Image data processing method and device, electronic equipment and storage medium
By determining sensitive content processing strategies based on image types and desensitizing videos and photos shared on the Internet, the problems of privacy leakage and psychological impact are solved, and user experience and system efficiency are improved.
Patent Information
- Application Number
- CN202311851270.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2023-12-28
- Publication Date
- 2025-07-01
AI Technical Summary
Video footage or photos shared and disseminated on the Internet may contain private content or adverse content, resulting in user privacy leakage or psychological impact.
By determining the sensitive content processing strategy based on the image type and performing desensitization processing, the effect and intelligence of the desensitization processing are improved.
It effectively avoids user privacy leakage and psychological impact, improves user experience, and reduces the system's computing volume and power consumption.
Smart Images
Figure CN120238613A_ABST
Abstract
Description
Technical Field
[0001] This application relates to the field of image processing technology, and particularly relates to a method and device for processing image data, an electronic device, and a storage medium. Background Art
[0002] With the rapid development of Internet technology, current users can conduct video calls, share multimedia data such as videos or photos through electronic devices, enriching the entertainment methods of users.
[0003] However, it is found in practice that video images or photos shared and spread on the Internet may involve privacy content or inappropriate content, which may lead to the leakage of user privacy or cause psychological impact due to receiving inappropriate information. Summary of the Invention
[0004] Embodiments of this application disclose a method and device for processing image data, an electronic device, and a storage medium, which can select an appropriate sensitive content processing strategy for desensitization processing according to the image type corresponding to the first image, improving the effect of desensitization processing.
[0005] In a first aspect, an embodiment of this application discloses a method for processing image data, the method comprising:
[0006] Obtain a first image;
[0007] Determine a sensitive content processing strategy corresponding to the first image according to the image type corresponding to the first image, where the image type includes an image to be sent or a received image;
[0008] Desensitize the sensitive content in the first image according to the sensitive content processing strategy to obtain a second image.
[0009] In a second aspect, an embodiment of this application discloses a device for processing image data, the device comprising:
[0010] An obtaining unit, configured to obtain a first image;
[0011] A first determining unit, configured to determine a sensitive content processing strategy corresponding to the first image according to the image type corresponding to the first image, where the image type includes an image to be sent or a received image;
[0012] A first processing unit, configured to desensitize the sensitive content in the first image according to the sensitive content processing strategy to obtain a second image.
[0013] In a third aspect, an embodiment of this application discloses an electronic device, comprising:
[0014] A memory storing executable program code; a processor coupled to the memory;
[0015] The processor calls the executable program code stored in the memory and executes the method for processing image data disclosed in the first aspect of the embodiments of the present application.
[0016] The fourth aspect of the embodiments of the present application discloses a computer-readable storage medium storing a computer program, wherein the computer program causes a computer to execute the method for processing image data disclosed in the first aspect of the embodiments of the present application.
[0017] The fifth aspect of the embodiments of the present application discloses a computer program product, which when running on a computer, causes the computer to execute some or all of the steps of any one of the methods disclosed in the first aspect of the embodiments of the present application.
[0018] The sixth aspect of the embodiments of the present application discloses an application publishing platform for publishing a computer program product, wherein when the computer program product runs on a computer, it causes the computer to execute some or all of the steps of any one of the methods disclosed in the first aspect of the embodiments of the present application.
[0019] Compared with the related art, the embodiments of the present application have the following beneficial effects:
[0020] In the embodiments of the present application, the image type of the obtained first image may include an image to be sent or a received image. It can be understood that the sensitive content in the image to be sent and the received image by the user may be different. For example, the user may be more sensitive to the privacy content in the image to be sent, while the received image may be more sensitive to the bad content. In this case, when the first image is obtained, the sensitive content processing strategy corresponding to the first image can be determined according to the image type corresponding to the first image, improving the intelligence and flexibility of the method; and then, according to the determined sensitive content processing strategy, the sensitive content in the first image can be desensitized to obtain a second image with the sensitive content removed, improving the desensitization effect, avoiding the leakage of the user's privacy, or the psychological impact caused by seeing the bad content, and improving the user experience. BRIEF DESCRIPTION OF THE DRAWINGS
[0021] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required to be used in the embodiments. Obviously, the drawings described below are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.
[0022] Figure 1It is a schematic flowchart of a video call process disclosed in an embodiment of the present application;
[0023] Figure 2 It is a schematic flowchart of a method for processing image data disclosed in an embodiment of the present application;
[0024] Figure 3 It is a schematic flowchart of another method for processing image data disclosed in an embodiment of the present application;
[0025] Figure 4 It is a schematic diagram of a custom interface disclosed in an embodiment of the present application;
[0026] Figure 5 It is a schematic flowchart of yet another method for processing image data disclosed in an embodiment of the present application;
[0027] Figure 6 It is a schematic diagram of the display of prompt information disclosed in an embodiment of the present application;
[0028] Figure 7A It is a schematic flowchart of still another method for processing image data disclosed in an embodiment of the present application;
[0029] Figure 7B It is a schematic diagram of the structure of an electronic device disclosed in an embodiment of the present application;
[0030] Figure 8 It is a schematic diagram of the structure of a device for processing image data disclosed in an embodiment of the present application;
[0031] Figure 9 It is a schematic diagram of the structure of an electronic device disclosed in an embodiment of the present application. Detailed implementation manners
[0032] Next, the technical solutions in the embodiments of the present application will be clearly and completely described in conjunction with the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are only a part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present application.
