Image processing method and device, storage medium and electronic equipment

Abstract

The application discloses an image processing method, device, storage medium and electronic equipment. The image processing method is applied to the electronic equipment, and the image processing method comprises the following steps: acquiring an image; determining the correlation degree of the image and a preset object; if the correlation degree of the image and the preset object is less than or equal to a preset correlation degree threshold value, and the storage time of the image on the electronic equipment is greater than a preset time threshold value, the image is processed according to a preset deletion procedure. The application can improve the efficiency of deleting images with a small correlation degree or no correlation.

Description

Technical Field

[0001] This application relates to the field of electronic equipment technology, specifically to an image processing method, apparatus, storage medium, and electronic equipment. Background Technology

[0002] Currently, electronic devices such as smartphones use various social media applications. When viewing images, most of these applications require users to download the images to their devices. These images are then stored long-term in the device's storage space. When users need to delete less relevant or irrelevant images from this storage space, they must manually delete each image individually, which is time-consuming and inefficient. Summary of the Invention

[0003] In view of this, this application provides an image processing method, apparatus, storage medium, and electronic device to improve the low efficiency of manually deleting images with low relevance or irrelevantness in existing solutions.

[0004] In a first aspect, embodiments of this application provide an image processing method applied to an electronic device, the image processing method comprising:

[0005] Acquire images;

[0006] Determine the correlation between the image and the preset object;

[0007] If the correlation between the image and the preset object is less than or equal to a preset correlation threshold, and the storage time of the image on the electronic device is greater than a preset time threshold, then the image is processed according to a preset deletion procedure.

[0008] Optionally, acquiring the image includes:

[0009] Download images from social media applications in the electronic device.

[0010] Optionally, determining the relevance of the image includes:

[0011] Extract preset feature parameters from the image;

[0012] The correlation between the image and the preset object is determined based on the preset feature parameters.

[0013] Optionally, the preset feature parameters include at least one of the following:

[0014] The target objects are images, scenes, and text.

[0015] Optionally, extracting preset feature parameters from the image includes:

[0016] Extract the target object image, scene, and text from the image;

[0017] Determining the correlation between the image and the preset object based on the preset feature parameters includes:

[0018] Determine the correlation between the target object image and the preset object, the correlation between the scene and the preset object, and the correlation between the text and the preset object;

[0019] The relevance between the image and the preset object is determined based on the relevance between the target object image and the preset object and the corresponding weight coefficient, the relevance between the scene and the preset object and the corresponding weight coefficient, and the relevance between the text and the preset object and the corresponding weight coefficient.

[0020] Optionally, determining the relevance between the target object image and the preset object, the relevance between the scene and the preset object, and the relevance between the text and the preset object includes:

[0021] The relevance between the target object image and the preset object is determined based on whether the target object image is a known object image.

[0022] The relevance of the scenario to the preset object is determined based on the type of the scenario;

[0023] The relevance of the text to the preset object is determined based on the content after decoding the text.

[0024] Optionally, the target object image includes a face image or an object image.

[0025] Optionally, the preset deletion procedure includes automatic deletion or isolation. If the relevance of the image to a preset object is less than or equal to a preset relevance threshold, and the storage time of the image on the electronic device is greater than a preset time threshold, then the image is processed according to the preset deletion procedure, including:

[0026] If the relevance of the image to the preset object is less than or equal to a preset relevance threshold, and the storage time of the image on the electronic device is greater than a preset time threshold, then the image will be automatically deleted or isolated.

[0027] Secondly, embodiments of this application provide an image processing apparatus applied to an electronic device, the image processing apparatus comprising:

[0028] The acquisition module is used to acquire images;

[0029] The determination module is used to determine the correlation between the image and the preset object;

[0030] The processing module is configured to process the image according to a preset deletion procedure if the correlation between the image and a preset object is less than or equal to a preset correlation threshold, and the storage time of the image on the electronic device is greater than a preset time threshold.

[0031] Thirdly, embodiments of this application provide a computer-readable storage medium storing a computer program thereon, which, when executed on a computer, causes the computer to execute the process in the image processing method provided in embodiments of this application.

