Image data management method, device, equipment and storage medium

CN118035955BActive Publication Date: 2024-11-19深圳兴科华创信息技术有限公司
View PDF 0 Cites 0 Cited by

Patent Information

Application Number
CN202410204157.X
Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
Filing Date
2024-02-23
Publication Date
2024-11-19
Estimated Expiration
2044-02-23

AI Technical Summary

Technical Problem

然而,随之而来的盗版和侵权问题也日益严重,给版权所有者带来了损失和困扰

Benefits of technology

[0018] This application provides an image data management method, device, equipment and storage medium. The method includes obtaining an image to be identified and performing dynamic object processing on the image to be identified to obtain a background image of the image to be identified. ; Acquire multiple background images corresponding to the background image; wherein each of the background images is different from each other; for each of the background images, perform background attribute encoding processing on the background image based on a preset background attribute encoding rule, Obtain the background attribute code corresponding to the background image; for each of the background images, obtain a target copyright image set corresponding to the background image in a preset image copyright database based on the background attribute code corresponding to the background image; wherein , the target copyrighted image set includes a plurality of copyrighted images; determining whether the image to be identified is infringing based on each of the background images and the target copyrighted image set corresponding to each of the background images. This method, on the one hand, obtains the background image of the image to be recognized by performing dedynamic processing on the image to be recognized, obtains multiple background images corresponding to the background image, and determines the target based on each of the background images. Whether the image to be identified is infringing can be accurately determined whether the image to be identified is infringing, and effective protection of image copyright is achieved. On the other hand, by performing background attribute encoding processing on the background image based on preset background attribute encoding rules for each of the background images, the background attribute encoding corresponding to the background image is obtained, and for each of the background images, Based on the background attribute coding corresponding to the background image, the target copyright image set corresponding to the background image is obtained in the preset image copyright database, achieving a more accurate judgment of whether the image to be identified is infringing, and reducing the risk of misjudgment. possibility, while improving the efficiency of judgment.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN118035955B_ABST
    Figure CN118035955B_ABST
Patent Text Reader

Abstract

The present application relates to the field of image processing technology, and provides a method, device, equipment and storage medium for managing image data. The method includes: performing dynamic object removal processing on an image to be identified to obtain a background image of the image to be identified; obtaining multiple background images corresponding to the background image; wherein each background image is different from each other; for each background image, performing background attribute encoding processing on the background image based on a preset background attribute encoding rule to obtain a background attribute encoding corresponding to the background image; for each background image, obtaining a target copyright image set corresponding to the background image in a preset image copyright database based on the background attribute encoding corresponding to the background image; wherein the target copyright image set includes multiple copyright images; judging whether the image to be identified is infringing based on each background image and the target copyright image set corresponding to each background image. The method can accurately judge whether the image to be identified is infringing.
Need to check novelty before this filing date? Find Prior Art

Description

Technical Field

[0001] The present application relates to the field of image processing technology, and in particular to an image data management method, device, equipment and storage medium. Background Art

[0002] With the widespread application of digital technology, the dissemination and use of image data has become a common phenomenon in daily life. However, the problems of piracy and infringement have become increasingly serious, causing losses and troubles to copyright owners. At present, the method of identifying whether an image is infringing is usually to obtain the similarity between the image and each copyright image in the copyright image database. When any similarity is greater than the preset similarity threshold, the image is judged to be infringing. This method of identifying whether an image is infringing has the problem of low accuracy. Summary of the invention

[0003] The present application provides an image data management method, device, equipment and storage medium to solve the problems raised by the above background technology.

[0004] In a first aspect, the present application provides a method for managing image data, comprising:

[0005] Acquire an image to be identified, and perform dynamic object removal processing on the image to be identified to obtain a background image of the image to be identified;

[0006] Acquire multiple background images corresponding to the background image; wherein each of the background images is different from each other;

[0007] For each of the background images, performing background attribute coding processing on the background image based on a preset background attribute coding rule to obtain a background attribute code corresponding to the background image;

[0008] For each of the background images, based on the background attribute code corresponding to the background image, a target copyright image set corresponding to the background image is obtained in a preset image copyright database; wherein the target copyright image set includes a plurality of copyright images;

[0009] Whether the image to be identified is infringing is determined based on each of the background images and the target copyright image set corresponding to each of the background images.

