the description of the embodiments of the present application are applicable to the following explanations:

[0037] Visual discomfort image: an image that is easy to cause people to be uncomfortable, such as various insect images, skin disease images, and bacteria images.

[0038] Hidden display processing: an image that is easy to cause visual discomfort is displayed in a corresponding cartoon form, and an interactive mode is designed to display the original image.

[0039] At present, images in a webpage that cause discomfort to the user's vision can be hidden in its entirety. However, hiding all such images will have the following problems: images that cause visual discomfort to the user are different for different people, some people are afraid of insects, some people have entomophobia, but other people do not necessarily feel that the image will cause discomfort; if all such images are hidden, it will cause the information in the webpage to be imprecise, for example, when selling insect repellent, the types of insects need to be compared, or the specific symptoms of skin diseases need to be viewed.

[0040] In order to solve the above problems, the present application provides the following solutions.

[0041] Embodiment 1

[0042] According to the embodiments of the present application, an image processing method is also provided. It should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from here.

[0043] The method embodiments provided by the embodiments of the present application can be executed in a mobile terminal, a computer terminal or similar computing device. Figure 1 A hardware structure block diagram of a computer terminal (or mobile device) for implementing the image processing method is shown. As shown in Figure 1 , the computer terminal 10 (or mobile device 10) can include one or more processors 102 (the processor 102 can include but not limited to a microprocessor MCU or a programmable logic device FPGA processing device), a memory 104 for storing data, and a transmission device 106 for communication function. In addition, it can also include a display, an input / output interface (I / O interface), a universal serial bus (USB) port (which can be included as one of the ports of the BUS bus), a network interface, a power supply and / or a camera. Those skilled in the art can understand that Figure 1 The structure shown is only schematic, which does not limit the structure of the above-mentioned electronic device. For example, the computer terminal 10 can also include more or less components than those shown in Figure 1 , or have a different configuration from Figure 1 .

[0044] It should be noted that the one or more processors 102 and / or other data processing circuits described above can be referred to herein as "data processing circuits" in general. The data processing circuit can be embodied in whole or in part as software, hardware, firmware or any other combination. In addition, the data processing circuit can be a single independent processing module, or any one of the other elements combined into the computer terminal 10 (or mobile device) in whole or in part. As referred to in the embodiments of the present application, the data processing circuit as a kind of processor control (for example, the selection of the variable resistance terminal path connected with the interface).

[0045] The memory 104 can be used to store software programs of application software and modules, such as program instructions / data storage means corresponding to the image processing method in the embodiments of the present application. The processor 102 executes various functional applications and data processing, i.e., implements the image processing method described above, by running the software programs and modules stored in the memory 104. The memory 104 can include a high-speed random access memory, and can further include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some examples, the memory 104 can further include memories remotely arranged with respect to the processor 102, which can be connected to the computer terminal 10 through a network. Examples of the network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0046] The transmission device 106 is used to receive or send data via a network. Specific examples of the network can include a wireless network provided by a communication provider of the computer terminal 10. In one example, the transmission device 106 includes a network adapter (NIC) which can be connected to other network devices through a base station so as to be able to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module which is used to communicate with the Internet in a wireless manner.

[0047] The display can be, for example, a touch screen type liquid crystal display (LCD) which can enable a user to interact with a user interface of the computer terminal 10 (or a mobile device).

[0048] It should be noted that, in some optional embodiments, the above Figure 1 The computer device (or mobile device) shown can include hardware elements (including circuitry), software elements (including computer code stored on a computer readable medium), or a combination of both hardware and software elements. It should be noted that Figure 1 is only one example of a particular implementation and is intended to illustrate the types of components that can be present in the above-described computer device (or mobile device).

[0049] In the above-described operating environment, the present application provides an image processing method as shown in Figure 2 . Figure 2 is a flowchart of an image processing method according to Embodiment 1 of the present application. As shown in Figure 2 , the method can include the following steps:

[0050] In step S202, a description page of a target object is acquired.

[0051] The description page contains an original image corresponding to the target object and description information of the original image.

[0052] The target object in the above steps can be a product in an e-commerce shopping platform, and can also be a product or disease introduced in a knowledge-based webpage or a diagnostic webpage, and can also be a crime scene in a news webpage.

[0053] The description page of the target object in the above steps can be an introduction page or a purchase page of the product in the e-commerce shopping platform, and can also be a description page of the product or disease in the knowledge-based webpage or the diagnostic webpage, and can also be a report page of the crime scene in the news webpage.

[0054] The original image in the above steps can be an image originally existing in the description page, that is, an image without any processing.

[0055] The description information of the original image in the above steps can be description information describing the content of the original image or description information related to the content of the original image, for example, the original image is a cockroach image, and the description information of the original image can be the efficacy of cockroach medicine.

[0056] In an optional embodiment, the introduction page of the product can be acquired when the user starts browsing the e-commerce shopping platform, so as to process the product introduction image in the product introduction page that will cause visual discomfort to the user in advance, avoid the user from watching when browsing, and thus improve the browsing experience of the user. The description page of the product or disease can also be acquired when the user starts browsing the knowledge-based webpage or the diagnostic webpage, so as to process the pathological image in the description page that will cause visual discomfort to the user in advance, avoid the user from watching when browsing, and thus improve the browsing experience of the user. The report page of the news webpage can also be acquired when the user starts browsing the news webpage, so as to process the crime scene image in the report page in advance, avoid the user from watching when browsing, and thus improve the browsing experience of the user.

[0057] In another optional embodiment, the description page of the target object can be acquired when the user searches for the target object by using the search box but has not successfully jumped to the target object, the image in the description page that will cause visual discomfort to the user can be processed in advance, so that the user cannot see any image that will cause visual discomfort after successfully jumping to the page, and thus the browsing experience of the user is improved.

[0058] In another alternative embodiment, the user can click an image option for processing the image causing discomfort when entering the e-commerce shopping platform, the encyclopedia webpage, the diagnostic webpage and the news webpage, so as to facilitate the user to process the original image of the target object according to the browsing needs of the user, thereby improving the flexibility of the user browsing. The image option for processing the image causing discomfort can be a control, an icon, a fixed button, a floating button, a hyperlink, a specific gesture, etc. set in the webpage, and the setting manner of the image option for processing the image causing discomfort is not limited herein.

[0059] In another alternative embodiment, in order to better process the description page of the target object, the obtained description page of the target object can be transmitted to the corresponding processing device for processing, for example, directly transmitted to the computer terminal (for example, a notebook computer, a personal computer, etc.) of the user for processing, or transmitted to the cloud server through the computer terminal of the user for processing. It should be noted that, since the description page of the target image needs a large amount of computing resources, the processing device in the embodiment of the present application is taken as the cloud server for illustration.

[0060] For example, in order to facilitate the user to upload the description page of the target object, an interactive interface can be provided to the user, as shown in FIG. 8, the user can click the "select page" button to determine the description page to be uploaded, and click the "upload" button to upload the description page to the cloud server for processing. In addition, in order to facilitate the user to confirm whether the selected description page is the description page of the target object to be processed, the selected description page of the target object can be displayed in the "page display" area, and the user can click the "upload" button to upload the data after confirming that the selected description page is correct. Figure 3

[0061] It should be noted that the client and the cloud server can interact through a specific interface, the client can transmit the selected description page of the target object to the interface function as a parameter of the interface, so as to achieve the purpose of uploading the description page of the target object to the cloud server.

[0062] Step S204, determining whether the original image is the target image based on the original image or the description information.

[0063] The target image is an image that causes visual discomfort.

[0064] In an alternative embodiment, a pre-trained first classification model can be used to classify the original image, so as to determine whether the original image is the target image.

[0065] ​In another optional embodiment, the description information can be classified by using a pre-trained second classification model to determine whether the description information is information describing the target image, so as to determine whether the original image is the target image.

[0066] In another optional embodiment, the classification results of the first classification model and the second classification model can be combined to determine whether the original image is the target image.

[0067] For example, if any one of the first classification model and the second classification model determines that the original image is the target image, it is determined that the original image is the target image; if neither of the first classification model and the second classification model determines that the original image is the target image, it is determined that the original image is not the target image.

[0068] For example, if any one of the first classification model and the second classification model determines that the original image is not the target image, it is determined that the original image is not the target image; if both of the first classification model and the second classification model determine that the original image is the target image, it is determined that the original image is the target image.

[0069] In another optional embodiment, the target image can be an image in a product introduction page of an insect repellent, cockroach medicine, etc. to be sold on an e-commerce shopping platform, for example, a type of insect image, a scene effect image after using the product, etc., wherein the type of insect image generally contains a large number of insects or specific structures of the insects, and the scene effect image contains a large number of images of dead insects, which generally causes some users to have visual discomfort. The target image can also be an image of a rat poison or other images that cause users to feel uncomfortable in vision on an e-commerce shopping platform.

[0070] In another optional embodiment, the target image can be an image in a product or disease description page in a medical diagnosis webpage or a medical encyclopedia webpage, for example, a skin pathology image or a type of bacteria image, wherein the skin pathology image generally contains skin symptoms of a patient, and the bacteria in the type of bacteria image are generally dense, which generally causes some users to have visual discomfort.

[0071] In yet another optional embodiment, the target image can be a crime scene image in a news webpage, for example, a corpse image or a murder weapon image, wherein the corpse and the murder weapon in the corpse image and the murder weapon image cause people to have a sense of fear, and if a user sees such an image, he or she generally has visual and psychological discomfort.

[0072] In step S206, if the original image is the target image, a target replacement image corresponding to the original image is obtained.

[0073] The target replacement image in the above step can be a target cartoon image corresponding to the original image, such as a cartoon font, a cartoon image, a sketch, etc.

[0074] In an optional embodiment, the target replacement image can be a target vector image with the same contour as the original image, so that the user can roughly understand the content displayed in the original image according to the vector image; the target replacement image can also be a mosaic, so that the user can roughly understand the information in the original image according to the mosaic; the target replacement image can also be an expression package, so that the user can view a more interesting image during browsing, improving the user's browsing interest.

[0075] In an optional embodiment, the target replacement image can be directly generated according to the original image.

[0076] For example, feature points in the original image can be extracted by a feature extraction network, and then the target replacement image can be generated based on the obtained feature points. Specifically, if the original image is a bug image, the contour features of the bug in the image can be extracted by the feature extraction network, and then a drawing program can be used to cartoon draw according to the contour features of the bug, so as to obtain the target replacement image of the bug.

[0077] In another optional embodiment, the target replacement image corresponding to the target image can be selected from a replacement image gallery.

[0078] For example, if the original image is a type diagram of a bug or a structure diagram of a bug, a cartoon image of a bug can be selected as the target replacement image from the replacement image gallery, so that when the user sees the target replacement image, the content information of the original image expressed in the target replacement image can be clearly expressed as a bug, and the user can be prompted about the information expressed in the original image while reducing visual discomfort.