[0032] Fourthly, embodiments of this application also provide an electronic device, including a memory and a processor, wherein the processor executes the process in the image processing method provided in embodiments of this application by calling a computer program stored in the memory.

[0033] In the image processing method, apparatus, storage medium, and electronic device of this application embodiment, the electronic device can acquire downloaded images; determine the relevance of the image to a preset object; if the relevance of the image to the preset object is less than or equal to a preset relevance threshold, and the storage time of the image on the electronic device is greater than a preset time threshold, i.e., the image has low or no relevance to the preset object, and the storage time of the image on the electronic device has exceeded the preset time threshold, then the image is processed according to a preset deletion procedure, i.e., the electronic device automatically deletes images with low or no relevance, without requiring manual deletion. Therefore, the embodiments of this application can improve the efficiency of deleting images with low or no relevance. Attached Figure Description

[0034] The technical solution and its beneficial effects will become apparent from the following detailed description of specific embodiments of this application, in conjunction with the accompanying drawings.

[0035] Figure 1 This is a schematic flowchart of the image processing method provided in the embodiments of this application;

[0036] Figure 2 This is another schematic flowchart of the image processing method provided in the embodiments of this application;

[0037] Figure 3 This is a flowchart illustrating the image processing method provided in this application embodiment in one scenario;

[0038] Figure 4 yes Figure 3 Visual interface diagrams for corresponding scenarios;

[0039] Figure 5 This is a schematic diagram of the structure of the image processing apparatus provided in the embodiments of this application;

[0040] Figure 6 This is a schematic diagram of the structure of the electronic device provided in the embodiments of this application;

[0041] Figure 7 This is another structural schematic diagram of the electronic device provided in the embodiments of this application. Detailed Implementation

[0042] Please refer to the illustrations, where the same component symbols represent the same components. The principles of this application are illustrated by example in a suitable computing environment. The following description is based on the specific embodiments of this application illustrated, and should not be construed as limiting other specific embodiments not detailed herein.

[0043] It is understood that the execution subject of the embodiments of this application can be an electronic device. In actual scenarios, the specific form of the electronic device is not limited in the embodiments of this application, such as including but not limited to: mobile phones, tablets, laptops, PDAs, personal digital assistants (PDAs), portable media players (PMPs) and other handheld terminals; vehicle navigation devices; wearable devices and other mobile terminals with corresponding functions.

[0044] Please see Figure 1 , Figure 1 This is a schematic flowchart of an image processing method provided in an embodiment of this application. This image processing method can be applied to electronic devices. The process of this image processing method may include:

[0045] 101. Obtain the image.

[0046] Currently, electronic devices such as smartphones use various social media applications. When viewing images, most of these applications require users to download the images to their devices. These images are then stored long-term in the device's storage space. For users, some of these images may be highly relevant, while others may be less relevant or irrelevant. When users need to delete less relevant or irrelevant images from storage, they must manually delete each image individually, which is time-consuming and inefficient.

[0047] In related technologies, the following method is used to determine whether images in storage are user-relevant: First, images are grouped based on facial information present in them; then, they are sorted according to the number of faces appearing in each image, for example, sorting the images in descending order of the number of faces appearing, or in ascending order of the number of faces appearing. Since the sorting is based solely on the number of faces appearing in the images, rather than on the number of user-relevant faces, this may result in all images containing faces potentially having low or no relevance to the user.

[0048] This method of sorting images by the number of faces in them suffers from low accuracy in determining whether an image in storage is relevant to the user because it doesn't consider whether those faces are related to the user. Furthermore, sorting images by the number of faces relies solely on screenshots from three different documents, which can easily lead to errors in the detected number of faces.

[0049] In this embodiment, the electronic device can acquire images. For example, the electronic device can acquire a currently downloaded image, which can be downloaded directly from a server or downloaded from a server via an application. It is understood that when downloaded via an application, the application can be an application installed on the electronic device, a public account, or an application installed on a third-party device, etc.

[0050] It should be noted that the application can be a social media application, through which social functions can be implemented.

[0051] 102. Determine the correlation between the image and the preset object.