[0033] It should be noted that the terms "first", "second", "third", "fourth", etc. in the specification and claims of this application are used to distinguish different objects, rather than to describe a specific order. The terms "including" and "having" in the embodiments of this application and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product, or device that includes a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units that are not clearly listed or are inherent to these processes, methods, products, or devices.
[0034] The embodiments of this application disclose a method and device for processing image data, an electronic device, and a storage medium, which can select an appropriate sensitive content processing strategy for desensitization processing according to the image type corresponding to the first image, improving the effect of desensitization processing.
[0035] The technical solution of this application will be described in detail below with reference to specific embodiments.
[0036] To introduce the image data processing method disclosed in the embodiments of this application more clearly, first, the application scenarios applicable to this method will be introduced.
[0037] Optionally, this method can be applied to various electronic devices with image processing capabilities, including: portable electronic devices such as mobile phones and tablets, wearable devices such as smart watches and smart bracelets, or projection devices, image projection devices, etc., which are not limited herein.
[0038] Optionally, this method can be applied during a video call on an electronic device, or during the process of transmitting and sharing multimedia data such as videos and pictures, or during the process of projecting multimedia data such as videos and pictures, and can also be applied to the multimedia data flow process of a multimedia framework deeply customized based on WebRTC, which is not limited herein.
[0039] In practice, it is found that the video frames or photos shared and spread by users on the Internet may involve privacy content or inappropriate content. For example, during a video call, a user may inadvertently send a video frame involving privacy content to the opposite device of the call, resulting in the leakage of the user's privacy; or receive a video frame including inappropriate content sent by the opposite device, which may have an impact on the user's psychology.
[0040] To avoid the above situations, the embodiments of this application disclose a method for processing image data to solve the above problems. Taking the process of a video call as an example below, in combination with Figure 1 The method for processing image data disclosed in the embodiments of this application will be introduced. Figure 1This is a schematic flowchart of a video call process disclosed in an embodiment of the present application. Optionally, this method can be applied to one or more electronic devices for video calls. Hereinafter, two examples are used for illustration, which should not limit the embodiments of the present application.
[0041] Optionally, when the first electronic device 110 captures the first video call screen, it can determine the corresponding first sensitive content processing strategy according to the image type of the first video call screen being an image to be sent; then, according to the first sensitive content processing strategy, desensitize the first video call screen to obtain the second video call screen; then, the first electronic device 110 can perform operations such as encoding, encrypting, and packaging on the second video call screen to obtain a video data packet, and send the video data packet to the second electronic device 120;
[0042] When the second electronic device 120 receives the video data packet, it can perform operations such as decompressing, decrypting, and decoding the video data packet to obtain the second video call screen; then, the second electronic device 120 can determine the corresponding second sensitive content processing strategy according to the image type of the second video call screen being a received image; then, according to the second sensitive content processing strategy, desensitize the second video call screen to obtain the third video call screen; then, the second electronic device 120 can render and display the third video call screen.
[0043] It can be seen that the image data processing method disclosed in the embodiments of the present application can determine the sensitive content processing strategy corresponding to the video call image according to the image type corresponding to the video call image, improving the intelligence and flexibility of the method; then, according to the determined sensitive content processing strategy, desensitize the sensitive content in the video call image to obtain a video call image from which the sensitive content has been removed, thereby avoiding the leakage of user privacy or the psychological impact caused by the presence of bad information in the video call screen, and improving the user experience. In addition, the method disclosed in the embodiments of the present application can be implemented on the electronic device side, without the need to interact with the cloud server and without relying on the network, thereby improving the low latency of the method and expanding the usage scenarios of the method.
[0044] Based on this, the following introduces the image data processing method, device, electronic device, and storage medium disclosed in the embodiments of the present application.
[0045] Please refer to Figure 2 , Figure 2 This is a schematic flowchart of an image data processing method disclosed in an embodiment of the present application. Optionally, this method can be used for the above-mentioned electronic devices or other execution entities, which is not limited herein. Optionally, this method may include the following steps:
[0046] 202. Obtain the first image.
[0047] In the embodiments of the present application, the first image may be an image collected by an electronic device, or an image received by the electronic device from other electronic devices or the Internet, which is not limited herein.
[0048] Optionally, the first image may be an image that has not been desensitized, or an image that has been desensitized, which is not limited herein.
[0049] Optionally, the first image may be a photo, or an image of a certain frame in video data, which is not limited herein.
[0050] 204. Determine a sensitive content processing strategy corresponding to the first image according to the image type corresponding to the first image, where the image type includes an image to be sent or a received image.
[0051] In the embodiments of the present application, the image type may include an image to be sent, a received image, etc. Among them, the image to be sent is an image that the electronic device is to send to other electronic devices, including but not limited to an image collected by the electronic device, or an image stored in the electronic device. The received image is an image received by the electronic device from other electronic devices, or an image downloaded from the Internet, which is not limited herein.
[0052] In some other optional embodiments, the image type may further include other types. Optionally, the received image may be further classified into an image received from other electronic devices, an image downloaded from the Internet, etc., which is not limited herein. It can be understood that the sources of the received images are different, and the sensitive information included therein may also vary. For this, different sensitive content processing strategies can be adopted for targeted desensitization processing.
