Image processing method, device, computer-readable storage medium, and electronic device

Abstract

The present invention discloses an image processing method, apparatus, computer-readable storage medium, and electronic device. The method comprises: responding to a control instruction triggered by a current application, determining at least one candidate image from the communication content of the current application, parsing the at least one candidate image to obtain image features of the at least one candidate image; displaying at least one target image on the graphical user interface of the current application, the at least one target image being an image selected from the at least one candidate image based on the image features; and responding to a selection operation on the at least one target image, batch-generating emoticon images corresponding to the target image corresponding to the selection operation. The present invention solves the technical problem of low emoticon image generation efficiency caused by the inability of the prior art to simultaneously generate multiple emoticon images.

Description

Technical Field

[0001] The present invention relates to the field of image processing, and in particular to an image processing method, device, computer-readable storage medium, and electronic device. Background Art

[0002] With the rapid development of information technology, people can now communicate without leaving their homes through various social media apps. When users communicate via social media apps, the client can create emoticon images from images in the communication and save the generated emoticon images. For example, a user can long-press an emoticon image sent by another user to select the emoticon image and add it to the emoticon storage unit of the social media app.

[0003] However, in existing technologies, users can only generate and save one emoticon image at a time, reducing the efficiency of emoticon image generation. Furthermore, when duplicate emoticon images are stored on the client, the duplicate images cannot be automatically deleted. When a user wants to use an emoticon image, they need to search through multiple emoticon images stored in the emoticon storage unit. When there are a large number of emoticon images, it is difficult to quickly obtain the emoticon image the user needs, which reduces the user experience.

[0004] To address the above-mentioned problems, no effective solutions have been proposed so far. Summary of the Invention

[0005] Embodiments of the present invention provide an image processing method, apparatus, computer-readable storage medium, and electronic device to at least solve the technical problem of low efficiency in emoticon image generation caused by the inability of the prior art to simultaneously generate multiple emoticon images.

[0006] According to one aspect of an embodiment of the present invention, there is provided an image processing method, comprising: responding to a control instruction triggered for a current application, determining at least one candidate image from the communication content of the current application, and parsing the at least one candidate image to obtain image features of the at least one candidate image; displaying at least one target image in a graphical user interface of the current application, the at least one target image being an image screened out from the at least one candidate image based on the image features; and responding to a selection operation for the at least one target image, batch-generating emoticon images corresponding to the target image corresponding to the selection operation.

[0007] Furthermore, the graphical user interface of the current application includes an emoticon package generation control, and the image processing method also includes: responding to an emoticon package generation instruction triggered by the emoticon package generation control; obtaining communication content of a preset length according to the emoticon package generation instruction; and extracting at least one candidate image from the communication content.

[0008] Furthermore, the image processing method also includes: when the number of communication objects corresponding to the communication content is multiple, responding to the object selection instruction, determining the target object from the multiple communication objects, wherein the communication object is the object communicating with the current object; and filtering out the target communication content associated with the target object from the communication content of a preset length according to the emoticon package generation instruction.

[0009] Furthermore, the image processing method also includes: when it is determined based on image features that at least one candidate image does not contain text, screening out at least one first candidate image containing a subject image from at least one candidate image based on the image features, wherein the subject image is an object with facial expression; screening out at least one second candidate image from at least one first candidate image whose facial expression and / or body movement of the subject image meets a first preset condition; determining at least one target image based on the at least one second candidate image, and displaying the at least one target image.

[0010] Furthermore, the image processing method further includes: removing images stored in a preset storage area from at least one second candidate image, and / or removing overlapping images from at least one second candidate image, to obtain at least one target image.

[0011] Furthermore, the image processing method also includes: when determining that at least one candidate image contains text based on image features, obtaining the text length of the text; screening at least one target image from at least one candidate image based on the text length and image features, and displaying at least one target image.

[0012] Furthermore, the image processing method also includes: when the text length is greater than a preset length, eliminating at least one candidate image; when the text length is less than or equal to the preset length, screening out at least one first candidate image containing a subject image from at least one candidate image based on image features, wherein the subject image is an object with facial expression; screening out at least one second candidate image whose facial expression and / or body movement of the subject image meets a first preset condition from at least one first candidate image; and determining at least one target image based on at least one second candidate image.

[0013] Furthermore, the image processing method also includes: obtaining image content in at least one second candidate image; eliminating at least one third candidate image of at least one second candidate image based on the text content and image content of the text to obtain at least one fourth candidate image, wherein the text content of at least one third candidate image does not match the image content of at least one third candidate image; eliminating images stored in a preset storage area from at least one fourth candidate image, and / or eliminating overlapping images in at least one fourth candidate image to obtain at least one target image.

[0014] Furthermore, the image processing method also includes: in response to a selection operation for at least one target image, after batch generating emoticon package images corresponding to the target images corresponding to the selection operation, matching the emoticon package images with preset emoticon package images to obtain matching results; deduplicating the emoticon package images based on the matching results to obtain deduplicated emoticon package images.