[0052] In this embodiment, after the electronic device acquires the downloaded image, it can determine the relevance of the image to a preset object. The preset object can be a user or an object, such as an animal. This embodiment uses a user as the preset object for illustration.

[0053] For example, when determining the relevance of an image to a user, the relevance of downloaded images to the user can be analyzed using predefined Relevant Features (RF). These predefined relevance features can include various user-related feature parameters. For instance, a relevance feature could be a face or person appearing in a person's gallery, indicating that images containing that face or person are closely related to the user, meaning the image is highly relevant and should not be deleted. Various methods can be used to calculate the relevance of an image to a user.

[0054] For example, in one implementation, a relevance score can be used to determine the relevance of an image to a user. For instance, an appropriate relevance score (RS) can be assigned to the image, representing its relevance to the user. This score is not based on a single feature parameter, but rather on various feature parameters universally stored in the image. Understandably, a higher relevance score indicates a greater relevance between the image and the user. For example, a relevance score greater than 70 indicates a high relevance between the image and the user, and the image is considered relevant. Conversely, a relevance score less than or equal to 70 indicates a low or no relevance, and the image is considered irrelevant.

[0055] For example, in one implementation, the relevance of an image to a user can be determined using a relevance percentage. For instance, an appropriate relevance percentage can be assigned to the image, representing its relevance to the user. This relevance percentage is not based on a single feature parameter, but rather on various feature parameters universally stored in the image. Understandably, a higher relevance percentage indicates a greater relevance between the image and the user. For example, a relevance percentage greater than 70% can be set to indicate a high relevance between the image and the user, thus determining that the image is relevant to the user. Conversely, a relevance percentage less than or equal to 70% can indicate a low or no relevance between the image and the user, thus determining that the image is irrelevant to the user.

[0056] For example, in one implementation, the relevance of an image can be determined using a relevance level. For instance, an appropriate relevance level can be assigned to the image, representing its relevance to the user. This relevance level is not based on a single feature parameter, but rather on various feature parameters commonly stored in the image. For example, relevance levels can be categorized as excellent, good, average, and poor. An excellent or good relevance level indicates a high relevance between the image and the user, thus determining that the image is relevant to the user. Conversely, an average or poor relevance level indicates a low or no relevance between the image and the user, thus determining that the image is irrelevant to the user.

[0057] 103. If the relevance of an image is less than or equal to a preset relevance threshold, and the image has been stored on an electronic device for a longer period than a preset time threshold, then the image will be processed according to a preset deletion procedure.

[0058] In this embodiment, a preset relevance threshold and a preset time threshold can be preset. The preset relevance threshold can be the minimum relevance score (MRS), and the preset time threshold can be the threshold duration (TD). If the relevance of an image is less than or equal to the preset relevance threshold, it indicates that the image has low relevance to the user, and the image can be deleted. If the image has been stored on the electronic device for a longer period than the preset time threshold, the image is processed according to a preset deletion procedure, such as deleting the image to free up storage space on the electronic device.

[0059] It is understood that in this embodiment, the electronic device can acquire downloaded images; determine the relevance of the image to a preset object (e.g., a user); if the relevance of the image to the preset object is less than or equal to a preset relevance threshold, and the storage time of the image on the electronic device is greater than a preset time threshold, i.e., the image has low or no relevance to the preset object, and the storage time of the image on the electronic device has exceeded the preset time threshold, then the image is processed according to a preset deletion procedure. That is, the electronic device will automatically delete images with low or no relevance without manual deletion. Therefore, this embodiment can improve the efficiency of deleting images with low or no relevance.

[0060] Please see Figure 2 , Figure 2 This is another schematic flowchart of the image processing method provided in an embodiment of this application. This image processing method is applied to an electronic device. Figure 2 In this process, the image processing method may include the following steps:

[0061] 201. Download images from social media applications on electronic devices.

[0062] For example, in this embodiment of the application, the electronic device is equipped with social media application software, such as social media applications. Images can be downloaded from the social media application software to the electronic device, and then the downloaded images are stored in the storage space of the electronic device, so that the user can view the images.

[0063] 202. Extract preset feature parameters from the image.