[0079] For example, if the original image is a skin pathology diagram or a type diagram of bacteria, a replacement image of skin or bacteria can be selected as the target replacement image from the replacement image gallery, so that when the user sees the target replacement image, the content information of the original image expressed in the target replacement image can be clearly expressed as skin pathology and bacteria, and the user can be prompted about the information expressed in the original image while reducing visual discomfort.

[0080] For example, if the original image is a crime scene image in a news webpage, a cartoon scene image corresponding to the crime scene can be selected from the image gallery as the target replacement image. For example, if the crime scene is a school, a cartoon scene image of the school can be selected as the target replacement image, so that the user can clearly understand that the original image represents an event occurring in the school when seeing the target replacement image. In this way, the user's visual discomfort can be reduced, and the information represented in the original image can be prompted to the user.

[0081] In another optional embodiment, if there is no target replacement image corresponding to the original image when the original image is the target image, a pre-set cartoon image can be used as the target replacement image to ensure that the target replacement image can be obtained for replacement, thereby improving the user's browsing experience.

[0082] In step S208, the original image is replaced by the target replacement image to obtain a processed description page.

[0083] In an optional embodiment, the original image in the description page can be replaced by the target replacement image to shield the image causing the user's visual discomfort and increase the user's browsing experience of the description page.

[0084] In another optional embodiment, the target replacement image can be overlaid on the original image. When the user slides or clicks the target replacement image, the original image can be displayed, so that the user can view the original image at any time when the user needs to understand the specific content of the original image.

[0085] Further, a line of text can be displayed near the target replacement image to remind the user that the original image can be displayed by clicking or sliding, so as to avoid the user's visual discomfort caused by mistakenly touching the target replacement image.

[0086] For example, "click to view the original image" or "slide to view the original image" can be displayed around the target replacement image, such as above, below, left, right, or inside the target replacement image, to achieve the effect of prompting the user to view.

[0087] In another optional embodiment, after obtaining the processed description page, the user can be prompted that the original image has been processed, so that the user can browse the description page with peace of mind. The user can be prompted that the original image has been processed by voice prompt, text prompt box, or the like. The specific prompting manner is not limited herein.

[0088] In another alternative embodiment, if the original image is not successfully replaced, the user can also be prompted that the original image is not processed, so that the user is prepared for the original image not to be replaced, or the user is reminded to replace the original image again, so as to avoid the user's visual discomfort caused by seeing the original image, thereby improving the user's experience of browsing the description page.

[0089] In another alternative embodiment, taking a live scene as an example, the target object can be a face in the live scene, a video frame in which the face image exists can be obtained, and it is determined from the video frame whether the face image is a target face image. The target face image can be the face image of a staff member who mistakenly enters the live scene, or the face image of a mysterious guest in the live scene. In the case where the face image is a target face image, a target replacement image corresponding to the face image is obtained, the face image is replaced with the target replacement image, and the target replacement image can be a sticker, a mosaic, a cartoon face image corresponding to the face image, etc. Then, the processed video frame is obtained and displayed to ensure that the identity information of the staff member and the mysterious guest is not disclosed in the live video.

[0090] In another alternative embodiment, taking a conference scene as an example, the target object can be a face of a participant. A video frame in which a face image of a participant exists can be obtained, and it is determined from the video frame whether the face image of the participant includes a face image of a target participant. The face image of the target participant can be that of a host or an important guest. In the case where the face image of the participant is that of the target participant, identification information image corresponding to the face image of the participant is obtained, and the identification information image can be an image of information such as name and position. The identification information image is placed above or below the face image of the target participant. By identifying the host or the important guest, the participants can smoothly conduct the conference.

[0091] In another alternative embodiment, taking an education scene as an example, the target object can be text in a teaching video. The text in the teaching video can be obtained, and it is determined according to attribute information of the text, such as shape, size, color, etc., whether the text is a target text. In the case where the text is a target text, a target replacement image corresponding to the text is obtained, and the target replacement image is used to obscure the text to obtain a processed teaching video. The target text is text that needs to be obscured. The user can complete the question provided in the teaching scene under the condition that the target text is obscured. When the user completes the question, the answer corresponding to the question can be obtained by clicking the obscured part, so that the user can check the answer after independently completing the question. The target replacement image can be a color palette of various colors or an opaque prompt box, etc.

[0092] In another optional embodiment, taking a medical scenario as an example, the target object can be a medical diagnosis page of disease morphology, wherein the medical diagnosis page contains an original image of disease morphology and description information of the original image. In a case where the original image is determined to be the target image based on the original image or the description information, it is illustrated that the original image can cause visual discomfort of the user. At this time, the original image in the medical diagnosis page needs to be processed in order to reduce the visual discomfort of the user. For example, the original image in the medical diagnosis page can be replaced by a target replacement image corresponding to the original image. Specifically, the bacteria in the medical diagnosis page can be replaced by a cartoon image of the bacteria, so as to reduce the visual discomfort of the user and remind the user of the information to be conveyed by the original image.

[0093] In yet another optional embodiment, taking a game scenario as an example, the target object can be an action page of a character image in the game. The description page contains a current action image corresponding to the character image and description information of the action image. Whether the current action image is a target action image is determined based on the current action image or the description information, wherein the target action image is an image that causes visual discomfort to a younger user, for example, a fighting image. In a case where the current action image is the target action image, a target replacement image corresponding to the current action image is obtained, and the current action image is replaced by the target replacement image, thereby obtaining a processed action page. The current action image can be replaced by a cartoon image of an animal or a cartoon character image, so as to reduce the visual discomfort of the younger user, thereby providing a good game environment for the younger user.

[0094] By the above steps of the present application, first, the description page of the target object is acquired, wherein the description page contains the original image corresponding to the target object and the description information of the original image, and then whether the original image is a target image with visual discomfort is determined based on the original image or the description information. In the case where the original image is a target image, the target replacement image corresponding to the original image is acquired, the original image is replaced by the target replacement image, and the processed description page is obtained, thereby realizing processing of the target image with visual discomfort to improve the browsing experience of the user. It is easy to note that after the description page of the target object is acquired, whether the original image will affect the user's visual experience can be determined according to the image content and the description information of the original image. In the case where it is determined that the original image will affect the user's visual experience, the original image is replaced by the target replacement image corresponding to the original image, which can avoid the original image causing discomfort to the user's vision. Since the target replacement image and the original image express the same content but have different forms, the target replacement image can be used to display the information expressed by the original image while improving the user's browsing experience, thereby solving the technical problem that the original image that will cause the user's visual discomfort is directly displayed to the user, thereby affecting the user's browsing experience.

[0095] In the above embodiments of the present application, determining whether the original image is a target image based on the original image or the description information includes one of the following: using a first classification model to identify the original image to determine whether the original image is a target image; using a second classification model to identify the description information of the original image to determine whether the original image is a target image; detecting whether a first preset operation is performed on the original image to determine whether the original image is a target image.

[0096] The first classification model in the above steps is used to identify and classify images, and the second classification model in the above steps is used to identify and classify texts.

[0097] In an optional embodiment, the first classification model can be a model such as a convolutional neural network, an image classifier, etc. that can identify images, and can also be another neural network set according to the user's needs. The second classification model can be a model such as a convolutional neural network, a text classifier, etc. that can identify texts, and can also be another neural network set according to the user's needs.

[0098] In another optional embodiment, a large number of sample images with annotations can be used to train an original classification model, thereby obtaining a first classification model that can identify and classify images. A large number of sample texts can be used to train an original classification model, thereby obtaining a second classification model that can identify and classify texts corresponding to the original image.

[0099] In another alternative embodiment, the first classification model can be used to identify and classify the original image. Specifically, the first classification model can first extract image features of the original image, and then determine whether the original image is an image that causes the user to have a visual discomfort by analyzing and comparing the image features. If it is determined that the original image is an image that causes the user to have a visual discomfort, the original image is determined to be the target image, otherwise, the original image can be determined to be other images. The second classification model can be used to identify the description information of the original image. Specifically, the second classification model can first extract text features in the description information, and then determine whether the description information is description information of an image that causes the user to have a visual discomfort by analyzing and comparing the text features. If it is determined that the description information is description information of an image that causes the user to have a visual discomfort, the original image corresponding to the description information is determined to be the target image.

[0100] The first preset operation in the above step can be a click button, control, hyperlink, etc. operation. Specifically, the image that causes the user to have a visual discomfort can be replaced by clicking the button, control, hyperlink, etc.

[0101] In an alternative embodiment, it can be detected whether the user performs the first preset operation. If the user performs the first preset operation, it indicates that the original image in the current description page causes the user to have a visual discomfort. At this time, the original image can be determined to be the target image according to the first preset operation, so as to replace the original image with the target replacement image, thereby improving the user's experience of browsing the page.

[0102] It should be noted that after the user performs the first preset operation, the operation can be recorded, so that when the user views a similar page again, the original image in the page can be directly replaced with the target replacement image, avoiding repeated user operations.

[0103] In the above embodiment of the present application, the first classification model is trained by a plurality of first samples, wherein each first sample includes a training image and an image label corresponding to the training image. The image label is obtained by any one of the following methods: based on a plurality of users labeling the training image; based on a target user labeling the training image; and based on the browsing behavior data of the target user.

[0104] The image label in the above step is used to distinguish whether the image is an image that causes the user to have a visual discomfort, wherein the image label can be an uncomfortable image or other images.

[0105] In an optional embodiment, multiple users can be obtained to label each training image, and the image label of the training image can be determined based on the multiple labeling results. Specifically, the labeling result can be an uncomfortable image or other images. Multiple users can be obtained to label the same training image. If more than half of the users label the training image as an uncomfortable image, the image label of the training image is determined as an uncomfortable image. If more than half of the users label the training image as other images, the image label of the training image is determined as other images.

[0106] For example, the multiple users can be multiple labeling personnel. Ten labeling personnel can be used to label each training image, and the image label of each training image can be determined. If more than five users think that a certain training image will cause visual discomfort of the user, the training image is considered to be an image that causes visual discomfort of the user. In this case, the image label of the training image is determined as an uncomfortable image. If less than five users think that a certain training image will not cause visual discomfort of the user, the training image is considered to not cause visual discomfort of the user. In this case, the image label of the training image is determined as other images.

[0107] The target user in the above steps can be a labeling personnel or a user who needs to browse the image description page.

[0108] In another optional embodiment, the image label of the training image can be obtained by the target user. If the target user thinks that the training image will cause discomfort, the image label of the training image is determined as an uncomfortable image. If the target user thinks that the training image will not cause discomfort, the image label of the training image is determined as other images. In this way, the target user can perform targeted image labeling on the training image, so that the first classification model trained by the training image is more in line with the browsing habits of the target user.

[0109] In yet another optional embodiment, the browsing behavior data of the target user can be obtained, and the browsing behavior data of the target user can be analyzed to obtain the browsing habits of the target user. The image label of the training image can be determined according to the browsing habits of the target user.

[0110] For example, when browsing a webpage, the target user generally screens out pictures of centipedes, caterpillars, and the like. In this case, if the training image includes images of centipedes, caterpillars, and the like, the image label of such training image can be set as an uncomfortable image.