[0010] In a second aspect, the present application provides an image data management device, comprising:

[0011] A first acquisition module is used to acquire an image to be recognized, and perform a dynamic object removal process on the image to be recognized to obtain a background image of the image to be recognized;

[0012] A second acquisition module is used to acquire a plurality of background images corresponding to the background image; wherein each of the background images is different from each other;

[0013] An encoding module, used for performing background attribute encoding processing on each of the background images based on a preset background attribute encoding rule to obtain a background attribute code corresponding to the background image;

[0014] A third acquisition module is used to acquire, for each of the background images, a target copyright image set corresponding to the background image in a preset image copyright database based on the background attribute code corresponding to the background image; wherein the target copyright image set includes a plurality of copyright images;

[0015] The judgment module is used to judge whether the image to be identified is infringing based on each of the background images and the target copyright image set corresponding to each of the background images.

[0016] In a third aspect, the present application provides a terminal device, comprising a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the image data management method as described above is implemented.

[0017] In a fourth aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, wherein when the computer program is executed by a processor, the image data management method as described above is implemented.

[0018] The present application provides a method, device, equipment and storage medium for managing image data, wherein the method includes obtaining an image to be identified, and performing a dynamic object removal process on the image to be identified to obtain a background image of the image to be identified; obtaining multiple background images corresponding to the background image; wherein each of the background images is different from each other; for each of the background images, performing background attribute encoding process on the background image based on a preset background attribute encoding rule to obtain a background attribute encoding corresponding to the background image; for each of the background images, based on the background attribute encoding corresponding to the background image, obtaining a target copyright image set corresponding to the background image in a preset image copyright database; wherein the target copyright image set includes multiple copyright images; judging whether the image to be identified is infringing based on each of the background images and the target copyright image set corresponding to each of the background images. The method, on the one hand, can accurately judge whether the image to be identified is infringing by performing a dynamic object removal process on the image to be identified to obtain a background image of the image to be identified, obtaining multiple background images corresponding to the background image, and judging whether the image to be identified is infringing based on each of the background images, thereby achieving effective protection of image copyright. On the other hand, by performing background attribute coding processing on each of the background images based on preset background attribute coding rules to obtain the background attribute coding corresponding to the background image, and for each of the background images, obtaining the target copyright image set corresponding to the background image in a preset image copyright database based on the background attribute coding corresponding to the background image, it is possible to more accurately judge whether the image to be identified is infringing, reduce the possibility of misjudgment, and improve the efficiency of judgment. BRIEF DESCRIPTION OF THE DRAWINGS

[0019] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying any creative work.

[0020] Figure 1 A flowchart of a method for managing image data provided in an embodiment of the present application;

[0021] Figure 2 A schematic block diagram of the structure of an image data management device provided in an embodiment of the present application;

[0022] Figure 3 A schematic block diagram of the structure of a terminal device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0023] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0024] The flowcharts shown in the accompanying drawings are only examples and do not necessarily include all the contents and operations / steps, nor must they be executed in the order described. For example, some operations / steps may also be decomposed, combined or partially merged, so the actual execution order may change according to actual conditions.

[0025] It should also be understood that the terms used in this application specification are only for the purpose of describing specific embodiments and are not intended to limit the application. As used in this application specification and the appended claims, unless the context clearly indicates otherwise, the singular forms "a", "an" and "the" are intended to include plural forms.

[0026] It should be further understood that the term “and / or” used in the specification and appended claims refers to any combination and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0027] With the widespread application of digital technology, the dissemination and use of image data has become a common phenomenon in daily life. However, the ensuing piracy and infringement problems are becoming increasingly serious, causing losses and troubles to copyright owners. At present, the method for identifying whether an image is infringing is usually to obtain the similarity between the image and each copyright image in the copyright image database. When any similarity is greater than a preset similarity threshold, the image is determined to be infringing. This method of identifying whether an image is infringing has the problem of low accuracy. To this end, the embodiments of the present application provide a method, device, equipment and storage medium for managing image data to solve the above problems.