[0064] For example, in this embodiment, preset feature parameters can be set in advance. For a specific image, the preset feature parameters can be extracted from the image, and then the relevance of the image to the user can be determined based on the preset feature parameters. The relevance of an image to a user is a combination of various factors, which can be used to determine whether an image is relevant or irrelevant to the user.

[0065] In one implementation, the preset feature parameters include at least one of the following: a target object image, a scene, and text. That is, the preset feature parameters may include a target object image, or they may include a target object image and a scene, or they may include a scene and text, or they may include a target object image, a scene, and text. It is understood that the relevance of the image to the user depends on the preset feature parameters. When the preset feature parameters include a target object image, a scene, and text, the calculated relevance between the image and the user is more accurate.

[0066] In one implementation, extracting preset feature parameters from the image in step 202 may include:

[0067] Extract the target object image, scene, and text from the image.

[0068] For example, once an electronic device acquires a downloaded image, it can extract the target object image, scene, and text from that image. The target object image is the part the user is interested in; it can include images of faces or objects, such as animal images or sculptures.

[0069] When the target image is a face image, for images downloaded by an electronic device, a face recognition (FR) algorithm based on deep learning (DL) can be used to detect or recognize faces from the images on the electronic device. The FR algorithm repeatedly captures new images taken by the user using a mobile camera, creating multiple known faces for the user. New faces identified by the FR algorithm are stored for further examination. Each face is unique, facilitating the identification of whether a face in a newly acquired image is a known face.

[0070] Understandably, when the target image is an object image, for images downloaded by electronic devices, object images can be detected or identified within the images. New images captured by the user clicking with the mobile camera are repeatedly taken to create multiple images of known objects for the user. The images of the newly identified objects are stored for further examination. Each object is unique, facilitating the identification of whether an object in a newly acquired image is a known object.

[0071] 203. Determine the correlation between the image and the preset object based on the preset feature parameters.

[0072] For example, in one implementation, after extracting preset feature parameters from an image, the correlation between the image and a preset object can be determined based on the preset feature parameters.

[0073] In one embodiment, when determining the correlation between an image and a preset object based on preset feature parameters, step 203 may include:

[0074] Determine the correlation between the target object image and the preset object, the correlation between the scene and the preset object, and the correlation between the text and the preset object;

[0075] The relevance between the image and the preset object is determined based on the relevance between the target object image and the preset object and the corresponding weight coefficient, the relevance between the scene and the preset object and the corresponding weight coefficient, and the relevance between the text and the preset object and the corresponding weight coefficient.

[0076] In one implementation, determining the relevance between the target object image and the preset object, the relevance between the scene and the preset object, and the relevance between the text and the preset object may include:

[0077] The relevance between the target object image and the preset object is determined based on whether the target object image is a known object image.

[0078] The relevance of the scenario to the preset object is determined based on the type of the scenario;

[0079] The relevance of the text to the preset object is determined based on the content after decoding the text.

[0080] For example, preset feature parameters can include target object images, scenes, and text. After extracting the target object image, scene, and text from the image, the relevance of the target object image to a preset object (e.g., a user), the relevance of the scene to the preset object, and the relevance of the text to the preset object can be determined separately. For instance, by determining whether the target object image is a known object image (an image of a known face or a known object), it can be determined whether the target object image is related to the preset object. If the target object image is a known object image, then the target object image is an image with a high degree of relevance to the preset object, and the magnitude of the relevance between the target object image and the preset object can be determined.

[0081] For example, the relevance between a scene and a preset object can be determined by identifying the type of scene in the image. For instance, a scene could be a party, a seaside landscape, a park landscape, a pastoral landscape, or other beautiful scenery.

[0082] For example, the relevance of text to a preset object can be determined by identifying the presence of text in an image and the content of the decoded text. Text decoding can be performed using a text detector and Natural Language Processing (NLP). The task of NLP is to calculate the importance of the text, because the decoded content may contain important information, such as "Good morning," "Meeting," "Party," "Coffee Shop," or other related information.