[0111] In the above embodiments of the present application, the second classification model is obtained by training the second preset model based on a plurality of second samples, wherein each of the plurality of second samples comprises description information of a training image and a description label corresponding to the description information, and the description label is obtained in any one of the following manners: based on a plurality of users labeling the description information of the training image; based on a target user labeling the description information of the training image; and based on browsing behavior data of the target user.

[0112] The description label in the above step is used to distinguish whether the description of the training image is a description of an image that causes visual discomfort of a user, wherein the description label can be an uncomfortable description or another description.

[0113] In an optional embodiment, a plurality of users can label the description information corresponding to each training image, and a description label of the description information corresponding to the training image is determined based on the plurality of labeling results. Specifically, the labeling result can be an uncomfortable description or another description. A plurality of users can label the description information corresponding to the same training image, and if more than half of the users label the description information corresponding to the training image as an uncomfortable description, it is determined that the description label of the description information corresponding to the training image is an uncomfortable description. If less than half of the users label the description label of the description information corresponding to the training image as another description, it is determined that the description label of the description information corresponding to the training image is another description.

[0114] For example, the plurality of users can be a plurality of labeling personnel. Ten labeling personnel can label the description information of each training image, and then determine the description label of the description information corresponding to each training image. If more than five of the labeling personnel believe that a certain training image causes visual discomfort of a user, it is determined that the description information corresponding to the training image is an uncomfortable description. If less than five of the labeling personnel believe that a certain training image does not cause visual discomfort of a user, it is determined that the training image does not cause visual discomfort of a user, and the description label of the description information corresponding to the training image is another description.

[0115] Further, if more than five of the labeling personnel believe that the description information corresponding to a certain training image is used to describe content of an image that causes visual discomfort of a user, it is determined that the description information corresponding to the training image is an uncomfortable description. If less than five of the labeling personnel believe that the description information corresponding to a certain training image is not used to describe content of an image that causes visual discomfort of a user, it is determined that the description information corresponding to the training image is another description.

[0116] In another optional embodiment, the target user can be asked to mark the description of the description information corresponding to the training image. If the target user thinks that the training image will cause discomfort, the description of the description information corresponding to the training image is marked as discomfort description. If the target user thinks that the training image will not cause discomfort, the description of the description information corresponding to the training image is marked as other description. Thus, the target user can mark the description of the training image, so that the second classification model trained by the description information of the training image is more in line with the browsing habits of the target user.

[0117] In another optional embodiment, the browsing behavior data of the target user can be obtained, and the browsing behavior data of the target user can be analyzed to obtain the browsing habits of the target user, so that the description information corresponding to the training image is marked according to the browsing habits of the target user.

[0118] For example, when the target user browses a webpage, the target user generally shields pictures of centipedes and caterpillars. At this time, if the training image includes images of centipedes and caterpillars, the description information corresponding to the training image can be marked as discomfort description.

[0119] In another optional embodiment, the description information of the training image can be marked according to the image annotation of the training image by multiple users. If the image annotation is discomfort image, the corresponding description annotation is discomfort description. If the image annotation is other image, the corresponding description annotation is other description.

[0120] In another optional embodiment, the description information of the training image can be marked according to the image annotation of the training image by the target user. The image annotation of the training image can also be determined according to the browsing behavior data of the target user, so that the description annotation is determined according to the image annotation.

[0121] In the above embodiments of the present application, whether the first preset operation on the original image exists is detected, and whether the target image exists in the description page is determined. If the first preset operation exists, the original image is determined to be the target image. If the first preset operation does not exist, the original image is determined to be not the target image.

[0122] The first preset operation in the above step is used to provide a flexible method for the user to shield the target image.

[0123] In an optional embodiment, if the first preset operation is detected, it indicates that the user has seen the target image causing visual discomfort, and the target image needs to be processed as soon as possible to reduce the user's visual discomfort. If the first preset operation is not detected during the user's browsing, it indicates that the image in the page does not affect the user, and it can be determined that the original image is not the target image, and the replacement operation of the original image is not needed, and the consumption of the running resources can be reduced.

[0124] In the above embodiment of the present application, obtaining the target replacement image corresponding to the original image comprises: matching the original image with a plurality of preset replacement images to obtain the target replacement image.

[0125] The plurality of preset replacement images in the above step can be set by the user in advance, or can be replacement images regularly crawled in the webpage by using a crawler software.

[0126] In an optional embodiment, after determining that the original image is the target image, the original image can be matched with a plurality of preset replacement images in a replacement image library, the preset replacement image with the highest matching degree is determined, and the preset replacement image with the highest matching degree is taken as the target replacement image, so that the target replacement image can indicate the information expressed in the original image, and the user can understand the information expressed in the original image while reducing the user's visual discomfort.

[0127] In the above embodiment of the present application, the original image and the plurality of preset replacement images are matched by using a matching model to obtain the target replacement image, wherein the matching model is obtained by training a third preset model by a plurality of image sets, and the plurality of image sets are generated based on image annotations of the target image and image annotations of the plurality of preset replacement images.

[0128] In an optional embodiment, the matching model can extract features of the original image and the plurality of preset replacement images, and match the original image and the plurality of preset replacement images by calculating the feature similarity between the features of the original image and the plurality of preset replacement images, if the similarity is higher, the matching degree is higher, and if the similarity is lower, the matching degree is lower.

[0129] Further, the matching degrees between the original image and the plurality of preset replacement images can be sorted from high to low, and the preset replacement image with the highest matching degree with the original image is selected as the target replacement image.

[0130] The third preset model in the above step can be a neural network model, and the matching model can be a trained neural network model.

[0131] The image label of the target image in the above step can be content information displayed by the target image. For example, the image label of a bug image can be a bug; and the image label of a skin disease image can be a skin disease. The image label of each of the plurality of preset replacement images in the above step can be content information displayed by the preset replacement image. For example, the image label of a replacement image of a bug can be a bug; and the image label of a replacement image of a skin disease can be a skin disease.

[0132] In another optional embodiment, the third preset model can be trained by the target image and the preset replacement image corresponding to the target image in each of the plurality of image sets, to obtain a matching model, so that the matching model can determine the target replacement image according to the target image. It should be noted that the target image and the plurality of preset replacement images can form a plurality of matching pairs, i.e., the plurality of image sets. In the process of training the third preset model by using the plurality of image sets, “matching” or “not matching” can be used as a supervision signal to train the third preset model.

[0133] In the above embodiments of the present application, the target replacement image is generated based on the original image in the case that the original image fails to match the plurality of preset replacement images.

[0134] In an optional embodiment, if the target replacement image corresponding to the target image is not matched by the matching model, the target replacement image can be generated based on image information of the original image or text information used to describe the original image.

[0135] In another optional embodiment, image features in the original image can be extracted, and the original image can be redrawn in a cartoon drawing manner according to the image features, so as to generate the target replacement image.

[0136] In yet another optional embodiment, text description information of the original image can be extracted, a plurality of replacement images corresponding to the text description information can be extracted from a webpage according to the text description information, and the replacement image with the highest matching degree can be determined as the target replacement image by matching the original image with the plurality of replacement images.

[0137] In the above embodiments of the present application, the original image is processed by using the generation model to generate the target replacement image, wherein the generation model is obtained by training a fourth preset model by using a plurality of third samples, and the plurality of third samples are generated based on the target image and the plurality of preset replacement images, or are generated based on description information of the target image and the plurality of preset replacement images.

[0138] The fourth preset model in the above step can be a neural network model, and the plurality of third samples can be used to train the neural network model, so as to obtain the generation model.

[0139] In an optional embodiment, the target image and the preset replacement image matched with the target image can be taken as a third sample, the fourth preset model is trained by multiple groups of third samples, and a generation model is obtained, so that the generation model can generate a target replacement image corresponding to the original image according to the corresponding relationship between the target image and the preset replacement image in each group of third samples.

[0140] In another optional embodiment, the description information of the target image and the preset replacement image matched with the description information can be taken as a third sample, the fourth preset model is trained by multiple groups of third samples, and a generation model is obtained, so that the generation model obtained by training can generate a target replacement image corresponding to the description information of the original image according to the corresponding relationship between the description information and the preset replacement image in each group of third samples.

[0141] In the above embodiments of the present application, after the original image is replaced by the target replacement image to obtain the processed description page, the method further comprises: obtaining prompt information corresponding to the target replacement image, wherein the prompt information is used to prompt a second preset operation of displaying the original image; and adding the prompt information to the processed description page.

[0142] In an optional embodiment, when the processed description page is obtained, the prompt information prompting the user to view the original image can be added below the target replacement image, and if the user needs to view the original image corresponding to the target replacement image, the second preset operation is performed according to the operation method displayed in the prompt information, so that the user can view the original image corresponding to the target replacement image.

[0143] The prompt information in the above step can be “click here to display the original image” or “slide here to display the original image”. The prompt information can also be a label of the original image, for example, if the original image is a bug, the prompt information can record the bug, so as to remind the user that the original image is a bug image.

[0144] The second preset operation in the above step can be clicking the target replacement image, sliding the target replacement image, etc., but is not limited thereto, and can also be a pre-set gesture operation.

[0145] In the above embodiments of the present application, after the second preset operation is detected, the target replacement image is replaced by the original image to obtain the description page.

[0146] In an optional embodiment, after the second preset operation is detected, the target replacement image can be replaced by the original image, and the processed description page is restored, so that the user can clearly and intuitively understand the image information of the original image according to the user's demand.

[0147] The following will be described in combination with Figure 4A preferred embodiment of the present application is described in detail. The method can be executed by a mobile terminal or a server. In the embodiment of the present application, the method is executed by the server as an example. As shown in Figure 4 The method can include the following steps:

[0148] Step S401, obtaining an original image and description information of the original image;

[0149] Step S402, identifying the original image by a first classification model and identifying the description information of the original image by a second classification model;

[0150] Step S403, determining whether the original image is a target image according to the classification result of the first classification model and the classification result of the second classification model. If the original image is the target image, step S404 is executed. If the original image is not the target image, step S408 is executed.

[0151] Step S404, matching the original image with a plurality of preset replacement images and determining whether the matching is successful. If the matching is successful, step S405 is executed. If the matching fails, step S406 is executed.

[0152] Step S405, determining a target replacement image corresponding to the original image from the plurality of preset replacement images, and executing step S407;

[0153] Step S406, generating the target replacement image according to the original image by using a generation model, and executing step S407;

[0154] Step S407, replacing the original image with the target replacement image;

[0155] Optionally, the original image can be hidden and displayed. Specifically, the image that is easy to cause visual discomfort is displayed in a corresponding comic form, and an interactive mode is designed to display the original image.