[0015] Furthermore, the image processing method further includes: after deduplicating the emoticon package images according to the matching results to obtain the deduplicated emoticon package images, performing deletion operations and / or classification operations on the deduplicated emoticon package images according to the corresponding control instructions.

[0016] According to another aspect of an embodiment of the present invention, an image processing device is also provided, including: a determination module, used to respond to a control instruction triggered for a current application, determine at least one candidate image from the communication content of the current application, and parse at least one candidate image to obtain image features of at least one candidate image; a display module, used to display at least one target image on the graphical user interface of the current application, at least one target image being an image screened out from at least one candidate image based on image features; a generation module, used to respond to a selection operation for at least one target image, and batch generate emoticon images corresponding to the target image corresponding to the selection operation.

[0017] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided, in which a computer program is stored. The computer program is configured to execute the above-mentioned image processing method when running.

[0018] According to another aspect of an embodiment of the present invention, an electronic device is also provided, which includes one or more processors; a storage device for storing one or more programs, which, when the one or more programs are executed by the one or more processors, enables the one or more processors to run the programs, wherein the programs are configured to execute the above-mentioned image processing method when running.

[0019] In an embodiment of the present invention, a method of batch generating emoticon images corresponding to multiple images is adopted. After responding to a control instruction triggered for a current application, at least one candidate image is determined from the communication content of the current application, and the at least one candidate image is parsed to obtain selected features of the at least one candidate image. Then, a target image is screened from the at least one candidate image based on the image features, and the target image is displayed in the graphical user interface of the current application. Finally, in response to a selection operation for the at least one target image, emoticon images corresponding to the target image corresponding to the selection operation are batch generated.

[0020] As can be seen from the above content, the present application can batch generate corresponding emoticon images from at least one candidate image in the communication content, thereby avoiding the problem of low efficiency in generating emoticon images caused by operating each candidate image separately. In addition, in the process of generating an emoticon image from at least one candidate image, the present application also screens at least one candidate image according to image features, thereby avoiding the problem of wasting system resources caused by processing images that do not meet the requirements of the emoticon image. In addition, since the screening operation is performed on at least one candidate image, in the present application, only images that meet the requirements of the emoticon image are produced as emoticon images, thereby avoiding the interference of images that do not meet the requirements of the emoticon image, and improving the efficiency of generating emoticon images. Finally, in the present application, the user can also perform further selection operations on the target image obtained by screening, and generate an emoticon image from the target image selected by the user, so that the user can flexibly select the image for which the emoticon image needs to be generated according to his or her needs, thereby improving the user experience.

[0021] It can be seen that the solution provided in this application achieves the purpose of generating multiple emoticon images at the same time, thereby realizing the technical effect of improving the generation efficiency of emoticon images, and further solving the technical problem of low emoticon image generation efficiency caused by the inability of existing technologies to generate multiple emoticon images at the same time. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] The drawings described herein are used to provide a further understanding of the present invention and constitute a part of this application. The exemplary embodiments of the present invention and their descriptions are used to explain the present invention and do not constitute an improper limitation of the present invention. In the drawings:

[0023] Figure 1 is a flowchart of an image processing method according to an embodiment of the present invention;

[0024] Figure 2 is a schematic diagram of an optional graphical user interface according to an embodiment of the present invention;

[0025] Figure 3 is a schematic diagram of an optional graphical user interface according to an embodiment of the present invention;

[0026] Figure 4 is a schematic diagram of an optional graphical user interface according to an embodiment of the present invention;

[0027] Figure 5 is a schematic diagram of an image processing device according to an embodiment of the present invention. DETAILED DESCRIPTION

[0028] In order to enable those skilled in the art to better understand the solutions of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the embodiments described are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative efforts should fall within the scope of protection of the present invention.

[0029] It should be noted that the terms "first", "second", etc. in the description and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that the numbers used in this way can be interchanged where appropriate, so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, system, product or device that includes a series of steps or units is not necessarily limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or inherent to these processes, methods, products or devices.

[0030] Example 1

[0031] According to an embodiment of the present invention, an embodiment of an image processing method is 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 can be executed in an order different from that shown here.

[0032] In addition, it should be noted that the client can serve as the execution subject of the method provided in this embodiment.

[0033] Figure 1 is a flow chart of an image processing method according to an embodiment of the present invention. Figure 1 As shown, the method includes the following steps:

[0034] Step S102 , responding to a control instruction triggered for the current application, determining at least one candidate image from the communication content of the current application, and parsing the at least one candidate image to obtain image features of the at least one candidate image.