[0083] It should be noted that, in this application embodiment, corresponding weight coefficients are assigned to the relevance between the target object image and the preset object, the relevance between the scene and the preset object, and the relevance between the text and the preset object. The sum of the weight coefficients for the target object image, the scene, and the text is 1. For example, in one embodiment, the weight coefficient for the target object image is assigned 0.7, the weight coefficient for the scene is assigned 0.2, and the weight coefficient for the text is assigned 0.1. In another embodiment, the weight coefficient for the target object image is assigned 0.8, the weight coefficient for the scene is assigned 0.1, and the weight coefficient for the text is assigned 0.1, and so on. In practical applications, the weight coefficients for the target object image, the scene, and the text can be assigned according to specific needs, but the sum of these weight coefficients must be 1. This application embodiment does not impose any particular limitation on the magnitude of the weight coefficients for the target object image, the scene, and the text.

[0084] Understandably, the relevance between an image and a preset object can be determined based on the relevance and corresponding weight coefficients between the target image and the preset object, the relevance and corresponding weight coefficients between the scene and the preset object, and the relevance and corresponding weight coefficients between the text and the preset object. For example, the relevance between an image and a preset object can be calculated as follows: multiply the relevance and corresponding weight coefficients of the target image and the preset object to obtain the first product; multiply the relevance and corresponding weight coefficients of the scene and the preset object to obtain the second product; multiply the relevance and corresponding weight coefficients of the text and the preset object to obtain the third product; and sum the first, second, and third products to obtain the relevance between the image and the preset object. This calculation method can be used whenever a user downloads any image from social media applications.

[0085] It should be noted that the relevance between the image and the preset object can be represented in various ways, such as by relevance score, relevance percentage, or relevance level. For specific implementation, please refer to the embodiment of step 102, which will not be repeated here.

[0086] 204. If the correlation between the image and the preset object is less than or equal to the preset correlation threshold, and the image is stored on the electronic device for a longer time than the preset time threshold, the image will be automatically deleted or isolated.

[0087] For example, a preset deletion procedure may include automatic deletion or isolation. After determining the relevance of an image to a preset object, if the relevance is less than or equal to a preset relevance threshold (which could be a minimum relevance score), it means the image has little or no relevance to the preset object. Additionally, if the image's storage time (Time Present, TP) on the electronic device exceeds a preset time threshold, the image will be automatically deleted or isolated. In other words, after a predefined time period, such as after a preset time threshold, images with little or no relevance to the preset object can be automatically deleted or isolated for user approval, or the user can be prompted to check images whose relevance is less than or equal to the preset relevance threshold.

[0088] It is understood that in this embodiment, images with low or no relevance are automatically deleted, eliminating the need for manual image browsing and deletion. This improves user experience and effectively utilizes the storage space of electronic devices. Furthermore, related technologies employ unrelated methods when separating image data, leading to significant separation errors. This embodiment uses an enhanced and better method to calculate the relevance of each image to a preset object; that is, it uses a relevance-based method when separating image data. This makes filtering images with low or no relevance to the preset object more reliable and accurate. This embodiment improves the robustness and accuracy of image relevance (e.g., relevance score).

[0089] Please see Figure 3 , Figure 3 This is a flowchart illustrating the image processing method provided in this application embodiment in one scenario. For example, in this scenario, the target object image is a face image. After downloading the image from a social media application, the image is stored in the storage space of the electronic device, and a neural network algorithm is used to extract the face image, scenery, and text from the image. Please refer to... Figure 4 , Figure 4 yes Figure 3 A visual interface diagram for the corresponding scenario. Figure 4 In the image, facial images, scenery, and text can be extracted. The scenery is the sun, and the text is "Good morning".

[0090] After extracting the face image, scenery, and text, a relevance score between the image and the user can be calculated based on these elements. Then, it is determined whether this relevance score is greater than the minimum relevance score. If the score is greater, the image is considered highly relevant to the user, and no action is taken. If the score is less than or equal to the minimum relevance score, the image is considered less relevant or irrelevant to the user.