[0053] Optionally, the electronic device may obtain the image attributes of the first image. The image attributes may include the source information of the first image. Further, the electronic device may determine the image type corresponding to the first image according to the source information of the first image. Optionally, the source information may include the identification information of the electronic device that collected the first image. Optionally, if the identification information is this electronic device, it may be determined that the image type of the first image is an image to be sent; if the identification information is other electronic devices, it may be determined that the image type of the first image is a received image, which is not limited herein.
[0054] Optionally, the electronic device may bind various image types to corresponding sensitive content processing policies; further, the electronic device may determine the corresponding sensitive content processing policy according to the image type corresponding to the first image and the corresponding binding relationship. Optionally, when the electronic device determines the sensitive content processing policy according to the image type corresponding to the first image and the corresponding binding relationship, it may also receive a custom instruction input, and further adjust the determined sensitive content processing policy according to the custom instruction to obtain the sensitive content processing policy that meets the current needs of the user, which is not limited herein.
[0055] Optionally, the sensitive content processing policy may include one or more of the sensitive content to be desensitized, the processing method for desensitization, and the degree of desensitization processing, which is not limited herein.
[0056] Optionally, the sensitive content may include privacy content, inappropriate content, etc. Privacy content may include content involving user privacy such as user avatars, user account password information, etc.; inappropriate content may include content involving elements such as terror and violence, which is not limited herein.
[0057] Optionally, the processing method for desensitization may include blurring, adding mosaics, etc., which is not limited herein.
[0058] 206. According to the sensitive content processing policy, desensitize the sensitive content in the first image to obtain a second image.
[0059] In the embodiment of the present application, when the electronic device desensitizes the sensitive content in the first image according to the sensitive content processing policy to obtain a second image, if the second image is obtained by desensitizing the image to be sent, the second image may be sent to the target receiver; if the second image is obtained by desensitizing the received image, the second image may be rendered and displayed, which is not limited herein.
[0060] When implementing the methods disclosed in the above embodiments, the image types of the obtained first images may include images to be sent or received images. It can be understood that the sensitive content in the images to be sent and received by the user may be different. For example, the user may be more sensitive to the privacy content in the images to be sent, while the received images may be more sensitive to inappropriate content. In this case, when the first image is obtained, the sensitive content processing strategy corresponding to the first image can be determined according to the image type of the first image, which improves the intelligence and flexibility of the method; furthermore, the sensitive content in the first image can be desensitized according to the determined sensitive content processing strategy to obtain a second image with the sensitive content removed, which improves the desensitization effect, avoids the leakage of the user's privacy, or the psychological impact caused by seeing inappropriate content, and improves the user experience.
[0061] Please refer to Figure 3 , Figure 3 which is a schematic flowchart of another method for processing image data disclosed in the embodiments of the present application. Optionally, this method can be used in the above-mentioned electronic device or other execution entities, which is not limited herein. Optionally, this method may include the following steps:
[0062] 302. Obtain a first image.
[0063] 304. Determine processing parameters, where the processing parameters include one or more desensitization processing methods and the processing degrees corresponding to one or more desensitization processing methods.
[0064] As described above, the sensitive content processing strategy may include the processing method of the desensitization processing performed and the processing degree of the desensitization processing performed. Optionally, the processing method and the processing degree may be determined by the initial parameters set by the developer based on a large amount of development experience, or may be determined by the custom parameters set by the user according to the usage requirements, which is not limited herein.
[0065] Optionally, when the input custom parameters are detected, the custom parameters can be determined as the processing parameters. Optionally, when the input custom parameters are not detected, the initial parameters stored in the electronic device can be determined as the processing parameters, which is not limited herein.
[0066] Please refer to Figure 4 , Figure 4 which is a schematic diagram of a custom interface disclosed in the embodiments of the present application. Optionally, the electronic device can output a custom interface 400, where the custom interface 400 may include one or more desensitization processing methods 410, and the processing methods 410 include but are not limited to Figure 4The modules shown perform processing, adding mosaic processing, etc. Users can customize the processing method for sensitive content by checking the corresponding processing method 410.
[0067] Optionally, the customization interface 400 may further include a processing degree 420 corresponding to one or more desensitization processing methods. Among them, users can adjust the processing degree corresponding to various processing methods by dragging Figure 4 the virtual button 430 therein. In some other alternative embodiments, users can also directly determine the processing degree by inputting specific processing degree parameters, Figure 4 which should not limit the embodiments of the present application.
[0068] Furthermore, the electronic device can determine the custom parameters according to the custom operations input by the user in the customization interface 400.
[0069] Implementing the above method, the electronic device can, when detecting the input custom parameters, determine the custom parameters as processing parameters; while in the case where no input custom parameters are detected, it can determine the initial parameters stored in the electronic device as processing parameters, improving the intelligence and flexibility of the method.
[0070] 306. Determine the sensitive content processing strategy according to the image type corresponding to the first image and the processing parameters.
[0071] As an alternative implementation manner, the sensitive content processing strategy may include a first sensitive content processing strategy and a second sensitive content processing strategy. Among them, the first sensitive content processing strategy may correspond to the image to be sent, and the second sensitive content processing strategy may correspond to the received image.