[0035] In step S102, the current application may be but is not limited to a social application software, and the communication content may be the content communicated between users through the social software (i.e., the above-mentioned current application), wherein the communication content includes but is not limited to text, voice, images, videos, files and the like, and the images in the communication content may be static images (for example, images in PNG format, images in JPG format, images in a form unique to emoticon images), or dynamic images (for example, images in GIF format).

[0036] Furthermore, in step S102, the image features of at least one candidate image include at least: image information and text information contained in the candidate image, wherein the image information includes the type of subject and, if the subject is an object with facial expressions, the facial expression and / or body movements; and the text information includes at least the text content and text length. The subject is the object in the candidate image. For example, in an image containing a person, the subject is the person; in an image containing an animal, the subject is the animal.

[0037] It should be noted that by parsing the candidate images, the image features of the candidate images are obtained, so that the client can filter the candidate images according to the image features of the candidate images, thereby avoiding processing images that do not conform to the emoticon package images, resulting in low efficiency in generating emoticon package images.

[0038] In addition, it should be noted that, in this embodiment, the communication content is the communication content of the current application operated by the user. For example, when a user communicates with other users through WeChat (i.e., the above-mentioned current application), the user can determine at least one candidate image in the chat content in WeChat, and then batch generate emoticon images from at least one candidate image. This process can realize the batch generation of emoticon images from the images in the communication content without calling a third-party application, thereby avoiding the problem of low efficiency in emoticon image generation caused by the need to load a third-party application in the process of calling a third-party application to generate emoticon images, thereby improving the efficiency of emoticon image generation.

[0039] In an optional embodiment, when user A is communicating with other users in the current application, he or she may operate a specific control in the client. After detecting that user A has operated the specific control, the client obtains the communication content within a preset time period from the communication content of the current application, filters out images from the communication content within the preset time period to obtain candidate images, and then analyzes the candidate images to obtain image features of the candidate images. The preset time period may be a fixed time period, for example, a time period that is 2 hours apart from the current time period; the preset time period may also be a time period set by the user, for example, when creating an emoticon package image, the user may set the preset time period to 2 hours, one day, or one week, etc.

[0040] It should be noted that in the above embodiment, the client can obtain at least one candidate image within a preset time length from the communication content, so that the client can generate an emoticon package image from at least one candidate image at a time without the user having to operate each candidate image separately, thereby simplifying the production steps of multiple emoticon package images and improving the efficiency of batch production of emoticon package images.

[0041] Step S104 : displaying at least one target image on the graphical user interface of the current application, where the at least one target image is an image selected from at least one candidate image according to image features.

[0042] Optionally, the client presents the communication content, at least one target image selected from at least one candidate image, and an emoticon package image generated by the client to the user via a graphical user interface. The client may locally store characteristics of the target image, which are image characteristics of the image used to generate the emoticon package image. The client may perform image screening on the at least one candidate image by comparing the image characteristics of the at least one candidate image with the characteristics of the target image. The screened target image is the target image capable of generating the emoticon package image.

[0043] It should be noted that, through step S104, candidate images that do not meet the emoticon package characteristics are excluded, and emoticon package images are generated only for target images that meet the emoticon package characteristics, thereby improving the generation efficiency of emoticon package images.

[0044] Step S106 , in response to a selection operation on at least one target image, batch-generate emoticon images corresponding to the target images corresponding to the selection operation.

[0045] In step S106, after obtaining at least one target image that meets the characteristics of the emoticon package, the user can also filter the at least one target image, for example, Figure 2The graphical user interface shown shows 15 target images. After the user clicks the image filter control, a pop-up window appears in the client's graphical user interface. Figure 3 The target image selection interface shown in the figure displays a variety of target image screening rules, for example, Figure 3 , "Filter by time", "Filter by type" and "Custom filter". After the user selects the filtering rule of "Filter by time", the client pops up the "Filter by time interface". In this interface, the user can set the time range so that the client can filter out images with release time within the time range set by the user from multiple target images; after the user selects the filtering rule of "Filter by type", the client pops up the "Filter by type interface". In this interface, the user can set the image type, for example, human type, animal type, cartoon type, etc., so that the client can filter out images with the image type set by the user from multiple target images; after the user selects the filtering rule of "Custom filter", the client pops up the "Custom filter interface". In this interface, the user can set the filtering rules for the images, or directly check the images the user needs from multiple target images.

[0046] Furthermore, after selecting at least one target image, the client obtains images filtered from the at least one target image, and generates emoticon images from the filtered images in batches, for example, Figure 4 In the graphical user interface shown, after the user filters at least one target image, the image after filtering at least one image is displayed in the emoticon package generation interface, for example, Figure 4 As shown, the user selects target images 1, 5, and 11 from multiple target images. After the user clicks the "Confirm" control, the client generates emoticon images from target images 1, 5, and 11 with one click.

[0047] It should be noted that the client can generate an emoticon image corresponding to each target image, that is, the user only needs to perform one operation to generate emoticon images corresponding to multiple images, without having to operate on each image separately, thereby improving the efficiency of emoticon image generation.