[0091] When an image has little or no relevance to the user, the system checks if the image's storage time on the electronic device exceeds a preset time threshold. If the storage time exceeds the threshold, the image is deleted to free up storage space. If the storage time is less than or equal to the threshold, the image is deleted after a predetermined period to free up storage space. Since all methods operate on the electronic device and no data is transferred externally, user privacy is not affected.

[0092] Please see Figure 5 , Figure 5 This is a schematic diagram of the structure of an image processing apparatus provided in an embodiment of this application. The image processing apparatus can be applied to electronic devices. The image processing apparatus 300 may include: an acquisition module 301, a first determination module 302, and a second determination module 303.

[0093] The acquisition module 301 is used to acquire images;

[0094] The determining module 302 is used to determine the correlation between the image and the preset object;

[0095] The processing module 303 is used to process the image according to a preset deletion procedure if the correlation between the image and the preset object is less than or equal to a preset correlation threshold, and the storage time of the image on the electronic device is greater than a preset time threshold.

[0096] In one embodiment, the acquisition module 301 can be used to download images from social application software in the electronic device.

[0097] In one embodiment, the determining module 302 can be used to: extract preset feature parameters from the image; and determine the correlation between the image and a preset object based on the preset feature parameters.

[0098] In one implementation, the preset feature parameters include at least one of the following: target object image, scene, and text.

[0099] In one implementation, the determining module 302 can be used to extract target object images, scenes, and text from the image.

[0100] In one embodiment, the determining module 302 can be used to: determine the correlation between the target object image and a preset object, the correlation between the scene and the preset object, and the correlation between the text and the preset object; and determine the correlation between the image and the preset object based on the correlation between the target object image and the preset object and the corresponding weight coefficient, the correlation between the scene and the preset object and the corresponding weight coefficient, and the correlation between the text and the preset object and the corresponding weight coefficient.

[0101] In one embodiment, the determining module 302 can be used to: determine the relevance between the target object image and a preset object based on whether the target object image is a known object image; determine the relevance between the scene and the preset object based on the type of the scene; and determine the relevance between the text and the preset object based on the content after decoding the text.

[0102] In one implementation, the target object image includes a face image or an object image.

[0103] In one embodiment, the preset deletion procedure includes automatic deletion or isolation, and the processing module 303 can be used to: automatically delete or isolate the image if the correlation between the image and the preset object is less than or equal to a preset correlation threshold, and the storage time of the image on the electronic device is greater than a preset time threshold.

[0104] This application provides a computer-readable storage medium storing a computer program thereon, which, when executed on a computer, causes the computer to perform the process in the image processing method provided in this embodiment.

[0105] This application also provides an electronic device, including a memory and a processor, wherein the processor executes the process in the image processing method provided in this embodiment by calling a computer program stored in the memory.

[0106] For example, the aforementioned electronic devices can be handheld terminals such as mobile phones, tablets, laptops, PDAs, personal digital assistants, and portable media players; in-vehicle navigation devices; and wearable devices, etc., which are mobile terminals with corresponding functions. Please refer to [link / reference]. Figure 6 , Figure 6 This is a schematic diagram of the structure of an electronic device provided in an embodiment of this application.

[0107] The electronic device 400 may include components such as a memory 401 and a processor 402. Those skilled in the art will understand that... Figure 6The electronic device structure shown does not constitute a limitation on the electronic device and may include more or fewer components than shown, or combine certain components, or have different component arrangements.

[0108] Memory 401 can be used to store applications and data. The applications stored in memory 401 contain executable code. Applications can be composed of various functional modules. Processor 402 executes various functional applications and data processing by running the applications stored in memory 401.

[0109] The processor 402 is the control center of the electronic device. It connects various parts of the electronic device through various interfaces and lines. By running or executing the application program stored in the memory 401 and calling the data stored in the memory 401, it performs various functions of the electronic device and processes data, thereby monitoring the electronic device as a whole.

[0110] In this embodiment, the processor 402 in the electronic device loads the executable code corresponding to the processes of one or more applications into the memory 401 according to the following instructions, and the processor 402 runs the applications stored in the memory 401 to execute:

[0111] Acquire images;

[0112] Determine the correlation between the image and the preset object;

[0113] If the correlation between the image and the preset object is less than or equal to a preset correlation threshold, and the storage time of the image on the electronic device is greater than a preset time threshold, then the image is processed according to a preset deletion procedure.