[0156] For example, the target replacement image can be a target comic image. The display interface after replacing the original image with the target comic image can be as shown in Figure 5 wherein the original image can be an image of a corpse, the upper part of the display interface can be a comic image of the corpse, and the text box in the lower part of the display interface displays an explanation of the original image and prompt information for clicking to display the original image. When the user needs to view the original image to understand more information, the prompt information can be clicked. At this time, the original image of the corpse can be overlaid on the comic image to meet the viewing needs of the user, as shown on the right side of Figure 5 The right side of the display interface is shown.

[0157] Step S408, directly displaying the original image.

[0158] As shown in Figure 6 The structure block diagram of image processing is shown. First, the original image or the description information of the original image is input into the classification network. The original image and the corresponding description information of the original image are identified through the classification network, so as to determine that the original image is an inappropriate image or a remaining image. The classification network can be composed of a first classification model and a second classification model. The first classification model is used for classifying the original image, and the second classification model is used for classifying the description information of the original image. When it is determined that the original image is a remaining image, it can be directly output and displayed. When it is determined that the original image is an inappropriate image, the inappropriate image and the comic image in the comic image library can be matched through the matching network. If the matching is successful, the original image is replaced with the target comic image in the comic image library, and the original image is hidden. If the matching fails, a target comic image corresponding to the original image is generated by using the generation model, and the original image is hidden. It should be noted that Figure 6 The classification network in Figure 6 can be set according to the preferences of the user. For example, the user has a visual discomfort for insects and dense images. The classification network can be trained to determine that the original image with insect points or the original image with dense images is an inappropriate image.

[0159] Among them, Figure 6 The comic images in the comic image library in Figure 6 can be crawled through the network. The comic images in the network can be crawled according to the description information of the images that make the user feel visually uncomfortable. For example, the comic images labeled with the words such as “caterpillar” and “centipede” can be searched in the network. If the crawled comic images do not match the description information, the annotation information of the comic images can be modified in an artificial way.

[0160] Among them, in the process of training the classification network in Figure 6 , the target user or the annotation personnel can perform image annotation or description annotation on the training image according to their own visual feelings of the training image. The training image can be annotated as an inappropriate image or other images according to the image annotation and the description annotation. The first preset model is classified by using the image annotation to obtain the first classification model. The second preset model is classified by using the description annotation to obtain the second classification model. The first classification model and the second classification model are combined to obtain the classification network. In the process of testing the classification network, the first classification model and the second classification model in the classification network can be adjusted according to the preferences of the user and the browsing records of the user, so that the classification network can classify the original image according to the habits of the user.

[0161] Among them, in the process of training the classification network in Figure 6In the matching network process, multiple pre-defined replacement image pairs can be randomly generated based on the image annotations of the comic images and the inappropriate images, serving as training samples. These training samples are then used to train a third pre-defined model, thus obtaining the matching network. The third pre-defined model can be trained using "match" or "mismatch" as supervisory signals. Specifically, image pairs can be input into the third pre-defined network; if the image annotations in the image pair are the same, the two images in the pair are considered a match; if the image annotations are different, the two images in the pair are considered a mismatch. When testing the trained matching network, multiple pre-defined replacement image pairs can be generated by combining the inappropriate image with all images in the comic image library. The matching network can then determine whether the two images in these pre-defined replacement image pairs match. If the matching network successfully determines that the two images in the pairs match, the matching network training is considered successful.

[0162] Among them, in training Figure 6 In the process of generating the network, a fourth preset network can be trained based on inappropriate images or their descriptive information, as well as a comic image library, to obtain the generating network. Specifically, training samples can be generated based on inappropriate images and a comic image library, or training samples can be generated based on the descriptive information of inappropriate images and a comic image library, and the resulting training samples can be used to train the fourth preset network to obtain the generating network. When testing the generating network, corresponding comic images can be generated based on inappropriate images that fail to match or their descriptive information.

[0163] Through the above steps, extensive user annotations can be used when collecting visually uncomfortable training images, incorporating user preferences and overcoming the one-size-fits-all image discrimination methods in related technologies. Furthermore, by replacing the original images that cause visual discomfort with replacement images, visual discomfort can be reduced while still conveying the information intended by the original images. Additionally, the original images can be retained; users can click to replace the original image and display it, preserving the integrity of the information. The interactive method of retaining the original image allows users to flexibly view it.

[0164] The classification network, matching network, and generator network in the above steps can be existing neural networks; there are no restrictions on the type of neural network here.

[0165] It should be noted that, for the sake of simplicity, the foregoing method embodiments are all described as a series of actions. However, those skilled in the art should understand that this application is not limited to the described order of actions, as some steps may be performed in other orders or simultaneously according to this application. Furthermore, those skilled in the art should also understand that the embodiments described in the specification are preferred embodiments, and the actions and modules involved are not necessarily essential to this application.

[0166] Through the description of the above embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be realized by means of software on a general hardware platform as necessary, and of course can also be realized by hardware, but in many cases the former is a better embodiment. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product in essence or in the form of a part of the prior art that makes a contribution. The computer software product is stored in a storage medium (such as a ROM / RAM, a magnetic disk, or an optical disk) and includes a plurality of instructions for causing a terminal device (which can be a mobile phone, a computer, a server, or a network device) to execute the method of each embodiment of the present application.

[0167] Embodiment 2

[0168] According to the embodiments of the present application, an image processing method embodiment is also provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0169] Figure 7 is a flowchart of an image processing method according to an embodiment of the present application. As shown in Figure 7 , the method can include the following steps:

[0170] Step S702, obtaining a description page of a target object.

[0171] The description page contains the original image corresponding to the target object and the description information of the original image.

[0172] Step S704, in the case where it is determined that the original image is a target image based on the original image or the description information, obtaining a target replacement image corresponding to the original image.

[0173] The target image is an image that is visually uncomfortable.

[0174] Step S706, displaying the processed description page.

[0175] The processed description page is a page obtained by replacing the original image with the target replacement image.

[0176] In the above embodiments of the present application, determining whether the original image is the target image based on the original image or the description information comprises one of: identifying the original image using a first classification model to determine whether the original image is the target image; identifying the description information of the original image using a second classification model to determine whether the original image is the target image; detecting whether a first preset operation is performed on the original image, and determining whether the original image is the target image based on a detection result.

[0177] In the above embodiments of the present application, obtaining the target replacement image corresponding to the original image comprises: matching the original image with a plurality of preset replacement images to obtain the target replacement image.

[0178] It should be noted that the preferred embodiments involved in the above embodiments of the present application have the same application scenarios and implementation processes as the schemes provided in Embodiment 1, but are not limited to the schemes provided in Embodiment 1.

[0179] Embodiment 3

[0180] According to the embodiments of the present application, an image processing method embodiment is also provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although a logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown herein.

[0181] Figure 8 is a flowchart of an image processing method according to Embodiment 3 of the present application. As shown in Figure 8 , the method can include the following steps:

[0182] Step S802, receiving a description page of a target object.

[0183] The description page contains an original image corresponding to the target object and description information of the original image.

[0184] In an optional embodiment, the description page of the target object can be processed in a mobile terminal, a computer terminal, a cloud server, or the like. In the present application, a cloud server is taken as an example for illustration.

[0185] Illustratively, the description page of the target object can be processed in the cloud server, and the cloud server can receive the description page of the target object.

[0186] Step S804, determining whether the original image is the target image based on the original image or the description information.

[0187] The target image is an image that has visual discomfort.

[0188] In an optional embodiment, whether the original image is the target image can be determined based on the original image or the description information in the cloud server.

[0189] In step S806, if the original image is the target image, a target replacement image corresponding to the original image is obtained.

[0190] In an optional embodiment, if the original image is the target image, a target replacement image corresponding to the original image can be obtained in the cloud server.

[0191] In step S808, the original image is replaced by the target replacement image to obtain a processed description page.

[0192] In an optional embodiment, the original image can be replaced by the target replacement image in the cloud server to obtain a processed description page.

[0193] In step S810, the processed description page is output.

[0194] In an optional embodiment, the processed description page can be output to a device used by the user through the cloud server.

[0195] In the above embodiments of the present application, determining whether the original image is the target image based on the original image or the description information includes one of the following: identifying the original image using a first classification model to determine whether the original image is the target image; identifying the description information of the original image using a second classification model to determine whether the original image is the target image; detecting whether a first preset operation is performed on the original image, and determining whether the original image is the target image based on the detection result.

[0196] In the above embodiments of the present application, obtaining the target replacement image corresponding to the original image includes matching the original image with a plurality of preset replacement images to obtain the target replacement image.

[0197] It should be noted that the preferred embodiments involved in the above embodiments of the present application have the same scheme, application scenario and implementation process as provided in Embodiment 1, but are not limited to the scheme provided in Embodiment 1.

[0198] Embodiment 4

[0199] According to the embodiments of the present application, an image processing method embodiment is also provided. It should be noted that the steps shown in the flowchart of the drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described can be executed in an order different from that shown here.

[0200] Figure 9is a flowchart of an image processing method according to Embodiment 4 of the present application. As shown in Figure 9 the method can include the following steps:

[0201] Step S902, obtaining a description page of a product.

[0202] The description page contains an original image of the product and description information of the original image.

[0203] The product in the above steps can be a commodity to be sold on an e-commerce platform, such as an insect repellent, a cockroach medicine, etc.

[0204] Step S904, determining whether the original image is a target image based on the original image or the description information.

[0205] The target image is an image that is visually uncomfortable.

[0206] In an optional embodiment, if the product is an insect repellent, the description page can be a description of the precautions and use effect of the insect repellent. According to the original image and the description information of the insect repellent, it can be determined that the original image corresponding to the insect repellent is a visually uncomfortable insect image.

[0207] Step S906, obtaining a target replacement image corresponding to the original image in the case where the original image is a target image.

[0208] In an optional embodiment, in the case where the original image is an insect image, an insect replacement image corresponding to the insect image can be obtained to reduce the discomfort caused by the insect image to the user's vision.

[0209] Step S908, replacing the original image with the target replacement image to obtain a processed description page.

[0210] In an optional embodiment, the insect image can be replaced with the insect replacement image to obtain a processed description page to improve the user's browsing experience.

[0211] In the above embodiments of the present application, determining whether the original image is a target image based on the original image or the description information includes one of the following: using a first classification model to identify the original image to determine whether the original image is a target image; using a second classification model to identify the description information of the original image to determine whether the original image is a target image; detecting whether a first preset operation is performed on the original image, and determining whether the original image is a target image based on the detection result.

[0212] In the above embodiments of the present application, obtaining a target replacement image corresponding to the original image includes matching the original image with a plurality of preset replacement images to obtain a target replacement image.

[0213] It should be noted that the preferred embodiments involved in the above embodiments of the present application have the same application scenarios and implementation processes as the schemes provided in Embodiment 1, but are not limited to the schemes provided in Embodiment 1.

[0214] Embodiment 5

[0215] According to the embodiments of the present application, an image processing method embodiment is further provided. It should be noted that the steps shown in the flowchart of the accompanying drawings can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown herein.

[0216] Figure 10 is a flowchart of an image processing method according to Embodiment 5 of the present application. As shown in Figure 10 , the method can include the following steps:

[0217] Step S1002, receiving a description page of a target object by calling a first interface.