[0048] Based on the scheme defined by the above steps S102 to S106, it can be known that in an embodiment of the present invention, a method of batch generating emoticon images corresponding to multiple images is adopted. After responding to a control instruction triggered for the current application, at least one candidate image is determined from the communication content of the current application, and the at least one candidate image is parsed to obtain selected features of the at least one candidate image. Then, a target image is obtained by screening from the at least one candidate image according to the image features, and the target image is displayed in the graphical user interface of the current application. Finally, in response to a selection operation for at least one target image, emoticon images corresponding to the target image corresponding to the selection operation are batch generated.

[0049] It is easy to notice that the present application can batch generate corresponding emoticon images from at least one candidate image in the communication content, thus avoiding the problem of low efficiency in emoticon image generation caused by operating each candidate image separately. In addition, in the process of generating an emoticon image from at least one candidate image, the present application also screens at least one candidate image according to image features, thereby avoiding the problem of waste of system resources caused by processing images that do not meet the requirements of emoticon images. In addition, since the screening operation is performed on at least one candidate image, in the present application, only images that meet the requirements of emoticon images are produced, thus avoiding the interference of images that do not meet the requirements of emoticon images and improving the efficiency of emoticon image generation. Finally, in the present application, the user can also perform further selection operations on the target image obtained by screening, and generate an emoticon image from the target image selected by the user, so that the user can flexibly select the image for which the emoticon image needs to be generated according to his or her needs, thereby improving the user experience.

[0050] It can be seen that the solution provided in this application achieves the purpose of generating multiple emoticon images at the same time, thereby realizing the technical effect of improving the generation efficiency of emoticon images, and further solving the technical problem of low emoticon image generation efficiency caused by the inability of existing technologies to generate multiple emoticon images at the same time.

[0051] In an optional embodiment, the graphical user interface of the current application includes an emoticon package generation control, for example, Figure 2The transparency of the emoticon package generation control in the graphical user interface shown can vary depending on whether the communication content contains an image. For example, when the communication content does not contain an image, the emoticon package generation control is in a transparent state, and when the communication content contains an image, the emoticon package generation control is in a non-transparent state. Optionally, the transparency of the emoticon package generation control can also vary depending on the type of image contained in the communication content. For example, when the communication content does not contain an image or the image contained in the communication content cannot generate an emoticon package image, the emoticon package generation control is in a transparent state, and when the communication content contains an image and the image contained in the communication content can generate an emoticon package image, the emoticon package generation control is in a non-transparent state.

[0052] In an optional embodiment, before parsing and screening at least one candidate image and generating an emoticon package image, the client first needs to obtain at least one candidate image. The client responds to an emoticon package generation instruction triggered by an emoticon package generation control, obtains communication content of a preset duration according to the emoticon package generation instruction, and then extracts at least one candidate image from the communication content.

[0053] Optionally, when a user needs to create an emoticon image, the user can operate the emoticon generation control on the display interface of the client, or operate the physical control for generating an emoticon image in the terminal device. After detecting the operation of generating an emoticon image, the client generates an emoticon generation instruction. The client obtains the communication content within a preset time period before the current time according to the emoticon generation instruction, and extracts at least one candidate image from the communication content.

[0054] It should be noted that after detecting the operation of generating an emoticon image, the client generates a prompt message to prompt the user to determine the extraction time of the communication content. For example, the client generates multiple time lengths for the user to choose, or the client generates an input box for the extraction time length, and the user can enter the extraction time length in the input box, so that the client can determine the preset time length based on the extraction time length.

[0055] In an optional embodiment, the client may also determine the communication content based on the number of communication objects corresponding to the communication content. Specifically, when the number of communication objects corresponding to the communication content is multiple, the client responds to the object selection instruction, determines the target object from the multiple communication objects, and filters out the target communication content associated with the target object from the communication content of a preset length according to the emoticon package generation instruction, wherein the communication object is the object communicating with the current object. For example, in a WeChat chat group, the communication object is other users in the WeChat chat group except the current user.

[0056] Optionally, the communication objects corresponding to the above-mentioned communication content are the number of objects participating in the social interaction. For example, in a WeChat chat group, there are 20 members, and the number of objects corresponding to the communication content is 20. When the number of objects corresponding to the communication content is multiple, the user can select a target object from multiple communication objects through the client. In this scenario, the client filters out communication content related to the target object as the target communication content. For example, the client filters out voice, text, images, videos, files, etc. sent by the target object within a preset time period from the communication content as the target communication content.

[0057] Optionally, when the number of objects corresponding to the communication content is only one, after the client detects that the user clicks on the emoticon package generation control, the client automatically obtains the communication content within a preset time period.