[0114] Please see Figure 7 , Figure 7 This is another structural schematic diagram of the electronic device provided in the embodiments of this application. The electronic device 400 may include components such as a memory 401, a processor 402, an input unit 403, an output unit 404, and a speaker 405.

[0115] Memory 401 can be used to store applications and data. The applications stored in memory 401 contain executable code. Applications can be composed of various functional modules. Processor 402 executes various functional applications and data processing by running the applications stored in memory 401.

[0116] The processor 402 is the control center of the electronic device. It connects various parts of the electronic device through various interfaces and lines. By running or executing the application program stored in the memory 401 and calling the data stored in the memory 401, it performs various functions of the electronic device and processes data, thereby monitoring the electronic device as a whole.

[0117] The input unit 403 can be used to receive input numbers, characters, or user characteristic information (such as fingerprints), and to generate keyboard, mouse, joystick, optical, or trackball signal inputs related to user settings and function control.

[0118] The output unit 404 can be used to display information input by the user or information provided to the user, as well as various graphical user interfaces of electronic devices. These graphical user interfaces can be composed of graphics, text, icons, video, and any combination thereof. The output unit may include a display panel.

[0119] Speaker 405 can be used to play sound signals.

[0120] In addition, electronic devices may include components such as batteries and microphones. Batteries supply power to the various modules of the electronic device, while microphones are used to pick up sound signals from the surrounding environment.

[0121] In this embodiment, the processor 402 in the electronic device loads the executable code corresponding to the processes of one or more applications into the memory 401 according to the following instructions, and the processor 402 runs the applications stored in the memory 401 to execute:

[0122] Acquire images;

[0123] Determine the correlation between the image and the preset object;

[0124] If the correlation between the image and the preset object is less than or equal to a preset correlation threshold, and the storage time of the image on the electronic device is greater than a preset time threshold, then the image is processed according to a preset deletion procedure.

[0125] In one embodiment, when performing the image acquisition, the processor 402 may also perform: downloading images from social application software in the electronic device.

[0126] In one embodiment, when the processor 402 performs the step of determining the correlation between the image and a preset object, it may also perform the following: extracting preset feature parameters from the image; and determining the correlation between the image and the preset object based on the preset feature parameters.

[0127] In one implementation, the preset feature parameters include at least one of the following: target object image, scene, and text.

[0128] In one embodiment, when the processor 402 performs the extraction of preset feature parameters from the image, it may also perform the extraction of target object images, scenes, and text from the image.

[0129] In one embodiment, when the processor 402 executes the step of determining the relevance between the image and the preset object based on the preset feature parameters, it may also execute: determining the relevance between the target object image and the preset object, the relevance between the scene and the preset object, and the relevance between the text and the preset object; determining the relevance between the image and the preset object based on the relevance between the target object image and the preset object and the corresponding weight coefficient, the relevance between the scene and the preset object and the corresponding weight coefficient, and the relevance between the text and the preset object and the corresponding weight coefficient.

[0130] In one embodiment, when the processor 402 performs the steps of determining the relevance between the target object image and the preset object, the relevance between the scene and the preset object, and the relevance between the text and the preset object, it may also perform the following: determining the relevance between the target object image and the preset object based on whether the target object image is a known object image; determining the relevance between the scene and the preset object based on the type of the scene; and determining the relevance between the text and the preset object based on the content after decoding the text.

[0131] In one implementation, the target object image includes a face image or an object image.

[0132] In one embodiment, when the processor 402 executes the preset deletion procedure, which includes automatic deletion or isolation, and the step of processing the image according to the preset deletion procedure if the correlation between the image and the preset object is less than or equal to a preset correlation threshold and the storage time of the image on the electronic device is greater than a preset time threshold, the processor 402 may further execute: if the correlation between the image and the preset object is less than or equal to a preset correlation threshold and the storage time of the image on the electronic device is greater than a preset time threshold, the processor 402 may automatically delete or isolate the image.