[0028] In conjunction with the accompanying drawings, some embodiments of the present application are described in detail below. In the absence of conflict, the following embodiments and features in the embodiments can be combined with each other.

[0029] See also Figure 1 , Figure 1 A flowchart of the image data management method provided in the embodiment of the present application is shown in FIG. Figure 1 As shown, the image data management method provided in the embodiment of the present application includes steps S100 to S500.

[0030] Step S100: Acquire an image to be recognized, and remove dynamic objects from the image to be recognized to obtain a background image of the image to be recognized.

[0031] Step S200: Acquire multiple background images corresponding to the background image; wherein each of the background images is different from each other.

[0032] Step S300: for each of the background images, perform background attribute coding processing on the background image based on a preset background attribute coding rule to obtain a background attribute code corresponding to the background image.

[0033] Step S400: for each of the background images, based on the background attribute code corresponding to the background image, a target copyright image set corresponding to the background image is obtained from a preset image copyright database; wherein the target copyright image set includes a plurality of copyright images.

[0034] Step S500: determining whether the image to be identified is infringing based on each of the background images and the target copyright image set corresponding to each of the background images.

[0035] In this embodiment, as described in the above step S100, an image to be identified is obtained, and the image to be identified is processed to remove dynamic objects to obtain a background image of the image to be identified. Specifically, after the image to be identified is obtained, first, the image to be identified is input into a preset semantic segmentation model to obtain multiple objects in the image to be identified, and the image to be identified is processed by frame division to obtain multiple first image frames corresponding to the image to be identified, and then, for each of the objects, multiple first target image frames including the object are selected from the multiple first image frames, and then, for each of the objects, the position of the pixel corresponding to the object is determined in each of the first target image frames corresponding to the object, and it is determined whether each of the positions is completely consistent, and when each of the positions is not completely consistent, it is determined that the object is a dynamic object, and finally, for each of the dynamic objects, the dynamic object is removed from each of the first target image frames corresponding to the dynamic object to obtain the background image of the image to be identified. The semantic segmentation model includes an input layer, a deep network learning layer and an output layer. The input layer is used to receive the image to be identified. The deep network learning layer is used to perform deep learning on the image to be identified to obtain multiple objects of the image to be identified. The output layer is used to output multiple objects. The objects include but are not limited to people, animals, plants, buildings and vehicles.

[0036] As described in the above step S200, after obtaining the background image, multiple background images corresponding to the background image are obtained. Specifically, first, the background image is frame-divided to obtain multiple second image frames corresponding to the background image. Then, for each of the second image frames, the chromaticity value of each pixel of the second image frame is calculated, and based on the position of the pixel corresponding to each of the chromaticity values ​​in the second image frame, each of the chromaticity values ​​is arranged in sequence to obtain a chromaticity value vector corresponding to the second image frame. Secondly, the first difference vectors between the chromaticity value vectors corresponding to two adjacent second image frames are calculated respectively. Then, for each of the first difference vectors, the first vector modulus of the first difference vector is calculated, and the first vector modulus is compared with a first preset vector modulus, and when the first vector modulus is greater than the first preset vector modulus, the second image frame corresponding to the first difference vector is determined as the second target image frame. Finally, all the second target image frames are deduplicated to obtain multiple background images.

[0037] As described in the above step S300, after obtaining multiple background images, for each of the background images, background attribute encoding processing is performed on the background image based on a preset background attribute encoding rule to obtain the background attribute encoding corresponding to the background image. Specifically, for each of the background images, first, the background image is input into a preset background image classification model to obtain the background attribute of the background image, and then, a preset background attribute-background attribute encoding relationship mapping table is traversed to obtain the background attribute encoding corresponding to the background attribute. Among them, the background image classification model includes an input layer, a feature extraction layer, a classification layer and an output layer, the input layer is used to receive the background image, the feature extraction layer is used to extract the features of the background image, the classification layer generates the background attributes of the background image based on the features of the background image, and the output layer is used to output the background attributes. The background attributes include but are not limited to landscapes, field pictures, home pictures, office space pictures, pastoral pictures and portraits of people.