[0058] It should be noted that after receiving the emoticon package generation instruction, the client first detects whether there is an image in the communication content. If it is detected that there is no image in the communication content, the client generates a prompt message, wherein the prompt message is used to remind the user that there is no image in the communication content, and the user is required to reset the preset time length or reselect the communication content.

[0059] In an optional embodiment, after obtaining at least one preset candidate image from the communication content, the client can filter out at least one target image from the at least one candidate image based on image features. The client first detects whether the at least one candidate image contains text based on the image features. When it is determined that the at least one candidate image does not contain text based on the image features, the client filters out at least one first candidate image containing a subject image based on the image features. Then, the client filters out at least one second candidate image whose facial expression and / or body movement of the subject image meets a first preset condition from the at least one first candidate image. Finally, the client determines at least one target image based on the at least one second candidate image and displays the at least one target image. The subject image is an object with a facial expression.

[0060] Optionally, upon determining that at least one candidate image does not contain text, the client detects a subject object contained in the at least one candidate image and selects an image containing the subject image from the at least one candidate image to avoid interference with the emoticon package image by images of landscapes or physical objects. The subject object is an image with facial expressions, such as an animal, a human, or a cartoon.

[0061] Furthermore, after obtaining the first candidate image containing the subject image, the client further detects the facial expressions and / or body movements of the subject image, and eliminates images whose facial expressions and / or body movements do not meet the requirements based on the facial expressions and / or body movements of the subject image. For example, images with relatively normal facial expressions are eliminated, while images with relatively exaggerated facial expressions and / or body movements are retained, thereby avoiding interference of ID photos or everyday character images with emoticon package images.

[0062] It should be noted that at least one target image obtained through the above process may overlap with the image stored by the client for making emoticon images, or there may be multiple duplicate images in at least one target image. Making emoticon images for overlapping images will undoubtedly increase the consumption of system resources.

[0063] To reduce system resource consumption, the client also performs deduplication processing on the at least one second candidate image during the process of determining the at least one target image based on the at least one second candidate image. Specifically, the client removes images stored in a preset storage area from the at least one second candidate image and / or removes overlapping images from the at least one second candidate image to obtain the at least one target image.

[0064] Optionally, the client compares the image identifier (for example, the image name, generation time, etc.) corresponding to at least one candidate image with the target image identifier of the image pre-stored in a preset storage area of ​​the client. By comparing, the client removes the image whose image identifier is the same as the target image identifier from at least one candidate image, thereby achieving deduplication operation on at least one candidate image.

[0065] Optionally, the client can also obtain the image identifier corresponding to at least one candidate image, and detect whether there is an image with the same image identifier in at least one image. If so, the redundant images with the same image identifier in at least one image are eliminated, and only one image with the image identifier is retained, thereby achieving deduplication operation on at least one candidate image.

[0066] In an optional embodiment, when the client determines that at least one candidate image contains text based on image features, it obtains the text length of the text, and filters out at least one target image from the at least one candidate image based on the text length and image features, and displays the at least one target image.

[0067] Specifically, when the text length is greater than a preset length, the client eliminates at least one candidate image; when the text length is less than or equal to the preset length, the client filters out at least one first candidate image containing the subject image from at least one candidate image based on image features, and filters out at least one second candidate image whose facial expression and / or body movement of the subject image meets a first preset condition from at least one first candidate image, and then determines at least one target image based on the at least one second candidate image.

[0068] It should be noted that when the text length is long (for example, the above-mentioned text length is greater than the preset length), the client can determine that the text is used to annotate the candidate image, that is, the text is the annotation text, and is not the target text in the emoticon image. Therefore, by eliminating candidate images with longer text lengths, the interference of the annotation text on the generation of the emoticon image can be avoided.

[0069] In addition, it should be noted that when the text length is short (for example, the text length is less than or equal to the preset length), the client can use the above-mentioned processing method for candidate images that do not contain text to screen images.

[0070] Similarly, after obtaining at least one second candidate image, the client may perform image screening on the at least one second candidate image to obtain at least one target image. When performing image screening on the at least one second candidate image, the client needs to consider both image content and text content.

[0071] Specifically, the client first obtains image content from at least one second candidate image, and eliminates at least one third candidate image from the at least one second candidate image based on the text content and image content of the text to obtain at least one fourth candidate image. Then, the client eliminates images stored in a preset storage area from the at least one fourth candidate image, and / or eliminates overlapping images from the at least one fourth candidate image to obtain at least one target image. The text content of the at least one third candidate image does not match the image content of the at least one third candidate image.

[0072] Optionally, when screening the second candidate images containing text, the client first eliminates images whose text content and image content do not match in the second candidate images. For example, the text content of candidate image A is "Hahahaha" and the image content of candidate image A is a cartoon character crying. In this scenario, the client will eliminate candidate image A from the second candidate images.

[0073] Furthermore, after eliminating images whose text content does not match the image content from the second candidate images to obtain at least one fourth candidate image, the client performs deduplication processing on the at least one fourth candidate image.