[0072] Optionally, the sensitive content for which the first sensitive content processing strategy and the second sensitive content processing strategy perform desensitization processing is different, and / or, the processing methods for which the first sensitive content processing strategy and the second sensitive content processing strategy perform desensitization processing are different; and / or, the processing degrees for which the first sensitive content processing strategy and the second sensitive content processing strategy perform desensitization processing are different, which are not limited herein.
[0073] Implementing the above method, the electronic device can adopt different sensitive content processing strategies according to different image types, improving the intelligence and flexibility of the method.
[0074] Optionally, the situation where the sensitive content for which the first sensitive content processing strategy and the second sensitive content processing strategy perform desensitization processing is different may include: the sensitive content for which the first sensitive content processing strategy performs desensitization processing at least includes privacy content, and the sensitive content for which the second sensitive content processing strategy performs desensitization processing includes bad content.
[0075] It can be understood that the user may have different sensitivities to sensitive content in the to-be-sent image and the received image. For example, the user may be more sensitive to privacy content in the to-be-sent image, while the received image may be more sensitive to inappropriate content. In this regard, the sensitive content to be desensitized by the first sensitive content processing strategy for the to-be-sent image may at least include privacy content; and the sensitive content to be desensitized by the second sensitive content processing strategy for the received image may at least include inappropriate content.
[0076] By implementing the above method, according to the image type corresponding to the first image, a targeted sensitive content processing strategy can be adopted to perform targeted desensitization processing on the content that the user is more sensitive to in the first image, thereby avoiding the leakage of the user's privacy or the psychological impact caused by seeing inappropriate content, and improving the user experience.
[0077] Optionally, when the electronic device determines the first sensitive content processing strategy or the second sensitive content processing strategy according to the image type corresponding to the first image, it can further adjust the first sensitive content processing strategy or the second sensitive content processing strategy according to the processing parameters to obtain a sensitive content processing strategy determined according to the image type and the processing parameters.
[0078] 308. Desensitize the sensitive content in the first image according to the sensitive content processing strategy to obtain a second image.
[0079] Please refer to again Figure 4 , the custom interface 400 may further include an enable switch 440 for whether to perform desensitization processing. Optionally, when the enable switch 440 is in the on state, desensitize the sensitive content in the first image according to the sensitive content processing strategy; if the enable switch 440 is in the off state, do not desensitize the sensitive content in the first image. In this regard, the user can decide whether to perform desensitization processing by adjusting the enable switch 440, which improves the flexibility and controllability of the method and the user experience.
[0080] As an optional implementation manner, the electronic device can perform image recognition on the first image according to the sensitive content processing strategy to determine whether the first image includes sensitive content; if the first image includes sensitive content, desensitize the sensitive content in the first image; if the first image does not include sensitive content, do not desensitize the first image.
[0081] By implementing the above method, the electronic device can first determine whether the first image includes sensitive content. If so, desensitization processing is performed. If not, desensitization processing is not performed, thereby reducing the amount of calculation of the electronic device and reducing power consumption; in addition, the processing efficiency of the first image is also accelerated.
[0082] Optionally, the electronic device may preprocess the first image, and the preprocessing may include performing operations such as video denoising, image enhancement, and image segmentation on the input first image to facilitate subsequent feature extraction and classifier training.
[0083] Then, the electronic device may perform image feature extraction on the preprocessed first image to obtain first image features, wherein the first image features may include color, texture, shape, etc., so as to facilitate subsequent classification by a classifier.
[0084] Then, the electronic device can input the first image feature into a classification model based on a convolutional neural network to determine whether the first image includes sensitive content. Optionally, the classification model based on the convolutional neural network can analyze the first image to determine whether the first image contains sensitive content, and if so, output the first image with the location and type of the sensitive content marked, otherwise directly output the first image.
[0085] The electronic device can then determine whether the first image includes sensitive content based on whether the location and type of sensitive content are marked in the first image output by the classification model based on the convolutional neural network.
[0086] As an optional implementation, the sensitive content type to be detected included in the sensitive content processing strategy may include: a user-defined sensitive content type. Optionally, the electronic device may perform image recognition on the first image according to the sensitive content processing strategy to determine whether the first image includes sensitive content corresponding to the sensitive content type to be detected.
[0087] Please refer again Figure 4 The custom interface 400 may also include one or more sensitive content types 450, including but not limited to Figure 4 The types of pornography, blood, horror and personal privacy shown are Figure 4 This shall not be construed as limiting the embodiments of the present application. Optionally, the user may check the corresponding sensitive content type from the defined sensitive content type.
[0088] By implementing the above method, users can customize the type of sensitive content to be detected, which improves the controllability and customizability of the method, thereby improving the user experience.
[0089] As another alternative implementation, the types of sensitive content to be detected included in the sensitive content processing policy may be determined according to the image type of the first image. Optionally, when the image type of the first image is an image to be sent, the types of sensitive content to be detected at least include privacy content; when the image content of the first image is a received image, the types of sensitive content to be detected at least include inappropriate content.
[0090] Optionally, considering that the electronic device at the other end can also perform desensitization processing on the image, when the image type of the first image is an image to be sent, the types of sensitive content to be detected may only include privacy content and not include inappropriate content; when the image content of the first image is a received image, the types of sensitive content to be detected may only include inappropriate content and not include privacy content, thereby reducing the computing amount and power consumption of the electronic device and improving the efficiency of image processing.
[0091] Optionally, when the electronic device determines that the first image includes sensitive content, it may determine whether the electronic device has the permission to send the sensitive content to the police terminal; if so, the electronic device may send the sensitive content to the police terminal.