[0038] As described in the above step S400, after the background attribute code is obtained, for each of the background images, a target copyright image set corresponding to the background image is obtained in a preset image copyright database based on the background attribute code corresponding to the background image. Specifically, for each of the background images, first, an identification code of the target copyright image set is generated based on the background attribute code corresponding to the background image, and then, the target copyright image set is obtained in a preset image copyright database based on the identification code.

[0039] As described in step S500, after obtaining the target copyright image set corresponding to each background image, it is determined whether the image to be identified is infringing based on each background image and the target copyright image set corresponding to each background image. Specifically, for each background image, each copyright image in the target copyright image set corresponding to the background image is traversed, and if there is a copyright image that is consistent with the background image, it is determined that the image to be identified is infringing.

[0040] The method provided in this embodiment, on the one hand, obtains the background image of the image to be identified by performing de-dynamic processing on the image to be identified, obtains multiple background images corresponding to the background image, and judges whether the image to be identified is infringing based on each of the background images, so as to accurately judge whether the image to be identified is infringing, thereby achieving effective protection of image copyright. On the other hand, by performing background attribute coding processing on each of the background images based on a preset background attribute coding rule to obtain the background attribute code corresponding to the background image, and for each of the background images, obtaining the target copyright image set corresponding to the background image in a preset image copyright database based on the background attribute code corresponding to the background image, it is possible to more accurately judge whether the image to be identified is infringing, reduce the possibility of misjudgment, and improve the efficiency of judgment.

[0041] In some embodiments, the process of removing dynamic objects from the image to be identified to obtain a background image of the image to be identified includes the following steps:

[0042] Inputting the image to be identified into a preset semantic segmentation model to obtain multiple objects in the image to be identified, and performing frame processing on the image to be identified to obtain multiple first image frames corresponding to the image to be identified;

[0043] For each of the objects, selecting a plurality of first target image frames including the object from the plurality of first image frames;

[0044] For each of the objects, respectively determine the position of the pixel corresponding to the object in each of the first target image frames corresponding to the object, and judge whether each of the positions is completely consistent, and when each of the positions is not completely consistent, determine that the object is a dynamic object;

[0045] For each of the dynamic objects, the dynamic object is removed from each of the first target image frames corresponding to the dynamic object to obtain a background image of the image to be recognized.

[0046] In this embodiment, first, the image to be identified is input into a preset semantic segmentation model to obtain multiple objects in the image to be identified, and the image to be identified is processed into frames to obtain multiple first image frames corresponding to the image to be identified. Specifically, first, the semantic segmentation model is obtained from a preset database, then, the image to be identified is input into the semantic segmentation model, and each object in the image to be identified is identified and segmented using the semantic segmentation model, and finally, the image to be identified is segmented according to the time sequence of playback to obtain multiple first image frames.

[0047] Then, for each of the objects, multiple first target image frames including the object are selected from the multiple first image frames. Specifically, for each of the objects, all the first image frames are traversed, and the first image frame including the object is determined as the first target image frame.

[0048] Secondly, for each of the objects, the positions of the pixels corresponding to the object are determined in each of the first target image frames corresponding to the object, and it is determined whether the positions are completely consistent. When the positions are not completely consistent, the object is determined to be a dynamic object. Specifically, first, position editing is performed for each pixel of each of the first target image frames corresponding to the object, and then, for each of the objects, the pixels occupied by the object are determined in each of the first target image frames corresponding to the object. Secondly, the positions of the pixels occupied by the object are determined in each of the first target image frames corresponding to the object, and then, in each of the first target image frames corresponding to the object, it is determined whether the positions of the pixels occupied by the object in each of the first target image frames are completely consistent. Finally, when they are not completely consistent, the object is determined to be a dynamic object. Exemplarily, the target object corresponds to three first target image frames, and the target object occupies the first, second, third and fourth pixels of the three first target image frames in the three first target image frames, then it is determined that the positions of the pixels occupied by the target object in each of the first target image frames are completely consistent.

[0049] Finally, for each of the dynamic objects, the dynamic object is removed from each of the first target image frames corresponding to the dynamic object to obtain a background image of the image to be recognized.