[0074] It should be noted that the client's deduplication operation on the fourth candidate image is the same as the deduplication operation on the second candidate image that does not contain text, and will not be described in detail here.

[0075] In addition, it should be noted that after obtaining at least one target image in the above manner, the client automatically generates an emoticon package image corresponding to each target image without the user having to repeat the operation for each target image, thereby improving the efficiency of generating emoticon package images.

[0076] In an optional embodiment, in response to a selection operation for at least one target image, after batch generating emoticon package images corresponding to the target images corresponding to the selection operation, the client also matches the emoticon package images with preset emoticon package images to obtain matching results, and deduplicates the emoticon package images based on the matching results to obtain deduplicated emoticon package images.

[0077] That is, after obtaining the emoticon package images, the client can also perform a deduplication operation on the emoticon package images. Specifically, the client can compare the emoticon package images corresponding to the generated at least one target image with the emoticon package images stored on the client (i.e., the preset emoticon package images mentioned above), for example, by comparing the image identifiers, generation times, etc. of the emoticon package images. Through the comparison, the emoticon package images stored on the server are removed from the emoticon package images corresponding to the at least one target image, thereby avoiding the problem of poor user experience caused by storing multiple duplicate emoticon package images in the prior art.

[0078] In another optional embodiment, during the process of deduplicating candidate images, the client can also compare the similarity between the candidate images and preset emoticon package images (i.e., emoticon package images stored by the server), and delete images with a similarity greater than the preset similarity from the candidate images, without having to generate emoticon package images and then deduplicate the emoticon package images, thereby simplifying the deduplication steps of the emoticon package images.

[0079] Optionally, after deduplicating the emoticon images according to the matching results and obtaining the deduplicated emoticon images, the client performs a deletion operation and / or classification operation on the deduplicated emoticon images according to the corresponding control instructions. For example, the client generates a pop-up window and displays all the emoticon images in the pop-up window. The user can delete the emoticon images displayed in the pop-up window to save the remaining emoticon images after deletion locally on the client. In addition, the user can also classify the emoticon images displayed in the pop-up window and customize the names of the classified emoticon images. For example, the user can group the selected emoticon images together to obtain multiple sets and name each set so that the user can quickly find the customized emoticon images in the subsequent use of the emoticon images.

[0080] As can be seen from the above, the solution provided by this application can achieve one-click extraction of all images within a fixed time length in the communication content, filter multiple images, and then generate emoticon images from the filtered images with one click, thereby improving the efficiency of emoticon image generation. Moreover, after generating the emoticon images, the user can also filter and classify the generated emoticon images, which not only avoids the addition of duplicate emoticon images, but also enables users to quickly find customized emoticon images, improving the user experience of using emoticon images.

[0081] Example 2

[0082] According to an embodiment of the present invention, an embodiment of an image processing device is further provided, wherein: Figure 5 is a schematic diagram of an image processing apparatus according to an embodiment of the present invention. Figure 5 As shown, the device includes: a determination module 501 , a display module 503 and a generation module 505 .

[0083] Among them, the determination module 501 is used to respond to the control instruction triggered for the current application, determine at least one candidate image from the communication content of the current application, and parse at least one candidate image to obtain the image features of at least one candidate image; the display module 503 is used to display at least one target image in the graphical user interface of the current application, and the at least one target image is an image screened out from at least one candidate image according to the image features; the generation module 505 is used to respond to the selection operation for at least one target image, and batch generate emoticon package images corresponding to the target image corresponding to the selection operation.

[0084] It should be noted that the above-mentioned determination module 501, display module 503 and generation module 505 correspond to steps S102 to S106 in the above-mentioned embodiment. The examples and application scenarios implemented by the three modules and the corresponding steps are the same, but are not limited to the contents disclosed in the above-mentioned embodiment 1.

[0085] Optionally, the graphical user interface of the current application includes an emoticon package generation control, and the determination module includes: a first generation module, a first acquisition module, and an extraction module. The first generation module is configured to respond to an emoticon package generation instruction triggered by the emoticon package generation control; the first acquisition module is configured to acquire communication content of a preset duration based on the emoticon package generation instruction; and the extraction module is configured to extract at least one candidate image from the communication content.

[0086] Optionally, the first acquisition module includes: a first determination module and a first screening module. The first determination module is configured to, when the communication content corresponds to multiple communication objects, respond to the object selection instruction and determine a target object from the multiple communication objects, wherein the communication object is a object communicating with the current object; and the first screening module is configured to, based on the emoticon package generation instruction, screen target communication content associated with the target object from communication content of a preset duration.