[0133] The embodiments of the electronic device and readable storage medium provided in this application include all the technical features of the embodiments of the above-described methods. The extended and explanatory content of the specification is the same as that of the embodiments of the above-described positioning methods, and will not be repeated here.

[0134] This application also provides a computer program product, which includes computer program code that, when run on a computer, causes the computer to perform the methods described in the various possible embodiments described above.

[0135] This application also provides a chip including a memory and a processor. The memory is used to store a program, and the processor is used to call and run the program from the memory, causing a device with the chip installed to perform the methods described in the various possible embodiments above.

[0136] In the above embodiments, the descriptions of each embodiment have different focuses. For parts not described in detail in a certain embodiment, please refer to the detailed description of the image processing method above, which will not be repeated here.

[0137] The image processing apparatus provided in this application embodiment belongs to the same concept as the image processing method in the above embodiment. Any of the methods provided in the image processing method embodiment can be run on the image processing apparatus. For details of its implementation process, please refer to the image processing method embodiment, which will not be repeated here.

[0138] It should be noted that, for the image processing method described in the embodiments of this application, those skilled in the art will understand that all or part of the process of the image processing method described in the embodiments of this application can be implemented by a computer program controlling related hardware. The computer program can be stored in a computer-readable storage medium, such as a memory, and executed by at least one processor. During execution, it can include the process of the embodiments of the image processing method described. The storage medium can be a magnetic disk, optical disk, read-only memory (ROM), random access memory (RAM), etc.

[0139] For the image processing apparatus described in this application embodiment, its functional modules can be integrated into a single processing chip, or each module can exist physically separately, or two or more modules can be integrated into one module. The integrated module can be implemented in hardware or as a software functional module. If the integrated module is implemented as a software functional module and sold or used as an independent product, it can also be stored in a computer-readable storage medium, such as a read-only memory, a disk, or an optical disk.

[0140] The foregoing has provided a detailed description of an image processing method, apparatus, storage medium, and electronic device provided in the embodiments of this application. Specific examples have been used to illustrate the principles and implementation methods of this application. The descriptions of the above embodiments are only for the purpose of helping to understand the method and core ideas of this application. At the same time, for those skilled in the art, there will be changes in the specific implementation methods and application scope based on the ideas of this application. Therefore, the content of this specification should not be construed as a limitation of this application.

Claims

1. An image processing method applied to an electronic device, comprising: The image processing method comprises: ​ When a user downloads an image from a social application software, preset feature parameters are extracted from the image, the preset feature parameters comprising a target object image, a scene and a text, wherein the text exists in the image; Degrees of correlation of the target object image, the scene and the text with a preset object are determined; Degrees of correlation of the target object image, the scene and the text with a preset object are determined; Degrees of correlation of the target object image, the scene and the text with a preset object are determined; 2. The image processing method of claim 1, wherein, The target object image comprises a human face image or an object image. The preset deletion procedure comprises automatic deletion or isolation. The image processing device comprises: A determining module is configured to, when a user downloads an image from a social application software, extract preset feature parameters from the image, the preset feature parameters comprising a target object image, a scene and a text, wherein the text exists in the image; determine degrees of correlation of the target object image, the scene and the text with a preset object; and determine a degree of correlation of the image with the preset object according to degrees of correlation of the target object image, the scene and the text with the preset object and corresponding weight coefficients, wherein the preset object is the user; 3. The image processing method of claim 1, wherein, A processing module is configured to, if the degree of correlation of the image with the preset object is less than or equal to a preset degree of correlation threshold value and a storage time of the image on the electronic device is greater than a preset time threshold value, process the image according to a preset deletion procedure.

4. The image processing method of claim 1, wherein, ​ ​ 5. An image processing apparatus applied to an electronic device, characterized by comprising: ​ ​ ​ 6. A computer-readable storage medium having stored thereon a computer program, characterized in that When the computer program is executed on a computer, it causes the computer to perform the method of any one of claims 1 to 4.

7. An electronic device, comprising: A computer program product comprising a memory and a processor, characterized in that the processor, by invoking the computer program stored in the memory, is operative to perform the method of any one of claims 1 to 4.

Images