[0050] By adopting the method of this embodiment, dynamic objects in the image to be identified can be accurately removed, thereby obtaining a clear background image, which helps to accurately determine whether the image to be identified is infringing.

[0051] In some embodiments, the obtaining of multiple background images corresponding to the background image includes the following method:

[0052] Performing frame processing on the background image to obtain a plurality of second image frames corresponding to the background image;

[0053] For each of the second image frames, calculate the chromaticity value of each pixel of the second image frame, and arrange the chromaticity values ​​in sequence based on the position of the pixel corresponding to each of the chromaticity values ​​in the second image frame to obtain a chromaticity value vector corresponding to the second image frame;

[0054] respectively calculating a first difference vector between the chroma value vectors corresponding to two adjacent second image frames;

[0055] For each of the first difference vectors, calculating a first vector modulus of the first difference vector, and comparing the first vector modulus with a first preset vector modulus, and when the first vector modulus is greater than the first preset vector modulus, determining a second image frame corresponding to the first difference vector as a second target image frame;

[0056] Deduplication processing is performed on all the second target image frames to obtain a plurality of the background images.

[0057] In this embodiment, first, the background image is subjected to frame processing to obtain a plurality of second image frames corresponding to the background image. Specifically, video processing software such as Adobe Premiere Pro, Final Cut Pro, and Sony Vegas Pro can be used to perform frame processing on the background image to obtain a plurality of second image frames corresponding to the background image.

[0058] Then, for each of the second image frames, the chromaticity values ​​of each pixel of the second image frame are calculated, and based on the positions of the pixels corresponding to each of the chromaticity values ​​in the second image frame, the chromaticity values ​​are arranged in sequence to obtain the chromaticity value vector corresponding to the second image frame. Specifically, for each of the second image frames, first, the chromaticity values ​​of each pixel of the second image frame are calculated using image processing software such as Adobe Photoshop, GIMP, OpenCV, and MATLAB, and then, based on the positions of the pixels corresponding to each of the chromaticity values ​​in the second image frame, the chromaticity values ​​are arranged in sequence to obtain the chromaticity value vector corresponding to the second image frame.

[0059] Secondly, first difference vectors between the chrominance value vectors corresponding to two adjacent second image frames are calculated respectively.

[0060] Furthermore, for each of the first difference vectors, a first vector modulus of the first difference vector is calculated, and the first vector modulus is compared with a first preset vector modulus, and when the first vector modulus is greater than the first preset vector modulus, the second image frame corresponding to the first difference vector is determined as the second target image frame. It can be understood that each of the first difference vectors corresponds to two of the second image frames.

[0061] Finally, all the second target image frames are deduplicated to obtain a plurality of the background images. Specifically, first, the second target image frames are arranged in sequence based on the playback order of the background image to obtain a sequence of second target image frames, and then, the second difference vectors between the chromaticity value vectors corresponding to two adjacent second target image frames are calculated respectively, and finally, for each second difference vector, the second vector modulus of the second difference vector is calculated, and the second vector modulus is compared with the second preset vector modulus, and when the second vector modulus is smaller than the second preset vector modulus, any second target image frame of the two second target image frames corresponding to the second difference vector is deleted; wherein, the second preset vector modulus is smaller than the first preset vector modulus.

[0062] The method provided in this embodiment obtains multiple second image frames corresponding to the background image by performing frame processing on the background image, and respectively obtains the chromaticity value vectors corresponding to each of the second image frames, and obtains multiple background images based on each of the chromaticity value vectors, so that multiple background images can be accurately obtained.