[0087] Optionally, the display module includes: a second screening module, a third screening module, and a second determination module. The second screening module is configured to, when it is determined based on image features that at least one candidate image does not contain text, screen out at least one first candidate image containing a subject image from the at least one candidate image based on the image features, wherein the subject image is an object with facial expressions; the third screening module is configured to screen out at least one second candidate image from the at least one first candidate image, wherein the subject image's facial expression and / or body movements meet a first preset condition; and the second determination module is configured to determine at least one target image based on the at least one second candidate image, and display the at least one target image.

[0088] Optionally, the second determination module includes: a first elimination module, used to eliminate images stored in a preset storage area from at least one second candidate image, and / or eliminate overlapping images in at least one second candidate image to obtain at least one target image.

[0089] Optionally, the display module includes: a second acquisition module and a fourth screening module. The second acquisition module is configured to acquire the text length when at least one candidate image is determined to contain text based on image features; and the fourth screening module is configured to screen at least one target image from the at least one candidate image based on the text length and image features, and display the at least one target image.

[0090] Optionally, the fourth screening module includes: a second elimination module, a fifth screening module, a sixth screening module, and a third determination module. The second elimination module is configured to eliminate at least one candidate image when the text length is greater than a preset length; the fifth screening module is configured to filter out at least one first candidate image containing a subject image from at least one candidate image based on image features when the text length is less than or equal to the preset length, wherein the subject image is an object with facial expressions; the sixth screening module is configured to filter out at least one second candidate image from at least one first candidate image whose subject image's facial expression and / or body movements meet a first preset condition; and the third determination module is configured to determine at least one target image based on at least one second candidate image.

[0091] Optionally, the third determination module includes: a third acquisition module, a third elimination module, and a fourth elimination module. The third acquisition module is used to acquire the image content of at least one second candidate image; the third elimination module is used to eliminate at least one third candidate image of at least one second candidate image based on the text content and image content of the text, to obtain at least one fourth candidate image, wherein the text content of at least one third candidate image does not match the image content of at least one third candidate image; the fourth elimination module is used to eliminate images stored in a preset storage area from at least one fourth candidate image, and / or eliminate overlapping images in at least one fourth candidate image, to obtain at least one target image.

[0092] Optionally, the image processing device further includes a matching module and a processing module. The matching module is configured to, in response to a selection operation on at least one target image, batch-generate emoticon images corresponding to the target images corresponding to the selection operation, and then match the emoticon images with preset emoticon images to obtain matching results. The processing module is configured to deduplicate the emoticon images based on the matching results to obtain deduplicated emoticon images.

[0093] Optionally, the image processing device also includes: a processing submodule, which is used to deduplicate the emoticon package image according to the matching result, and after obtaining the deduplicated emoticon package image, perform deletion operations and / or classification operations on the deduplicated emoticon package image according to the corresponding control instructions.

[0094] Example 3

[0095] According to another aspect of an embodiment of the present invention, a computer-readable storage medium is provided, in which a computer program is stored. The computer program is configured to execute the image processing method in the above-mentioned embodiment 1 when running.

[0096] Example 4

[0097] According to another aspect of an embodiment of the present invention, an electronic device is also provided, which includes one or more processors; a storage device for storing one or more programs, which, when the one or more programs are executed by the one or more processors, enables the one or more processors to run the programs, wherein the programs are configured to execute the image processing method in the above-mentioned embodiment 1 when running.

[0098] The serial numbers of the above embodiments of the present invention are for description only and do not represent the advantages or disadvantages of the embodiments.

[0099] In the above embodiments of the present invention, the description of each embodiment has its own focus. For parts that are not described in detail in a certain embodiment, reference can be made to the relevant descriptions of other embodiments.

[0100] In the several embodiments provided in this application, it should be understood that the disclosed technical content can be implemented in other ways. Among them, the device embodiments described above are only exemplary. For example, the division of the units can be a logical function division. In actual implementation, there may be other division methods, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of units or modules, which can be electrical or other forms.

[0101] 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 may be located in one place or distributed across multiple units. Some or all of the units may be selected according to actual needs to achieve the purpose of the present embodiment.

[0102] In addition, the functional units in the various embodiments of the present invention may be integrated into a single processing unit, each unit may exist physically separately, or two or more units may be integrated into a single unit. The aforementioned integrated units may be implemented in the form of hardware or software functional units.

[0103] If the integrated unit is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art, or all or part of the technical solution can be embodied in the form of a software product. The computer software product is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, server or network device, etc.) to perform all or part of the steps of the method described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), mobile hard disk, magnetic disk or optical disk, etc. Various media that can store program codes.

[0104] The above is only a preferred embodiment of the present invention. It should be pointed out that for ordinary technicians in this technical field, several improvements and modifications can be made without departing from the principles of the present invention. These improvements and modifications should also be regarded as the scope of protection of the present invention.