[0218] The first interface includes a first parameter, and the parameter value of the first parameter is a description page, and the description page contains an original image corresponding to the target object and description information of the original image.

[0219] The first interface in the above steps can be an interface for data interaction between a cloud server and a client. The client can pass the description page of the target image into the interface function as the first parameter of the interface function, so as to achieve the purpose of uploading the description page of the target object to the cloud server.

[0220] Step S1004, determining whether the original image is a target image based on the original image or the description information.

[0221] The target image is an image that has visual discomfort.

[0222] In an optional embodiment, the first classification model and the second classification model can be deployed in the cloud server in advance. After receiving the description page of the target object uploaded by the client, the cloud server can use the first classification model to identify whether the original image corresponding to the target object is a target image based on the original image; and can use the second classification model to identify whether the original image corresponding to the target object is a target object based on the description information of the original image.

[0223] Step S1006, obtaining a target replacement image corresponding to the original image in the case where the original image is a target image.

[0224] At step S1008, the original image is replaced by the target replacement image to obtain a processed description page.

[0225] At step S1010, the processed description page is output by calling the second interface.

[0226] The second interface includes a second parameter, and a parameter value of the second parameter is the processed description page.

[0227] The second interface in the above steps can be an interface for data interaction between the cloud server and the client. The cloud server can pass the processed description page into an interface function as a second parameter of the interface function to achieve the purpose of distributing the processed description page to the client.

[0228] In the above embodiments of the present application, determining whether the original image is the target image based on the original image or the description information includes one of the following: identifying the original image by using a first classification model to determine whether the original image is the target image; identifying the description information of the original image by using a second classification model to determine whether the original image is the target image; detecting whether a first preset operation is performed on the original image, and determining whether the original image is the target image based on the detection result.

[0229] In the above embodiments of the present application, obtaining the target replacement image corresponding to the original image includes matching the original image with a plurality of preset replacement images to obtain the target replacement image.

[0230] It should be noted that the preferred implementation schemes involved in the above embodiments of the present application have the same application scenarios and implementation processes as the schemes provided in Embodiment 1, but are not limited to the schemes provided in Embodiment 1.

[0231] Embodiment 6

[0232] According to the embodiments of the present application, an image processing device for implementing the above image processing method is also provided, as shown in the figure, the device 1100 includes a first acquisition module 1102, a determination module 1104, a second acquisition module 1106 and a replacement module 1108. Figure 11

[0233] The first acquisition module 1102 is configured to acquire a description page of a target object, wherein the description page contains an original image corresponding to the target object and description information of the original image; the determination module 1104 is configured to determine whether the original image is a target image based on the original image or the description information, wherein the target image is an image that visually causes discomfort; the second acquisition module 1106 is configured to acquire a target replacement image corresponding to the original image in the case that the original image is the target image; and the replacement module 1108 is configured to replace the original image with the target replacement image to obtain a processed description page.​

[0234] It should be noted that the first obtaining module 1102, the determining module 1104, the second obtaining module 1006 and the generating module 1108 correspond to steps S202 to S208 in Embodiment 1, and the four modules have the same instances and application scenarios as the corresponding steps, but are not limited to the disclosure of Embodiment 1. It should be noted that the above modules can run in the computer terminal 10 provided in Embodiment 1 as part of the device.

[0235] In the above embodiments of the present application, the determining module comprises: a first determining unit, a second determining unit and a third determining unit.

[0236] The first determining unit is configured to identify the original image by using the first classification model to determine whether the original image is the target image; the second determining unit is configured to identify the description information of the original image by using the second classification model to determine whether the original image is the target image; and the third determining unit is configured to detect whether the first preset operation on the original image exists to determine whether the original image is the target image.

[0237] In the above embodiments of the present application, the device further comprises: a first labeling module and a third obtaining module.

[0238] The first classification model is obtained by training the first preset model by using a plurality of first samples, wherein each first sample comprises a training image and image labeling corresponding to the training image, the first labeling module is configured to label the training image based on a plurality of users to obtain the image labeling, the first labeling module is further configured to label the training image based on the target user to obtain the image labeling, and the third obtaining module is configured to obtain the image labeling based on the browsing behavior data of the target user.

[0239] In the above embodiments of the present application, the device further comprises: a second labeling module and a fourth obtaining module.

[0240] The second classification model is obtained by training the second preset model by using a plurality of second samples, wherein each second sample comprises description information of a training image and description labeling corresponding to the description information, the second labeling module is configured to label the description information of the training image based on a plurality of users to obtain the description labeling, the second labeling module is configured to label the description information of the training image based on the target user to obtain the description labeling, and the fourth obtaining module is configured to obtain the description labeling based on the browsing behavior data of the target user.

[0241] In the above embodiments of the present application, the third determining unit comprises: a first determining subunit and a second determining subunit.

[0242] The first determining sub-unit is configured to determine that the original image is the target image when it is detected that the first preset operation exists.

[0243] In the above embodiments of the present application, the second obtaining module comprises a matching unit.

[0244] The matching unit is configured to match the original image with the plurality of preset replacement images to obtain the target replacement image.

[0245] In the above embodiments of the present application, the matching unit comprises a matching sub-unit.

[0246] The matching sub-unit is configured to match the original image and the plurality of preset replacement images by using a matching model to obtain the target replacement image, wherein the matching model is obtained by training a third preset model based on a plurality of image sets, and the plurality of image sets are generated based on image labels of the target image and image labels of the plurality of preset replacement images.

[0247] In the above embodiments of the present application, the matching unit comprises a generating sub-unit.

[0248] The generating sub-unit is configured to generate the target replacement image based on the original image when the original image fails to match the plurality of preset replacement images.

[0249] In the above embodiments of the present application, the generating sub-unit comprises a processing sub-unit.

[0250] The processing sub-unit is configured to process the original image by using a generating model to generate the target replacement image, wherein the generating model is obtained by training a fourth preset model based on a plurality of third samples, and the plurality of third samples are generated based on the target image and the plurality of preset replacement images, or are generated based on description information of the target image and the plurality of preset replacement images.

[0251] In the above embodiments of the present application, the device further comprises a fifth obtaining module and an adding module.

[0252] The fifth obtaining module is configured to obtain prompt information corresponding to the target replacement image, wherein the prompt information is used to prompt a second preset operation of the original image; and the adding module is configured to add the prompt information to the processed description page.

[0253] In the above embodiments of the present application, the device further comprises a replacing module.

[0254] The replacing module is configured to replace the target replacement image with the original image to obtain the description page after detecting the second preset operation.

[0255] It should be noted that the preferred embodiments involved in the above embodiments of the present application have the same application scenarios and implementation processes as the schemes provided in Embodiment 1, but are not limited to the schemes provided in Embodiment 1.

[0256] Embodiment 7

[0257] According to the embodiments of the present application, an image processing device for implementing the above image processing method is further provided, as shown in the figure, the device 1200 includes: a first acquisition module 1202, a second acquisition module 1204, and a display module 1206. Figure 12

[0258] The first acquisition module 1202 is configured to acquire a description page of a target object, wherein the description page contains an original image corresponding to the target object and description information of the original image; the second acquisition module 1204 is configured to acquire a target replacement image corresponding to the original image in a case where it is determined that the original image is a target image based on the original image or the description information, wherein the target image is an image that is visually uncomfortable; and the display module 1206 is configured to display a processed description page, wherein the processed description page is a page obtained by replacing the original image with the target replacement image.

[0259] It should be noted that the first acquisition module 1202, the second acquisition module 1204, and the display module 1206 correspond to steps S702 to S706 in Embodiment 2, and the three modules have the same instances and application scenarios as the corresponding steps, but are not limited to the content disclosed in Embodiment 2. It should be noted that the above modules can run in the computer terminal 10 provided in Embodiment 1 as part of the device.

[0260] In the above embodiments of the present application, the device further includes a first identification module, a second identification module, and a detection module.

[0261] The first identification module is configured to identify the original image by using a first classification model to determine whether the original image is a target image; the second identification module is configured to identify the description information of the original image by using a second classification model to determine whether the original image is a target image; and the detection module is configured to detect whether there is a first preset operation performed on the original image, and determine whether the original image is a target image based on the detection result.

[0262] In the above embodiments of the present application, the second acquisition module includes a matching unit.

[0263] The matching unit is configured to match the original image with a plurality of preset replacement images to obtain the target replacement image.

[0264] ​It should be noted that the preferred embodiments involved in the above embodiments of the present application have the same scheme, application scenario and implementation process as provided in Embodiment 1, but are not limited to the scheme provided in Embodiment 1.

[0265] Embodiment 8

[0266] According to the embodiments of the present application, an image processing device for implementing the above image processing method is further provided, as shown in the figure, the device 1300 includes a receiving module 1302, a determining module 1304, an obtaining module 1306, a replacing module 1308, and an output module 1310. Figure 13

[0267] The receiving module 1302 is configured to receive a description page of a target object, wherein the description page contains an original image corresponding to the target object and description information of the original image; the determining module 1304 is configured to determine whether the original image is a target image based on the original image or the description information, wherein the target image is an image that is visually uncomfortable; the obtaining module 1306 is configured to obtain a target replacement image corresponding to the original image in the case that the original image is the target image; the replacing module 1308 is configured to replace the original image with the target replacement image to obtain a processed description page; and the output module 1310 is configured to output the processed description page.

[0268] It should be noted that the receiving module 1302, the determining module 1304, the obtaining module 1306, the replacing module 1308, and the output module 1310 correspond to steps S802 to S810 in Embodiment 3, and the five modules have the same instances and application scenarios as the corresponding steps, but are not limited to the contents disclosed in Embodiment 3. It should be noted that the above modules as part of the device can run in the computer terminal 10 provided in Embodiment 1.

[0269] In the above embodiments of the present application, the determining module includes a first identification unit, a second identification unit, and a detection unit.

[0270] The first identification unit is configured to identify the original image by using a first classification model to determine whether the original image is a target image; the second identification unit is configured to identify the description information of the original image by using a second classification model to determine whether the original image is a target image; and the detection unit is configured to detect whether there is a first preset operation on the original image, and determine whether the original image is a target image based on the detection result.

[0271] In the above embodiments of the present application, the obtaining module includes a matching unit.

[0272] The matching unit is configured to match the original image with a plurality of preset replacement images to obtain a target replacement image. ​

[0273] It should be noted that the preferred embodiments involved in the above embodiments of the present application have the same application scenarios and implementation processes as the schemes provided in Embodiment 1, but are not limited to the schemes provided in Embodiment 1.

[0274] Embodiment 9

[0275] According to the embodiments of the present application, an image processing device for implementing the above image processing method is further provided, as shown in the figure, the device 1400 includes a first acquisition module 1402, a determination module 1404, a second acquisition module 1406, and a replacement module 1408. Figure 14

[0276] The first acquisition module 1402 is configured to acquire a description page of a product, wherein the description page contains an original image of the product and description information of the original image; the determination module 1404 is configured to determine whether the original image is a target image based on the original image or the description information, wherein the target image is an image that is visually uncomfortable; the second acquisition module 1406 is configured to acquire a target replacement image corresponding to the original image in the case where the original image is the target image; and the replacement module 1408 is configured to replace the original image with the target replacement image to obtain a processed description page.