[0063] In some embodiments, the step of acquiring a target copyright image set corresponding to the background image in a preset image copyright database based on the background attribute code corresponding to the background image comprises the following steps:

[0064] Respectively obtaining the similarities between two adjacent coded characters of the background attribute code, and arranging the similarities in sequence based on the order of the coded characters corresponding to the similarities in the background attribute code to obtain the similarity sequence;

[0065] Taking the digits with the lowest similarity in the similarity sequence as target digits, and arranging the target digits in sequence based on the order of the similarities corresponding to the target digits in the similarity sequence, to obtain a digit sequence; wherein the digit sequence includes n digits;

[0066] Construct an n×n blank table;

[0067] For each row of the table, multiple target numbers are obtained by multiplying the number of the row by each number in the number sequence, and the target numbers are arranged in sequence based on the order of the numbers corresponding to the target numbers in the number sequence to obtain a target number sequence corresponding to the row, and the target numbers in the target number sequence are inserted into each cell of the row in sequence to obtain a target table;

[0068] Extracting the diagonal numbers of the target table, and arranging the diagonal numbers in sequence based on the order of the diagonal numbers in the target table, to obtain the identification code of the target copyrighted image set;

[0069] The target copyright image set is acquired from a preset image copyright database based on the identification code.

[0070] The method provided in this embodiment generates an identification code of a target copyright image set corresponding to each background image based on the background attribute code corresponding to the background image, and obtains the target copyright data set corresponding to the background image in a preset image copyright database based on the identification code, so that the target copyright data set corresponding to the background image can be accurately obtained in the preset image copyright database.

[0071] See also Figure 2 , Figure 2 The schematic block diagram of the structure of the image data management device 100 provided in the embodiment of the present application is as follows: Figure 2 As shown, the image data management device 100 includes:

[0072] The first acquisition module 110 is used to acquire the image to be recognized, and perform dynamic object removal processing on the image to be recognized to obtain a background image of the image to be recognized.

[0073] The second acquisition module 120 is used to acquire a plurality of background images corresponding to the background image; wherein each of the background images is different from each other.

[0074] The encoding module 130 is used to perform background attribute encoding processing on each of the background images based on a preset background attribute encoding rule to obtain a background attribute code corresponding to the background image.

[0075] The third acquisition module 140 is used to acquire, for each background image, a target copyright image set corresponding to the background image in a preset image copyright database based on the background attribute code corresponding to the background image; wherein the target copyright image set includes a plurality of copyright images.

[0076] The judgment module 150 is used to judge whether the image to be identified is infringing based on each of the background images and the target copyright image set corresponding to each of the background images.

[0077] It should be noted that technicians in the relevant technical field can clearly understand that for the convenience and simplicity of description, the specific working process of the above-described device and each module can refer to the corresponding process in the aforementioned image data management method embodiment, and will not be repeated here.

[0078] The image data management device 100 provided in the above embodiment can be implemented in the form of a computer program. The computer program can be used in Figure 3 The system is run on the terminal device 200 shown.

[0079] See also Figure 3 , Figure 3 The terminal device 200 provided in the embodiment of the present application is a schematic block diagram of the structure, wherein the terminal device 200 includes a processor 201 and a memory 202, wherein the processor 201 and the memory 202 are connected via a system bus 203, wherein the memory 202 may include a non-volatile storage medium and an internal memory.

[0080] The non-volatile storage medium can store a computer program. The computer program includes program instructions, and when the program instructions are executed by the processor 201, the processor 201 can execute any of the above-mentioned image data management methods.

[0081] The processor 201 is used to provide computing and control capabilities to support the operation of the entire terminal device 200.

[0082] The internal memory provides an environment for the operation of the computer program in the non-volatile storage medium. When the computer program is executed by the processor 201, the processor 201 can execute any of the above-mentioned image data management methods.

[0083] Those skilled in the art will understand that Figure 3 The structure shown in the figure is only a block diagram of a partial structure related to the scheme of the present application, and does not constitute a limitation on the terminal device 200 involved in the scheme of the present application. The specific terminal device 200 may include more or fewer components than shown in the figure, or combine certain components, or have a different component arrangement.

[0084] It should be understood that the processor 201 may be a central processing unit (CPU), and the processor 201 may also be other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. Among them, the general-purpose processor may be a microprocessor or the processor may also be any conventional processor, etc.