[0092] Optionally, the permission to send sensitive content to the police terminal may be determined according to the authorization instruction input by the user, which is not limited herein. Optionally, the police terminal may be a server, communicator, etc. for police work, which is not limited herein.
[0093] Implementing the above method, the electronic device can, with the consent of the user, feedback the detected sensitive content to the police as evidence for handling cases.
[0094] By implementing the methods disclosed in the above embodiments, the sensitive content processing strategy corresponding to the first image can be determined according to the image type corresponding to the first image, which improves the intelligence and flexibility of the method. Furthermore, the sensitive content in the first image can be desensitized according to the determined sensitive content processing strategy to obtain a second image with the sensitive content removed, thereby avoiding the leakage of user privacy or the psychological impact caused by seeing inappropriate content, and improving the user experience. In addition, when a custom parameter is detected as input, the custom parameter can be determined as the processing parameter. When no custom parameter is detected as input, the initial parameter stored in the electronic device can be determined as the processing parameter, which improves the intelligence and flexibility of the method. Moreover, different sensitive content processing strategies can be adopted according to different image types, which improves the intelligence and flexibility of the method. Also, according to the image type corresponding to the first image, a targeted sensitive content processing strategy can be adopted to specifically desensitize the content that the user is more sensitive to in the first image, thereby avoiding the leakage of user privacy or the psychological impact caused by seeing inappropriate content, and improving the user experience. Additionally, it can be first determined whether the first image contains sensitive content. If it contains sensitive content, desensitization processing is performed; if it does not contain sensitive content, no desensitization processing is performed, thereby reducing the computational load of the electronic device and lowering the power consumption. In addition, the processing efficiency for the first image is also accelerated. Moreover, the user can customize the type of sensitive content to be detected, which improves the controllability and customizability of the method and thus enhances the user experience. Also, with the consent of the user, the detected sensitive content can be reported to the police as evidence for handling cases.
[0095] Please refer to Figure 5 , Figure 5 which is a schematic flowchart of another method for processing image data disclosed in the embodiments of the present application. Optionally, this method can be applied to the above-mentioned electronic device or other execution entities, which is not limited herein. Optionally, the method may include the following steps:
[0096] 502. Obtain a first image.
[0097] 504. Determine the sensitive content processing strategy corresponding to the first image according to the image type corresponding to the first image, where the image type includes an image to be sent or a received image.
[0098] 506. Desensitize the sensitive content in the first image according to the sensitive content processing strategy to obtain a second image.
[0099] 508. Output a prompt message, which is used to prompt that the first image contains sensitive content and has been desensitized, and provide at least one post-processing method; and, if a selected post-processing method is detected, process the second image data according to the selected post-processing method.
[0100] Optionally, the electronic device can output the prompt message through a preset display method. The preset display method can include pop-up windows, information bars, etc., which are not limited herein.
[0101] Please refer to Figure 6 , Figure 6 FIG. is a schematic diagram of a pop-up window of a prompt message disclosed in an embodiment of the present application. Optionally, the prompt message can be output through window 600, where window 600 can include a prompt content 610 for prompting that the first image contains sensitive content and has been desensitized, and at least one post-processing method 620.
[0102] By implementing the above method, the electronic device can process sensitive content and pop up a prompt message at the same time, allowing the user to choose whether to continue desensitizing the sensitive content, giving the user the right to make independent choices, and at the same time avoiding the leakage of the user's privacy. In addition, the pop-up message can temporarily block the second image, thus avoiding the user being impacted by the sensitive content in the second image at the first time.
[0103] Optionally, the post-processing method can include one or more of whether to retain the desensitization effect in the second image, whether to send the second image to the target recipient, and whether to display the second image, which is not limited herein.
[0104] By implementing the above method, the electronic device can allow the user to choose whether to continue desensitizing the sensitive content, whether to send the processed second image, or whether to display the processed second image, giving the user the right to make independent choices, and at the same time avoiding the leakage of the user's privacy and also avoiding the user being impacted by the sensitive content in the second image at the first time.
[0105] In an optional implementation manner, the electronic device can detect the current image sharing scenario. If the current image sharing scenario is a bad content popularization scenario, the selected post-processing method can include not retaining the desensitization effect in the second image and sending the second image to the target recipient, or not retaining the desensitization effect in the second image and displaying the second image, which is not limited herein.
[0106] For example, when in the scenario of an online meeting course teaching and the teaching needs to use a scary picture as a teaching aid, the desensitization effect in the second image can be not retained, which improves the flexibility and intelligence of this.
[0107] By implementing the methods disclosed in the above embodiments, the sensitive content processing strategy corresponding to the first image can be determined according to the image type corresponding to the first image, which improves the intelligence and flexibility of the method. Furthermore, the sensitive content in the first image can be desensitized according to the determined sensitive content processing strategy to obtain a second image with the sensitive content removed, thereby avoiding the leakage of user privacy or the psychological impact caused by seeing inappropriate content, and improving the user experience. In addition, when processing the sensitive content, a prompt message can be popped up to allow the user to choose whether to continue desensitizing the sensitive content, giving the user the right to make an independent choice and avoiding the leakage of user privacy. Moreover, the pop-up message can temporarily block the second image, thus avoiding the user being impacted by the sensitive content in the second image immediately.