[0277] It should be noted that the first acquisition module 1402, the determination module 1404, the second acquisition module 1406, and the replacement module 1408 correspond to steps S902 to S908 in Embodiment 4, and the four modules have the same instances and application scenarios as the corresponding steps, but are not limited to the contents disclosed in Embodiment 4. It should be noted that the above modules, as part of the device, can run in the computer terminal 10 provided in Embodiment 1.

[0278] In the above embodiments of the present application, the determination module includes a first identification unit, a second identification unit, and a detection unit.

[0279] The first identification unit is configured to identify the original image by using a first classification model to determine whether the original image is a target image; the second identification unit is configured to identify the description information of the original image by using a second classification model to determine whether the original image is a target image; and the detection unit is configured to detect whether there is a first preset operation on the original image, and determine whether the original image is a target image based on the detection result.

[0280] In the above embodiments of the present application, the second acquisition module includes a matching unit.

[0281] The matching unit is configured to match the original image with a plurality of preset replacement images to obtain a target replacement image.

[0282] ​It should be noted that the preferred embodiments involved in the above embodiments of the present application have the same application scenarios and implementation processes as the schemes provided in Embodiment 1, but are not limited to the schemes provided in Embodiment 1.

[0283] Embodiment 10

[0284] According to the embodiments of the present application, an image processing device for implementing the above image processing method is further provided, as shown in the figure, the device 1500 includes: a first calling module 1502, a determination module 1504, an acquisition module 1506, a replacement module 1508, and a second calling module 1510. Figure 15

[0285] The first calling module 1502 is configured to receive a description page of a target object by calling a first interface, wherein the first interface includes a first parameter, and a parameter value of the first parameter is the description page, and the description page contains an original image corresponding to the target object and description information of the original image; the determination module 1504 is configured to determine whether the original image is a target image based on the original image or the description information, wherein the target image is an image that has visual discomfort; the acquisition module 1506 is configured to acquire a target replacement image corresponding to the original image in the case that the original image is the target image; the replacement module 1508 is configured to replace the original image with the target replacement image to obtain a processed description page; and the second calling module 1510 is configured to output the processed description page by calling a second interface, wherein the second interface includes a second parameter, and a parameter value of the second parameter is the processed description page.

[0286] It should be noted that the first calling module 1502, the determination module 1504, the acquisition module 1506, the replacement module 1508, and the second calling module 1510 correspond to steps S1002 to S1010 in Embodiment 5, and the five modules have the same instances and application scenarios as the corresponding steps, but are not limited to the contents disclosed in Embodiment 5. It should be noted that the above modules as part of the device can run in the computer terminal 10 provided in Embodiment 1.

[0287] In the above embodiments of the present application, the determination module includes a first identification unit, a second identification unit, and a detection unit.

[0288] The first identification unit is configured to identify the original image by using a first classification model to determine whether the original image is a target image; the second identification unit is configured to identify the description information of the original image by using a second classification model to determine whether the original image is a target image; and the detection unit is configured to detect whether there is a first preset operation on the original image, and determine whether the original image is a target image based on the detection result.

[0289] ​In the above embodiments of the present application, the acquisition module comprises a matching unit.

[0290] The matching unit is configured to match the original image with the plurality of preset replacement images to obtain a target replacement image.

[0291] It should be noted that the preferred embodiments involved in the above embodiments of the present application have the same scheme, application scenario and implementation process as provided in Embodiment 1, but are not limited to the scheme provided in Embodiment 1.

[0292] Embodiment 11

[0293] According to the embodiments of the present application, an image processing method embodiment is also provided. It should be noted that the steps shown in the flowchart can be executed in a computer system such as a set of computer executable instructions, and although the logical order is shown in the flowchart, in some cases, the steps shown or described herein can be executed in an order different from that shown herein.

[0294] Figure 16 is a flowchart of an image processing method according to Embodiment 11 of the present application. As shown in Figure 16 the method can comprise the following steps:

[0295] Step S1602, receiving a medical diagnosis page.

[0296] The medical diagnosis page contains an original image of a disease morphology and description information of the original image.

[0297] The medical diagnosis page in the above steps can be a medical diagnosis page of a skin disease, wherein the medical diagnosis page contains an image of a skin disease of a patient and description information of the skin disease.

[0298] Step S1604, in a case where it is determined based on the original image or the description information that the original image is a target image, displaying a processed medical diagnosis page.

[0299] The processed medical diagnosis page is obtained by replacing the original image with a target replacement image corresponding to the original image, and the target image is an image that causes visual discomfort.

[0300] In an optional embodiment, when it is determined according to the image of the skin disease or the description information that the image of the skin disease is an image that causes visual discomfort to the user, the medical diagnosis page can be processed to reduce the visual discomfort of the user. Specifically, the image of the skin disease in the medical diagnosis page can be replaced with a corresponding cartoon image or cartoon font, etc., to reduce the discomfort of the user in browsing and to remind the user of the information conveyed in the image of the skin disease.

[0301] In the above embodiments of the present application, the processed medical diagnosis page further includes prompt information corresponding to the target replacement image, wherein the prompt information is used to prompt the second preset operation of displaying the original image.

[0302] In the above embodiments of the present application, the medical diagnosis page is displayed after the second preset operation is detected.

[0303] In the above embodiments of the present application, the method further includes: displaying the target replacement image; receiving a modified replacement image, wherein the modified replacement image is obtained by modifying the target replacement image; and displaying a processed medical diagnosis page, wherein the processed medical diagnosis page is obtained by replacing the original image with the modified replacement image.

[0304] It should be noted that the preferred embodiments involved in the above embodiments of the present application are the same as the schemes and application scenarios and implementation processes provided in Embodiment 1, but are not limited to the schemes provided in Embodiment 1.

[0305] Embodiment 12

[0306] According to the embodiments of the present application, an image processing device for implementing the above image processing method is further provided, as shown in Figure 17 The device 1700 includes a first receiving module 1702 and a determining module 1704.

[0307] The first receiving module 1702 is configured to receive a medical diagnosis page, wherein the medical diagnosis page contains an original image of a disease morphology and description information of the original image. The determining module 1704 is configured to display a processed medical diagnosis page in a case where it is determined based on the original image or the description information that the original image is a target image, wherein the processed medical diagnosis page is obtained by replacing the original image with a target replacement image corresponding to the original image, and the target image is an image that is visually uncomfortable.

[0308] It should be noted that the first receiving module 1702 and the determining module 1704 correspond to steps S1602 to S1604 in Embodiment 11, and the two modules have the same instances and application scenarios as the corresponding steps, but are not limited to the contents disclosed in Embodiment 11. It should be noted that the above modules can run in the computer terminal 10 provided in Embodiment 1 as part of the device.

[0309] In the above embodiments of the present application, the processed medical diagnosis page further includes prompt information corresponding to the target replacement image, wherein the prompt information is used to prompt the second preset operation of displaying the original image.

[0310] In the above embodiments of the present application, the device further includes a first display module.

[0311] The first display module is used to display a medical diagnosis page after detecting the second preset operation.

[0312] In the above embodiments of this application, the device further includes: a second display module, a second receiving module, and a third display module.

[0313] The second display module is used to display the target replacement image; the second receiving module is used to receive the modified replacement image, wherein the modified replacement image is obtained by modifying the target replacement image; the third display module is used to display the processed medical diagnosis page, wherein the processed medical diagnosis page is obtained by replacing the original image with the modified replacement image.

[0314] It should be noted that the preferred implementation schemes involved in the above embodiments of this application are the same as the schemes, application scenarios and implementation processes provided in Embodiment 1, but are not limited to the schemes provided in Embodiment 1.

[0315] Example 13

[0316] According to an embodiment of this application, an image processing system is also provided, comprising:

[0317] Processor; and

[0318] The memory, connected to the processor, provides instructions to the processor to perform the following processing steps: obtaining a description page of a target object, wherein the description page contains the original image corresponding to the target object and descriptive information of the original image; determining whether the original image is the target image based on the original image or the descriptive information, wherein the target image is an image that is visually uncomfortable; if the original image is the target image, obtaining the target replacement image corresponding to the original image; replacing the original image with the target replacement image to obtain the processed description page.

[0319] It should be noted that the preferred implementation schemes involved in the above embodiments of this application are the same as the schemes, application scenarios and implementation processes provided in Embodiment 1, but are not limited to the schemes provided in Embodiment 1.

[0320] Example 14

[0321] Embodiments of this application may provide a computer terminal, which may be any computer terminal device in a group of computer terminals. Optionally, in this embodiment, the aforementioned computer terminal may also be replaced by a mobile terminal or other terminal device.

[0322] Optionally, in this embodiment, the computer terminal may be located in at least one of a plurality of network devices in a computer network.

[0323] In the embodiment, the computer terminal can execute program codes of the following steps in the image processing method: obtaining a description page of a target object, wherein the description page contains an original image corresponding to the target object and description information of the original image; determining whether the original image is a target image based on the original image or the description information, wherein the target image is an image that is visually uncomfortable; obtaining a target replacement image corresponding to the original image in a case where the original image is the target image; and replacing the original image with the target replacement image to obtain a processed description page.

[0324] Optionally, Figure 18 is a structural block diagram of a computer terminal according to Embodiment 14 of the present application. As shown in the figure, the computer terminal A can include one or more (only one is shown in the figure) processors 1802, a memory 1804. Figure 18

[0325] The memory can be used to store software programs and modules, such as program instructions / modules corresponding to the image processing method and device in the embodiments of the present application. The processor executes various functions and data processing by running the software programs and modules stored in the memory, that is, implements the image processing method described above. The memory can include a high-speed random access memory, and can further include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some examples, the memory can further include a memory remotely arranged with respect to the processor, which can be connected to the terminal A through a network. Examples of the network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and a combination thereof.

[0326] The processor can call information and application programs stored in the memory through the transmission device to execute the following steps: obtaining a description page of a target object, wherein the description page contains an original image corresponding to the target object and description information of the original image; determining whether the original image is a target image based on the original image or the description information, wherein the target image is an image that is visually uncomfortable; obtaining a target replacement image corresponding to the original image in a case where the original image is the target image; and replacing the original image with the target replacement image to obtain a processed description page.

[0327] Optionally, the processor can further execute program codes of the following steps: identifying the original image using a first classification model to determine whether the original image is a target image; identifying the description information of the original image using a second classification model to determine whether the original image is a target image; and detecting whether there is a first preset operation on the original image to determine whether the original image is a target image.

[0328] ​Optionally, the processor can further execute program codes of the following steps: obtaining image annotation based on annotation of the training images by a plurality of users; obtaining image annotation based on annotation of the training images by the target user; obtaining image annotation based on the browsing behavior data of the target user.