[0085] In some embodiments, the processor 201 is used to run a computer program stored in the memory to implement the following steps:

[0086] Acquire an image to be identified, and perform dynamic object removal processing on the image to be identified to obtain a background image of the image to be identified;

[0087] Acquire multiple background images corresponding to the background image; wherein each of the background images is different from each other;

[0088] For each of the background images, performing background attribute coding processing on the background image based on a preset background attribute coding rule to obtain a background attribute code corresponding to the background image;

[0089] For each of the background images, based on the background attribute code corresponding to the background image, a target copyright image set corresponding to the background image is obtained in a preset image copyright database; wherein the target copyright image set includes a plurality of copyright images;

[0090] Whether the image to be identified is infringing is determined based on each of the background images and the target copyright image set corresponding to each of the background images.

[0091] It should be noted that those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working process of the terminal device 200 described above can refer to the corresponding process of the aforementioned image data management method, and will not be repeated here.

[0092] An embodiment of the present application also provides a computer-readable storage medium, which stores a computer program. When the computer program is executed by one or more processors, the one or more processors implement the image data management method provided in the embodiment of the present application.

[0093] The computer-readable storage medium may be an internal storage unit of the terminal device 200 in the aforementioned embodiment, such as a hard disk or memory of the terminal device 200. The computer-readable storage medium may also be an external storage device of the terminal device 200, such as a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), etc. equipped with the terminal device 200.

[0094] The above is only a specific implementation of the present application, but the protection scope of the present application is not limited thereto. Any technician familiar with the technical field can easily think of various equivalent modifications or replacements within the technical scope disclosed in the present application, and these modifications or replacements should be included in the protection scope of the present application. Therefore, the protection scope of the present application shall be based on the protection scope of the claims.

Claims

1. A method for managing image data, characterized in that: include: Acquire an image to be identified, and perform dynamic object removal processing on the image to be identified to obtain a background image of the image to be identified; Acquire multiple background images corresponding to the background image; wherein each of the background images is different from each other; For each of the background images, performing background attribute coding processing on the background image based on a preset background attribute coding rule to obtain a background attribute code corresponding to the background image; For each of the background images, based on the background attribute code corresponding to the background image, a target copyright image set corresponding to the background image is obtained in a preset image copyright database; wherein the target copyright image set includes a plurality of copyright images; Determining whether the image to be identified is infringing based on each of the background images and the target copyright image set corresponding to each of the background images; The step of acquiring a target copyright image set corresponding to the background image in a preset image copyright database based on the background attribute code corresponding to the background image includes: Respectively obtaining the similarities between two adjacent coded characters of the background attribute code, and arranging the similarities in sequence based on the order of the coded characters corresponding to the similarities in the background attribute code to obtain the similarity sequence; Taking the lowest-order digits of each similarity in the similarity sequence as target digits, and arranging the target digits in sequence based on the order of the similarities corresponding to the target digits in the similarity sequence, to obtain a digit sequence; wherein the digit sequence includes n digits; Construct an n×n blank table; For each row of the table, multiple target numbers are obtained by multiplying the number of the row by each number in the number sequence, and the target numbers are arranged in sequence based on the order of the numbers corresponding to the target numbers in the number sequence to obtain a target number sequence corresponding to the row, and the target numbers in the target number sequence are inserted into each cell of the row in sequence to obtain a target table; Extracting the diagonal numbers of the target table, and arranging the diagonal numbers in sequence based on the order of the diagonal numbers in the target table, to obtain the identification code of the target copyrighted image set; The target copyright image set is acquired from a preset image copyright database based on the identification code.

2. The image data management method according to claim 1, characterized in that: The step of removing dynamic objects from the image to be identified to obtain a background image of the image to be identified includes: Inputting the image to be identified into a preset semantic segmentation model to obtain multiple objects in the image to be identified, and performing frame processing on the image to be identified to obtain multiple first image frames corresponding to the image to be identified; For each of the objects, selecting a plurality of first target image frames including the object from the plurality of first image frames; For each of the objects, respectively determine the position of the pixel corresponding to the object in each of the first target image frames corresponding to the object, and judge whether each of the positions is completely consistent, and when each of the positions is not completely consistent, determine that the object is a dynamic object; For each of the dynamic objects, the dynamic object is removed from each of the first target image frames corresponding to the dynamic object to obtain a background image of the image to be recognized.