[0108] Please refer to Figure 7A , Figure 7A which is a schematic flowchart of another method for processing image data disclosed in the embodiments of the present application, and is used to assist in understanding the method for processing image data disclosed in the embodiments of the present application. Among them:
[0109] Step 702: Obtain a first image;
[0110] Step 704: Determine whether to desensitize the first image; if yes, execute step 706; if no, execute step 716;
[0111] Step 706: Determine the type of sensitive content to be detected;
[0112] Step 708: Determine the processing method and the degree of desensitization processing for the desensitization processing;
[0113] Step 710: Detect the sensitive content in the first image according to the type of sensitive content to be detected, and desensitize the sensitive content in the first image according to the determined processing method and degree of desensitization processing to obtain a second image;
[0114] Step 712: Output the second image and output a prompt message, where the prompt message is used to prompt that the first image contains sensitive content and has been desensitized;
[0115] Step 714: Determine whether to continue desensitizing subsequent images; if yes, execute step 702 and step 716; if no, execute step 716;
[0116] Step 716: Perform post-processing on the second image, and the post-processing may include one or more of whether to retain the desensitization effect in the second image, whether to send the second image to the target receiving end, and whether to display the second image.
[0117] It should be noted that Figure 7A This is only a feasible example for convenience of explanation, and should not limit the embodiments of the present application.
[0118] Please refer to Figure 7B , Figure 7B which is a schematic structural diagram of an electronic device disclosed in an embodiment of the present application. Optionally, the electronic device may include a video acquisition module 720, a sensitive information detection and processing module 730, an encoding module 740, an encryption module 750, a decryption module 760, a decoding module 770, and a video rendering module 780, where:
[0119] The video acquisition module 720: is used for acquiring video data of the sender user, including acquiring the video picture of the camera, or the screen sharing picture as video data, and can also be used to provide a custom interface for sensitive content detection parameters;
[0120] The sensitive information detection and processing module 730: is used for determining a sensitive content processing strategy and performing sensitive content detection and desensitization processing on the picture images in the input video data. Among them, the adjustable parameters of the sensitive content processing strategy include whether to enable sensitive content detection, the detection type of sensitive content, the sensitive content processing method, etc.;
[0121] The encoding module 740: is used for encoding the video data for transmission and distribution;
[0122] The encryption module 750: is used for encrypting the video data to achieve end-to-end encryption of the video data;
[0123] The decryption module 760: is used for decrypting the video data to achieve end-to-end decryption of the video data;
[0124] The decoding module 770: is used for decoding the video data for sensitive information detection processing and playing of the data.
[0125] The video rendering module 780: is used for calling the rendering display module of the device to play the video data to complete the playing of the video data, and can also be used to provide processing parameters to the sensitive information detection and processing module at the receiving end.
[0126] Please refer to Figure 8 , Figure 8 which is a schematic structural diagram of a processing device for image data disclosed in an embodiment of the present application. Optionally, the device can be used for the above-mentioned electronic device, or other execution entities, which are not limited herein. Optionally, the device may include an acquisition unit 802, a first determination unit 804, and a first processing unit 806, where:
[0127] The acquisition unit 802 is used for acquiring a first image;
[0128] A first determination unit 804, configured to determine a sensitive content processing policy corresponding to the first image according to the image type of the first image, where the image type includes an image to be sent or a received image;
[0129] A first processing unit 806, configured to desensitize the sensitive content in the first image according to the sensitive content processing policy to obtain a second image.
[0130] Implementing the above device, the image type of the obtained first image may include an image to be sent or a received image. It can be understood that the sensitive content in the image to be sent and the received image may be different for the user. For example, the user may be more sensitive to the privacy content in the image to be sent, while the received image may be more sensitive to the bad content. In this case, when the first image is obtained, the sensitive content processing policy corresponding to the first image can be determined according to the image type of the first image, which improves the intelligence and flexibility of the method; furthermore, the sensitive content in the first image can be desensitized according to the determined sensitive content processing policy to obtain a second image with the sensitive content removed, which improves the desensitization effect, avoids the leakage of the user's privacy, or the psychological impact caused by seeing the bad content, and improves the user experience.
[0131] As an optional implementation manner, the sensitive content processing policy includes a first sensitive content processing policy and a second sensitive content processing policy. The first sensitive content processing policy corresponds to the image to be sent, and the second sensitive content processing policy corresponds to the received image;
[0132] Wherein, the sensitive content for which the first sensitive content processing policy and the second sensitive content processing policy perform desensitization is different, and / or, the processing methods for which the first sensitive content processing policy and the second sensitive content processing policy perform desensitization are different; and / or, the processing degrees for which the first sensitive content processing policy and the second sensitive content processing policy perform desensitization are different.
[0133] Implementing the above device, the electronic device can adopt different sensitive content processing policies according to different image types, which improves the intelligence and flexibility of the method.
[0134] As an optional implementation manner, the situation where the sensitive content for which the first sensitive content processing policy and the second sensitive content processing policy perform desensitization is different includes: the sensitive content for which the first sensitive content processing policy performs desensitization includes at least privacy content, and the sensitive content for which the second sensitive content processing policy performs desensitization includes at least bad content.
[0135] By implementing the above-mentioned device, according to the image type corresponding to the first image, a targeted sensitive content processing strategy can be adopted to perform targeted desensitization processing on the more sensitive content in the first image, thereby avoiding the leakage of user privacy or the psychological impact caused by seeing inappropriate content, and improving the user experience.