[0329] Optionally, the processor can further execute program codes of the following steps: obtaining description annotation based on annotation of the description information of the training images by a plurality of users; obtaining description annotation based on annotation of the description information of the training images by the target user; obtaining description annotation based on the browsing behavior data of the target user.

[0330] Optionally, the processor can further execute program codes of the following steps: determining that the original image is the target image when it is detected that the first preset operation exists; determining that the original image is not the target image when it is detected that the first preset operation does not exist.

[0331] Optionally, the processor can further execute program codes of the following steps: matching the original image with a plurality of preset replacement images to obtain a target replacement image.

[0332] Optionally, the processor can further execute program codes of the following steps: matching the original image with a plurality of preset replacement images to obtain a target replacement image using a matching model, wherein the matching model is obtained by training a third preset model based on a plurality of image sets, and the plurality of image sets are generated based on image annotation of the target image and image annotation of the plurality of preset replacement images.

[0333] Optionally, the processor can further execute program codes of the following steps: generating the target replacement image based on the original image when the original image fails to match the plurality of preset replacement images.

[0334] Optionally, the processor can further execute program codes of the following steps: processing the original image using a generation model to generate the target replacement image, wherein the generation model is obtained by training a fourth preset model based on a plurality of third samples, and the plurality of third samples are generated based on the target image and the plurality of preset replacement images, or based on description information of the target image and the plurality of preset replacement images.

[0335] Optionally, the processor can further execute program codes of the following steps: obtaining prompt information corresponding to the target replacement image, wherein the prompt information is used to prompt the second preset operation of displaying the original image; and adding the prompt information to the processed description page.

[0336] Optionally, the processor can further execute program codes of the following steps: replacing the target replacement image with the original image to obtain the description page after detecting the second preset operation.

[0337] The processor can call information and application programs stored in the memory through the transmission device to execute the following steps: obtaining a description page of a target object, wherein the description page contains an original image corresponding to the target object and description information of the original image; in a case where it is determined that the original image is a target image based on the original image or the description information, the target image being an image that is visually uncomfortable, obtaining a target replacement image corresponding to the original image; and displaying a processed description page, wherein the processed description page is obtained by replacing the original image with the target replacement image.

[0338] Optionally, the processor can further execute program codes of the following steps: identifying the original image by using a first classification model to determine whether the original image is a target image; identifying the description information of the original image by using a second classification model to determine whether the original image is a target image; and detecting whether a first preset operation is performed on the original image, and determining whether the original image is a target image based on a detection result.

[0339] Optionally, the processor can further execute program codes of the following steps: matching the original image with a plurality of preset replacement images to obtain a target replacement image.

[0340] The processor can call information and application programs stored in the memory through the transmission device to execute the following steps: receiving a description page of a target object, wherein the description page contains an original image corresponding to the target object and description information of the original image; determining whether the original image is a target image based on the original image or the description information, wherein the target image is an image that is visually uncomfortable; in a case where the original image is a target image, obtaining a target replacement image corresponding to the original image; replacing the original image with the target replacement image to obtain a processed description page; and outputting the processed description page.

[0341] Optionally, the processor can further execute program codes of the following steps: identifying the original image by using a first classification model to determine whether the original image is a target image; identifying the description information of the original image by using a second classification model to determine whether the original image is a target image; and detecting whether a first preset operation is performed on the original image, and determining whether the original image is a target image based on a detection result.

[0342] Optionally, the processor can further execute program codes of the following steps: matching the original image with a plurality of preset replacement images to obtain a target replacement image.

[0343] The processor can call information and application programs stored in the memory through the transmission device to execute the following steps: obtaining a description page of a product, wherein the description page contains an original image of the product and description information of the original image; determining whether the original image is a target image based on the original image or the description information, wherein the target image is an image that is visually uncomfortable; obtaining a target replacement image corresponding to the original image in the case that the original image is the target image; and replacing the original image with the target replacement image to obtain a processed description page.

[0344] Optionally, the processor can further execute program codes of the following steps: identifying the original image by using a first classification model to determine whether the original image is the target image; identifying the description information of the original image by using a second classification model to determine whether the original image is the target image; and detecting whether a first preset operation is performed on the original image, and determining whether the original image is the target image based on a detection result.

[0345] Optionally, the processor can further execute program codes of the following steps: matching the original image with a plurality of preset replacement images to obtain the target replacement image.

[0346] The processor can call information and application programs stored in the memory through the transmission device to execute the following steps: obtaining a description page of a product, wherein the description page contains an original image of the product and description information of the original image; determining whether the original image is a target image based on the original image or the description information, wherein the target image is an image that is visually uncomfortable; obtaining a target replacement image corresponding to the original image in the case that the original image is the target image; and replacing the original image with the target replacement image to obtain a processed description page.

[0347] Optionally, the processor can further execute program codes of the following steps: identifying the original image by using a first classification model to determine whether the original image is the target image; identifying the description information of the original image by using a second classification model to determine whether the original image is the target image; and detecting whether a first preset operation is performed on the original image, and determining whether the original image is the target image based on a detection result.

[0348] Optionally, the processor can further execute program codes of the following steps: matching the original image with a plurality of preset replacement images to obtain the target replacement image.

[0349] The processor can invoke information and applications stored in memory via a transmission device to perform the following steps: receiving a medical diagnostic page, wherein the medical diagnostic page contains an original image of the disease morphology and descriptive information of the original image; and, if the original image is determined to be the target image based on the original image or the descriptive information, displaying the processed medical diagnostic page.

[0350] Optionally, the processor may also execute program code that includes the following steps: the processed medical diagnosis page further includes prompt information corresponding to the target replacement image, wherein the prompt information is used to prompt a second preset operation to display the original image.

[0351] Optionally, the processor may also execute program code that displays a medical diagnostic page after detecting a second preset operation.

[0352] Optionally, the processor may also execute program code that performs the following steps: displaying a target replacement image; receiving a modified replacement image, wherein the modified replacement image is obtained by modifying the target replacement image; and displaying a processed medical diagnosis page, wherein the processed medical diagnosis page is obtained by replacing the original image with the modified replacement image.

[0353] Those skilled in the art will understand that Figure 16 The structure shown is for illustrative purposes only. The computer terminal can also be a smartphone (such as an Android phone, an iOS phone, etc.), a tablet computer, a PDA, a mobile Internet device (MID), a PAD, and other terminal devices. Figure 16 This does not limit the structure of the aforementioned electronic device. For example, computer terminal A may also include components that are more... Figure 16 The more or fewer components shown (such as network interfaces, display devices, etc.), or having the same Figure 16 The different configurations shown.

[0354] Those skilled in the art will understand that all or part of the steps in the various methods of the above embodiments can be implemented by a program instructing the hardware related to the terminal device. The program can be stored in a computer-readable storage medium, which may include: flash drive, read-only memory (ROM), random access memory (RAM), disk or optical disk, etc.

[0355] Example 13

[0356] Embodiments of this application also provide a storage medium. Optionally, in this embodiment, the storage medium can be used to store the program code executed by the image processing method provided in the above embodiments.

[0357] Optionally, in the embodiment, the storage medium can be located in any one of the computer terminals in the computer terminal group in the computer network, or in any one of the mobile terminals in the mobile terminal group.

[0358] Optionally, in the embodiment, the storage medium is configured to store program code for performing the following steps: obtaining a description page of a target object, wherein the description page contains an original image corresponding to the target object and description information of the original image; determining whether the original image is a target image based on the original image or the description information, wherein the target image is an image that is visually uncomfortable; obtaining a target replacement image corresponding to the original image in a case where the original image is the target image; and replacing the original image with the target replacement image to obtain a processed description page.

[0359] Optionally, the storage medium is further configured to store program code for performing the following steps: identifying the original image using a first classification model to determine whether the original image is the target image; identifying the description information of the original image using a second classification model to determine whether the original image is the target image; and detecting whether a first preset operation on the original image exists to determine whether the original image is the target image.

[0360] Optionally, the storage medium is further configured to store program code for performing the following steps: obtaining image annotations based on annotations of training images by multiple users; obtaining image annotations based on annotations of the training images by the target user; and obtaining image annotations based on browsing behavior data of the target user.

[0361] Optionally, the storage medium is further configured to store program code for performing the following steps: obtaining description annotations based on annotations of description information of training images by multiple users; obtaining description annotations based on annotations of the description information of the training images by the target user; and obtaining description annotations based on browsing behavior data of the target user.

[0362] Optionally, the storage medium is further configured to store program code for performing the following steps: determining that the original image is the target image in a case where it is detected that the first preset operation exists; and determining that the original image is not the target image in a case where it is detected that the first preset operation does not exist.

[0363] Optionally, the storage medium is further configured to store program code for performing the following steps: matching the original image with a plurality of preset replacement images to obtain the target replacement image.

[0364] Optionally, the storage medium is further configured to store program code for performing the following steps: matching the original image and the plurality of preset replacement images by using a matching model to obtain a target replacement image, wherein the matching model is obtained by training a third preset model based on a plurality of image sets, and the plurality of image sets are generated based on image labels of the target image and image labels of the plurality of preset replacement images.

[0365] Optionally, the storage medium is further configured to store program code for performing the following steps: generating the target replacement image based on the original image in a case where the original image fails to match the plurality of preset replacement images.

[0366] Optionally, the storage medium is further configured to store program code for performing the following steps: processing the original image by using a generation model to generate the target replacement image, wherein the generation model is obtained by training a fourth preset model based on a plurality of third samples, and the plurality of third samples are generated based on the target image and the plurality of preset replacement images, or are generated based on description information of the target image and the plurality of preset replacement images.

[0367] Optionally, the storage medium is further configured to store program code for performing the following steps: obtaining prompt information corresponding to the target replacement image, wherein the prompt information is used to prompt a second preset operation of displaying the original image; and adding the prompt information to the processed description page.

[0368] Optionally, the storage medium is further configured to store program code for performing the following steps: replacing the target replacement image with the original image to obtain the description page after detecting the second preset operation.

[0369] Optionally, in the embodiment, the storage medium is configured to store program code for performing the following steps: obtaining a description page of a target object, wherein the description page contains an original image corresponding to the target object and description information of the original image; obtaining a target replacement image corresponding to the original image in a case where it is determined that the original image is a target image based on the original image or the description information, wherein the target image is an image that is visually uncomfortable; and displaying a processed description page, wherein the processed description page is a page obtained by replacing the original image with the target replacement image.

[0370] Optionally, the storage medium is further configured to store program code for performing the following steps: identifying whether the original image is the target image by using a first classification model; identifying whether the original image is the target image by using a second classification model on the description information of the original image; and detecting whether there is a first preset operation on the original image, and determining whether the original image is the target image based on a detection result.

[0371] Optionally, the storage medium is further configured to store program code for performing the following steps: matching the original image with a plurality of preset replacement images to obtain a target replacement image.