3. The image data management method according to claim 1, characterized in that: The obtaining of a plurality of background images corresponding to the background image comprises: Performing frame processing on the background image to obtain a plurality of second image frames corresponding to the background image; For each of the second image frames, calculate the chromaticity value of each pixel of the second image frame, and arrange the chromaticity values ​​in sequence based on the position of the pixel corresponding to each of the chromaticity values ​​in the second image frame to obtain a chromaticity value vector corresponding to the second image frame; respectively calculating a first difference vector between the chrominance value vectors corresponding to two adjacent second image frames; For each of the first difference vectors, calculating a first vector modulus of the first difference vector, and comparing the first vector modulus with a first preset vector modulus, and when the first vector modulus is greater than the first preset vector modulus, determining a second image frame corresponding to the first difference vector as a second target image frame; Deduplication processing is performed on all the second target image frames to obtain a plurality of the background images.

4. The image data management method according to claim 3, characterized in that: The deduplication processing is performed on all the second target image frames to obtain a plurality of the background images, including: Arranging the second target image frames in sequence based on the playback order of the background image to obtain a sequence of second target image frames; respectively calculating a second difference vector between the chroma value vectors corresponding to two adjacent second target image frames; For each of the second difference vectors, calculate the second vector modulus of the second difference vector, and compare the second vector modulus with the second preset vector modulus, and when the second vector modulus is smaller than the second preset vector modulus, delete any second target image frame of the two second target image frames corresponding to the second difference vector; wherein the second preset vector modulus is smaller than the first preset vector modulus.

5. The image data management method according to claim 1, characterized in that: The step of judging whether the image to be identified is infringing based on each of the background images and the target copyright image set corresponding to each of the background images includes: For each of the background images, each copyright image in the target copyright image set corresponding to the background image is traversed, and if there is a copyright image that is consistent with the background image, it is determined that the image to be identified is infringing.

6. An image data management device, characterized in that: include: A first acquisition module is used to acquire an image to be recognized, and perform a dynamic object removal process on the image to be recognized to obtain a background image of the image to be recognized; A second acquisition module is used to acquire a plurality of background images corresponding to the background image; wherein each of the background images is different from each other; An encoding module, used for performing background attribute encoding processing on each of the background images based on a preset background attribute encoding rule to obtain a background attribute code corresponding to the background image; A third acquisition module is used to acquire, for each of the background images, a target copyright image set corresponding to the background image in a preset image copyright database based on the background attribute code corresponding to the background image; wherein the target copyright image set includes a plurality of copyright images; A judgment module, used for judging whether the image to be identified is infringing based on each of the background images and the target copyright image set corresponding to each of the background images; The step of acquiring a target copyright image set corresponding to the background image in a preset image copyright database based on the background attribute code corresponding to the background image includes: Respectively obtaining the similarities between two adjacent coded characters of the background attribute code, and arranging the similarities in sequence based on the order of the coded characters corresponding to the similarities in the background attribute code to obtain the similarity sequence; Taking the lowest-order digits of each similarity in the similarity sequence as target digits, and arranging the target digits in sequence based on the order of the similarities corresponding to the target digits in the similarity sequence, to obtain a digit sequence; wherein the digit sequence includes n digits; Construct an n×n blank table; For each row of the table, multiple target numbers are obtained by multiplying the number of the row by each number in the number sequence, and the target numbers are arranged in sequence based on the order of the numbers corresponding to the target numbers in the number sequence to obtain a target number sequence corresponding to the row, and the target numbers in the target number sequence are inserted into each cell of the row in sequence to obtain a target table; Extracting the diagonal numbers of the target table, and arranging the diagonal numbers in sequence based on the order of the diagonal numbers in the target table, to obtain the identification code of the target copyrighted image set; The target copyright image set is acquired from a preset image copyright database based on the identification code.

7. A terminal device, characterized in that: The terminal device includes a processor, a memory, and a computer program stored in the memory and executable by the processor, wherein when the computer program is executed by the processor, the image data management method according to any one of claims 1 to 5 is implemented.

8. A computer-readable storage medium, characterized in that: The computer-readable storage medium stores a computer program, wherein when the computer program is executed by a processor, the image data management method according to any one of claims 1 to 5 is implemented.