[0136] As an alternative implementation, Figure 8 The device shown may further include a second determination unit (not shown), where:
[0137] The second determination unit is used to determine processing parameters before determining the sensitive content processing strategy corresponding to the first image according to the image type corresponding to the first image. The processing parameters include one or more desensitization processing methods and the processing degrees corresponding to one or more desensitization processing methods;
[0138] In addition, the first determination unit 804 is further used to determine the sensitive content processing strategy according to the image type corresponding to the first image and the processing parameters.
[0139] By implementing the above-mentioned device, the electronic device can determine the custom parameters as the processing parameters when detecting the input custom parameters; and when the input custom parameters are not detected, the initial parameters stored in the electronic device can be determined as the processing parameters, improving the intelligence and flexibility of the method.
[0140] As an alternative implementation, the first processing unit 806 is further used to perform image recognition on the first image according to the sensitive content processing strategy to determine whether the first image includes sensitive content; and if the first image includes sensitive content, desensitize the sensitive content in the first image.
[0141] By implementing the above-mentioned device, the electronic device can first determine whether the first image includes sensitive content. If it includes sensitive content, desensitization processing is performed; if it does not include sensitive content, desensitization processing is not performed, thereby reducing the computing amount of the electronic device, reducing power consumption; and in addition, accelerating the processing efficiency of the first image.
[0142] As an alternative implementation, the types of sensitive content to be detected included in the sensitive content processing strategy include user-defined sensitive content types; and the first processing unit 806 is further used to perform image recognition on the first image according to the sensitive content processing strategy to determine whether the first image includes sensitive content corresponding to the types of sensitive content to be detected.
[0143] By implementing the above-mentioned device, the user can customize the types of sensitive content to be detected, improving the controllability and customizability of the method, and thereby improving the user experience.
[0144] As an alternative implementation, Figure 8 the illustrated device may further include a sending unit (not shown), where:
[0145] The sending unit is configured to, after performing image recognition on the first image according to the sensitive content processing policy to determine whether the first image includes sensitive content, if it is determined that the first image includes sensitive content and the electronic device has the permission to send the sensitive content to the police terminal, send the sensitive content to the police terminal.
[0146] Implementing the above device, the electronic device can, with the user's consent, feedback the detected sensitive content to the police as evidence for handling cases.
[0147] As an alternative implementation, Figure 8 the illustrated device may further include an output unit and a second processing unit (not shown), where:
[0148] The output unit is configured to, after performing desensitization processing on the sensitive content in the first image according to the sensitive information processing scheme to obtain second image data, output a prompt message, where the prompt message is used to prompt that the first image contains sensitive content and desensitization processing has been performed, and provide at least one post-processing method;
[0149] The second processing unit is configured to, when a selected post-processing method is detected, process the second image data according to the selected post-processing method.
[0150] Implementing the above device, the electronic device can process the sensitive content while popping up a prompt message, allowing the user to choose whether to continue desensitizing the sensitive content, giving the user the right to make an independent choice, and at the same time avoiding the leakage of the user's privacy. In addition, the pop-up message can temporarily block the second image, thereby avoiding the user being impacted by the sensitive content in the second image immediately.
[0151] As an alternative implementation, the post-processing method includes one or more of whether to retain the desensitization processing effect in the second image, whether to send the second image to the target recipient, and whether to display the second image.
[0152] Implementing the above device, the electronic device can allow the user to choose whether to continue desensitizing the sensitive content, whether to send the processed second image, or whether to display the processed second image, giving the user the right to make an independent choice, and at the same time avoiding the leakage of the user's privacy and also avoiding the user being impacted by the sensitive content in the second image immediately.
[0153] Please refer to Figure 9 , Figure 9It is a schematic structural diagram of another electronic device disclosed in an embodiment of the present application. As Figure 9 shown, the electronic device may include:
[0154] A memory 901 storing executable program code;
[0155] A processor 902 coupled to the memory 901;
[0156] Wherein, the processor 902 calls the executable program code stored in the memory 901 and executes the processing method of the image data disclosed in the above embodiments.
[0157] An embodiment of the present application discloses a computer-readable storage medium, which stores a computer program, wherein the computer program enables a computer to execute the processing method of the image data disclosed in the above embodiments.
[0158] An embodiment of the present application also discloses an application publishing platform, wherein the application publishing platform is used to publish a computer program product, and when the computer program product runs on a computer, it enables the computer to execute some or all of the steps of the methods in the above method embodiments.
[0159] It should be understood that the "one embodiment" or "an embodiment" mentioned throughout the specification means that the specific features, structures or characteristics related to the embodiment are included in at least one embodiment of the present application. Therefore, the "in one embodiment" or "in an embodiment" that appears throughout the specification does not necessarily refer to the same embodiment. In addition, these specific features, structures or characteristics can be combined in one or more embodiments in any suitable manner. Those skilled in the art should also know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily essential to the present application.
[0160] In various embodiments of the present application, it should be understood that the size of the serial numbers of the above processes does not necessarily mean the inevitable sequence of execution. The execution sequence of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present application.
[0161] The units described as separate components above may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place, or may be distributed to multiple network units. Some or all of the units can be selected according to actual needs to achieve the purpose of the solution of this embodiment.