Claims

1. An image processing method, characterized in that: include: In response to a control instruction triggered for a current application, determining at least one candidate image from communication content of the current application, and parsing the at least one candidate image to obtain image features of the at least one candidate image; displaying at least one target image on a graphical user interface of the current application, wherein the at least one target image is an image selected from the at least one candidate image according to the image feature; In response to a selection operation on the at least one target image, batch-generating emoticon package images corresponding to the target image corresponding to the selection operation; Among them, displaying at least one target image in the graphical user interface of the current application includes: when it is determined according to the image features that the at least one candidate image does not contain text, filtering out at least one first candidate image containing a subject image from the at least one candidate image according to the image features, wherein the subject image is an object with facial expression; filtering out at least one second candidate image whose facial expression and / or body movement of the subject image meets a first preset condition from the at least one first candidate image; determining the at least one target image based on the at least one second candidate image, and displaying the at least one target image.

2. The method according to claim 1, characterized in that The graphical user interface of the current application includes an emoticon package generation control, and the responding to the control instruction triggered for the current application to determine at least one candidate image from the communication content of the current application includes: Responding to an emoticon package generation instruction triggered by the emoticon package generation control; Acquire communication content of a preset duration according to the emoticon package generation instruction; The at least one candidate image is extracted from the communication content.

3. The method according to claim 2, characterized in that Acquiring communication content of a preset duration according to the emoticon package generation instruction includes: When there are multiple communication objects corresponding to the communication content, responding to the object selection instruction, determining a target object from the multiple communication objects, wherein the communication object is an object communicating with the current object; Target communication content associated with the target object is filtered out from the communication content of the preset duration according to the emoticon package generation instruction.

4. The method according to claim 1, wherein Determining the at least one target image according to the at least one second candidate image includes: The at least one target image is obtained by removing images stored in a preset storage area from the at least one second candidate image and / or removing overlapping images from the at least one second candidate image.

5. The method according to claim 1, wherein Displaying at least one target image in a graphical user interface of the current application includes: When it is determined according to the image features that the at least one candidate image contains text, obtaining a text length of the text; The at least one target image is selected from the at least one candidate image according to the text length and the image feature, and the at least one target image is displayed.

6. The method according to claim 5, characterized in that Screening out the at least one target image from the at least one candidate image according to the text length and the image feature includes: When the length of the text is greater than a preset length, eliminating the at least one candidate image; When the length of the text is less than or equal to the preset length, screening out at least one first candidate image containing a subject image from the at least one candidate image according to the image features, wherein the subject image is an object with a facial expression; Selecting at least one second candidate image from the at least one first candidate image, wherein the facial expression and / or body movement of the subject image meets a first preset condition; The at least one target image is determined according to the at least one second candidate image.

7. The method according to claim 6, characterized in that Determining the at least one target image according to the at least one second candidate image includes: Acquiring image content of the at least one second candidate image; Eliminating at least one third candidate image of the at least one second candidate image based on the text content of the text and the image content to obtain at least one fourth candidate image, wherein the text content of the at least one third candidate image does not match the image content of the at least one third candidate image; The at least one target image is obtained by removing images stored in a preset storage area from the at least one fourth candidate image and / or removing overlapping images from the at least one fourth candidate image.

8. The method according to claim 1, characterized in that After batch-generating emoticon images corresponding to the target images corresponding to the selection operation in response to the selection operation on the at least one target image, the method further includes: Matching the emoticon package image with a preset emoticon package image to obtain a matching result; Deduplication processing is performed on the emoticon package image according to the matching result to obtain a deduplicated emoticon package image.

9. The method according to claim 8, characterized in that After performing deduplication processing on the emoticon package image according to the matching result to obtain the deduplicated emoticon package image, the method further includes: The deleted emoticon package images are subjected to a deletion operation and / or a classification operation according to the response control instruction.

10. An image processing device, characterized in that: include: a determination module, configured to respond to a control instruction triggered for a current application, determine at least one candidate image from the communication content of the current application, and parse the at least one candidate image to obtain image features of the at least one candidate image; a display module, configured to display at least one target image on a graphical user interface of the current application, wherein the at least one target image is an image selected from the at least one candidate image according to the image feature; A generating module, configured to respond to a selection operation on the at least one target image and batch generate emoticon package images corresponding to the target images corresponding to the selection operation; In which, the display module is also used to: when it is determined according to the image features that the at least one candidate image does not contain text, filter out at least one first candidate image containing a subject image from the at least one candidate image according to the image features, wherein the subject image is an object with facial expression; filter out at least one second candidate image from the at least one first candidate image, in which the facial expression and / or body movement of the subject image meets a first preset condition; determine the at least one target image based on the at least one second candidate image, and display the at least one target image.

11. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, wherein the computer program is configured to execute the image processing method according to any one of claims 1 to 9 when executed.

12. An electronic device, characterized in that: The electronic device includes one or more processors; a storage device for storing one or more programs, which, when executed by the one or more processors, enables the one or more processors to run the programs, wherein the programs are configured to execute the image processing method described in any one of claims 1 to 9 when run.

Images