[0372] Optionally, in the embodiment, the storage medium is configured to store program code for performing the following steps: receiving a description page of a target object, wherein the description page contains an original image corresponding to the target object and description information of the original image; determining whether the original image is a target image based on the original image or the description information, wherein the target image is an image that is visually uncomfortable; obtaining a target replacement image corresponding to the original image in a case where the original image is the target image; replacing the original image with the target replacement image to obtain a processed description page; and outputting the processed description page.

[0373] Optionally, the storage medium is further configured to store program code for performing the following steps: identifying the original image using a first classification model to determine whether the original image is a target image; identifying the description information of the original image using a second classification model to determine whether the original image is a target image; and detecting whether a first preset operation is performed on the original image and determining whether the original image is a target image based on a detection result.

[0374] Optionally, the storage medium is further configured to store program code for performing the following steps: matching the original image with a plurality of preset replacement images to obtain a target replacement image.

[0375] Optionally, in the embodiment, the storage medium is configured to store program code for performing the following steps: obtaining a description page of a product, wherein the description page contains an original image of the product and description information of the original image; determining whether the original image is a target image based on the original image or the description information, wherein the target image is an image that is visually uncomfortable; obtaining a target replacement image corresponding to the original image in a case where the original image is the target image; replacing the original image with the target replacement image to obtain a processed description page.

[0376] Optionally, the storage medium is further configured to store program code for performing the following steps: identifying the original image using a first classification model to determine whether the original image is a target image; identifying the description information of the original image using a second classification model to determine whether the original image is a target image; and detecting whether a first preset operation is performed on the original image and determining whether the original image is a target image based on a detection result.

[0377] Optionally, the storage medium is further configured to store program code for performing the following steps: matching the original image with a plurality of preset replacement images to obtain a target replacement image.

[0378] Optionally, in the embodiment, the storage medium is configured to store program code for performing the following steps: receiving a description page of a target object by calling a first interface, wherein the first interface comprises: a first parameter, and a parameter value of the first parameter is the description page, and the description page contains an original image corresponding to the target object and description information of the original image; determining whether the original image is a target image based on the original image or the description information, wherein the target image is an image that is visually uncomfortable; in a case where the original image is the target image, obtaining a target replacement image corresponding to the original image; replacing the original image with the target replacement image to obtain a processed description page; and outputting the processed description page by calling a second interface, wherein the second interface comprises: a second parameter, and a parameter value of the second parameter is the processed description page.

[0379] Optionally, the storage medium is further configured to store program code for performing the following steps: identifying the original image using a first classification model to determine whether the original image is the target image; identifying the description information of the original image using a second classification model to determine whether the original image is the target image; and detecting whether a first preset operation is performed on the original image, and determining whether the original image is the target image based on a detection result.

[0380] Optionally, the storage medium is further configured to store program code for performing the following steps: matching the original image with a plurality of preset replacement images to obtain the target replacement image.

[0381] In the embodiment, the storage medium is configured to store program code for performing the following steps: receiving a medical diagnosis page, wherein the medical diagnosis page contains an original image of a disease morphology and description information of the original image; and in a case where it is determined that the original image is a target image based on the original image or the description information, displaying a processed medical diagnosis page.

[0382] Optionally, the storage medium is further configured to store program code for performing the following steps: the processed medical diagnosis page further comprises prompt information corresponding to the target replacement image, wherein the prompt information is used to prompt a second preset operation of displaying the original image.

[0383] Optionally, the storage medium is further configured to store program code for performing the following steps: after detecting the second preset operation, displaying the medical diagnosis page.

[0384] Optionally, the storage medium is further configured to store program code for displaying the target replacement image; receiving a modified replacement image, wherein the modified replacement image is obtained by modifying the target replacement image; and displaying a processed medical diagnosis page, wherein the processed medical diagnosis page is obtained by replacing the original image with the modified replacement image.

[0385] The sequence numbers of the above-described embodiments of the present application are only for description, and do not represent the advantages or disadvantages of the embodiments.

[0386] In the above-described embodiments of the present application, the description of each embodiment has its own focus, and the parts not described in detail in a certain embodiment can be referred to the relevant description of other embodiments.

[0387] In the several embodiments provided by the present application, it should be understood that the disclosed technology can be implemented in other ways. Of course, the unit embodiment described above is only schematic. For example, the division of the units is only a logical function division. There can be another division during actual implementation. For example, a plurality of units or components can be combined or integrated into another system, or some features can be ignored or not executed. In addition, the displayed or discussed coupling or direct coupling or communication connection between each set of units can be indirect coupling or communication connection through some interface, or electrical or other form.

[0388] The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, that is, they can be located in one place, or they can be distributed on a plurality of network units. According to actual needs, part or all of the units can be selected to achieve the purpose of the present embodiment.

[0389] In addition, each functional unit in each embodiment of the present application can be integrated into a processing unit, or each unit can exist physically, or two or more units can be integrated into one unit. The integrated unit can be implemented in the form of hardware or in the form of a software functional unit.

[0390] The integrated unit, if implemented in the form of a software function unit and sold or used as an independent product, can be stored in a computer readable storage medium. Based on such understanding, the technical solutions of the present application essentially or say the part that contributes to the prior art or the whole or part of the technical solutions can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes a plurality of instructions for causing a computer device (which can be a personal computer, a server or a network device, etc.) to execute all or part of the steps of the method described in the various embodiments of the present application. The aforementioned storage medium includes: a U disk, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a mobile hard disk, a magnetic disk or an optical disk, and various media that can store program codes.

[0391] The above is only the preferred embodiment of the present application, and it should be pointed out that for those skilled in the art, without departing from the principles of the present application, a number of improvements and refinements can be made, which should be considered as the protection scope of the present application.

Claims

1. An image processing method, characterized by, Comprise: In the process of searching for a target object by a user using a search box, but not yet successful, obtaining a description page of the target object, wherein the description page contains an original image corresponding to the target object, and description information of the original image, the description information is description information for explaining the content of the original image; Based on the original image or the description information, determine whether the original image is a target image, wherein the target image is an image that is visually uncomfortable; In the case where the original image is the target image, a feature extraction network is used to extract feature points from the original image, and a target replacement image is generated based on the feature points, wherein the target replacement image is the same as the content expressed by the original image; Replace the original image with the target replacement image to obtain a processed description page; Add the prompt information corresponding to the target replacement image to the processed description page, and after detecting a second preset operation, replace the target replacement image with the original image to obtain the description page.

2. The method of claim 1, wherein, Based on the original image or the description information, determine whether the original image is a target image includes one of: Use a first classification model to identify the original image and determine whether the original image is the target image; Use a second classification model to identify the description information of the original image and determine whether the original image is the target image.

3. The method of claim 2, wherein, The first classification model is obtained by training a first preset model with multiple sets of first samples, wherein each set of first samples includes a training image and an image label corresponding to the training image, and the image label is obtained by any one of the following ways: Based on multiple users labeling the training image; Based on a target user labeling the training image; Based on the browsing behavior data of the target user.

4. The method of claim 2, wherein, The second classification model is obtained by training a second preset model with multiple sets of second samples, wherein each set of second samples includes description information of a training image and a description label corresponding to the description information, and the description label is obtained by any one of the following ways: Based on multiple users labeling the description information of the training image; Based on a target user labeling the description information of the training image; Based on the browsing behavior data of the target user.

5. An image processing method characterized by, Comprise: In the process of searching for a product by a user using a search box, but not yet successful, obtaining a description page of the product, wherein the description page contains an original image of the product, and description information of the original image, the description information is description information for explaining the content of the original image; Based on the original image or the description information, determine whether the original image is a target image, wherein the target image is an image that is visually uncomfortable; In a case where the original image is the target image, extracting feature points from the original image by using a feature extraction network, and generating a target replacement image based on the feature points, wherein the target replacement image is the same as content expressed by the original image; replacing the original image with the target replacement image to obtain a processed description page; adding prompt information corresponding to the target replacement image to the processed description page, and replacing the target replacement image with the original image to obtain the description page after detecting a second preset operation.

6. An image processing method characterized by, Comprise: In a case where the original image is the target image, extracting feature points from the original image by using a feature extraction network, and generating a target replacement image based on the feature points, wherein the target replacement image is the same as content expressed by the original image; replacing the original image with the target replacement image to obtain a processed description page; adding prompt information corresponding to the target replacement image to the processed description page, and replacing the target replacement image with the original image to obtain the description page after detecting a second preset operation. Comprise: In a case where the original image is the target image, extracting feature points from the original image by using a feature extraction network, and generating a target replacement image based on the feature points, wherein the target replacement image is the same as content expressed by the original image; replacing the original image with the target replacement image to obtain a processed description page; 7. An image processing method characterized by, outputting the processed description page by calling a second interface, wherein the second interface comprises a second parameter, and a parameter value of the second parameter is the processed description page; adding prompt information corresponding to the target replacement image to the processed description page, and replacing the target replacement image with the original image to obtain the description page after detecting a second preset operation. Comprise: In a case where the original image is the target image, extracting feature points from the original image by using a feature extraction network, and generating a target replacement image based on the feature points, wherein the target replacement image is the same as content expressed by the original image; replacing the original image with the target replacement image to obtain a processed description page; adding prompt information corresponding to the target replacement image to the processed description page, and replacing the target replacement image with the original image to obtain the description page after detecting a second preset operation.

8. The method of claim 7, wherein, The processed medical diagnosis page further comprises prompt information corresponding to the target replacement image, wherein the prompt information is used to prompt a second preset operation of displaying the original image.

9. The method of claim 8, wherein, After detecting the second preset operation, the medical diagnosis page is displayed.

10. The method of claim 9, wherein, The method further comprises: displaying the target replacement image; receiving a modified replacement image, wherein the modified replacement image is obtained by modifying the target replacement image; displaying the processed medical diagnosis page, wherein the processed medical diagnosis page is obtained by replacing the original image with the modified replacement image.

11. A computer readable storage medium, characterized in that, The computer readable storage medium comprises a stored program, wherein the program controls the device where the computer readable storage medium is located to execute the image processing method of any one of claims 1 to 10 when the program is running.

12. A computer terminal, characterized in that comprises: a memory and a processor, wherein the processor is used to run a program stored in the memory, and the program executes the image processing method of any one of claims 1 to 10 when the program is running.

13. An image processing system, characterized by comprises: a processor; and a memory connected with the processor, used to provide the processor with instructions for processing the following processing steps: obtaining a description page of a target object during a process in which a user searches for the target object by using a search box but has not successfully jumped, wherein the description page comprises an original image corresponding to the target object and description information of the original image; determining whether the original image is a target image based on the original image or the description information, wherein the target image is an image that visually has discomfort; extracting feature points from the original image by using a feature extraction network and generating a target replacement image based on the feature points in a case where the original image is the target image; replacing the original image with the target replacement image to obtain a processed description page, wherein the target replacement image is the same as the content of the original image, the description information is description information for explaining the content of the original image; adding prompt information corresponding to the target replacement image to the processed description page; and replacing the target replacement image with the original image to obtain the description page after detecting a second preset operation.

Images