[0162] In addition, in each embodiment of the present application, each functional unit can be integrated into a processing unit, or each unit can exist physically alone, or two or more units can be integrated into one unit. The above-mentioned integrated unit can be implemented in the form of hardware or in the form of a software functional unit.
[0163] When the above-mentioned 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-accessible memory. Based on this understanding, the technical solution of the present application, in essence, or the part that contributes to the prior art, or all or part of this technical solution, can be embodied in the form of a software product. This computer software product is stored in a memory and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc., specifically, the processor in the computer device) to execute some or all of the steps of the above-mentioned methods in each embodiment of the present application.
[0164] Those of ordinary skill in the art can understand that all or part of the steps in the various methods of the above embodiments can be completed by instructing relevant hardware through a program. This program can be stored in a computer-readable storage medium. The storage medium includes a read-only memory (ROM), a random access memory (RAM), a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), a one-time programmable read-only memory (OTPROM), an electrically-erasable programmable read-only memory (EEPROM), a compact disc read-only memory (CD-ROM), or other optical disc memories, magnetic disk memories, tape memories, or any other computer-readable medium that can be used to carry or store data.
[0165] The above has introduced in detail the method and apparatus for processing image data, electronic device, and storage medium disclosed in the embodiments of the present application. Specific examples are used herein to elaborate on the principle and implementation manner of the present application. The description of the above embodiments is only used to help understand the method and its core idea of the present application; at the same time, for those of ordinary skill in the art, according to the idea of the present application, there will be changes in the specific implementation manner and application scope. In summary, the content of this specification should not be construed as a limitation to the present application.
Claims
1. A method for processing image data, characterized in that The method includes: Obtaining a first image; Determining a sensitive content processing strategy corresponding to the first image according to the image type corresponding to the first image, where the image type includes an image to be sent or a received image; Performing desensitization processing on the sensitive content in the first image according to the sensitive content processing strategy to obtain a second image.
2. The method according to claim 1, wherein The sensitive content processing strategy includes a first sensitive content processing strategy and a second sensitive content processing strategy. The first sensitive content processing strategy corresponds to the image to be sent, and the second sensitive content processing strategy corresponds to the received image; Wherein, the sensitive content for which the first sensitive content processing strategy and the second sensitive content processing strategy perform desensitization processing is different, and / or The processing methods for desensitization processing performed by the first sensitive content processing strategy and the second sensitive content processing strategy are different; and / or The degrees of desensitization processing performed by the first sensitive content processing strategy and the second sensitive content processing strategy are different.
3. The method according to claim 2, wherein The situation where the sensitive content for which the first sensitive content processing strategy and the second sensitive content processing strategy perform desensitization processing is different includes: the sensitive content for which the first sensitive content processing strategy performs desensitization processing includes at least privacy content, and the sensitive content for which the second sensitive content processing strategy performs desensitization processing includes at least inappropriate content.
4. The method according to claim 1, wherein Before determining the sensitive content processing strategy corresponding to the first image according to the image type corresponding to the first image, the method further includes: Obtaining set processing parameters, where the processing parameters include one or more desensitization processing methods and the degrees of processing corresponding to the one or more desensitization processing methods; And, determining the sensitive content processing strategy corresponding to the first image according to the image type corresponding to the first image includes: Determining the sensitive content processing strategy according to the image type corresponding to the first image and the processing parameters.
5. The method according to claim 1, wherein Performing desensitization processing on the sensitive content in the first image according to the sensitive content processing strategy to obtain a second image includes: Performing image recognition on the first image according to the sensitive content processing strategy to determine whether the first image includes sensitive content; If the first image includes sensitive content, desensitize the sensitive content in the first image.
6. The method according to claim 5, characterized in that The types of sensitive content to be detected corresponding to the sensitive content processing strategy include: user-defined sensitive content types, and / or sensitive content types set in the sensitive content processing strategy.
7. The method according to claim 5 or 6, characterized in that, After performing image recognition on the first image according to the sensitive content processing strategy to determine whether the first image includes sensitive content, the method further includes: If the first image includes sensitive content and the electronic device has the permission to send the sensitive content to the police terminal, send the sensitive content to the police terminal.
8. The method according to claim 1, wherein After performing desensitization processing on the sensitive content in the first image according to the sensitive content processing strategy to obtain a second image, the method further includes: Output a prompt message, which is used to prompt that the first image contains sensitive content and has been desensitized, and provide at least one post-processing method; If a selected post-processing method is detected, the second image is processed according to the selected post-processing method.
9. The method according to claim 8, wherein The post-processing methods include whether to retain the desensitization effect in the second image, whether to send the second image to a target recipient, and whether to display one or more of the second image.
10. An image data processing apparatus, characterized in that, The device includes: An acquisition unit, configured to acquire a first image; A first determination unit, configured to determine a sensitive content processing strategy corresponding to the first image according to the image type corresponding to the first image, where the image type includes an image to be sent or a received image; A first processing unit, configured to desensitize the sensitive content in the first image according to the sensitive content processing strategy to obtain a second image.
11. An electronic device, characterized in that, It includes a memory storing executable program code, and a processor coupled to the memory; wherein, the processor calls the executable program code stored in the memory to execute the method according to any one of claims 1 to 9.
12. A computer-readable storage medium stores a computer program, characterized in that, When the computer program is executed by a processor, the method according to any one of claims 1 to 9 is implemented.