An identity archiving method and device, electronic equipment and storage medium

Abstract

Embodiments of the present application provide an identity archiving method and device, electronic equipment and storage medium, which are used to realize identity archiving, reduce the probability of archiving the images of the same person into multiple archives, and improve the image archiving efficiency. The method comprises the following steps: obtaining a first image set with image quality higher than a first preset threshold from a collected face image set; adding identity identification information to each image in the first image set according to a static standard database to cluster the images in the face image set, and generating multiple archives; determining whether there is an image with added identity identification information in each archive of the multiple archives; if there is a first image with added identity identification information in a first archive, determining that the identity identification information of the first image is the identity identification information of the first archive; wherein the first image belongs to the first image set; and archiving the identity of the first archive according to the identity identification information.

Description

Technical Field

[0001] This invention relates to the field of computer network technology, and in particular to an identity archiving method, apparatus, electronic device, and storage medium. Background Technology

[0002] In related technologies, facial recognition is performed on the acquired images to extract facial feature values. These values ​​are then compared with existing manually created archives. If the comparison result meets a threshold, the image is archived in the current archive; otherwise, a new archive is created to store the acquired image. However, because each image needs to be compared with existing archives, the efficiency of image archiving is relatively low. Summary of the Invention

[0003] This application provides an identity archiving method, apparatus, electronic device, and storage medium for implementing identity archiving, reducing the probability of archiving the image of the same person into multiple files, and improving image archiving efficiency.

[0004] Firstly, an identity archiving method is provided, the method comprising:

[0005] Obtain a first image set whose image quality is higher than a first preset threshold from the collected face image set;

[0006] Identity identification information is added to each image in the first image set according to a static standard database; wherein, the static standard database is used to store identity verification images;

[0007] The images in the face image set are clustered to generate multiple profiles; each profile corresponds to a person's identity.

[0008] Determine whether each of the multiple files contains an image with added identification information;

[0009] If a first image with added identification information exists in the first file, then the identification information of the first image is determined to be the identification information of the first file; wherein, the first image belongs to the first image set;

[0010] The first file is archived based on the identity information.

[0011] Optionally, obtaining a first image set with image quality higher than a first preset threshold from the collected face image set includes:

[0012] Each image in the face image set is scored to obtain an image quality score for each image in the face image set.

[0013] Obtain a first set of images whose image quality scores are higher than the first preset threshold.

[0014] Optionally, adding identification information to each image in the first image set according to a static standard database includes:

[0015] The similarity score is obtained by comparing the second image in the first image set with the images in the static standard base library.

[0016] Identify the identity information of the first person whose similarity exceeds a second preset threshold;

[0017] Add the identity information corresponding to the first person to the second image.

[0018] Optionally, the method further includes:

[0019] Retrieve a third image with added identity information;

[0020] Determine whether a second file among the multiple archived files contains the same identity information as the third image;

[0021] If it is determined that the second file exists among the multiple files that have been identified and archived, then the third image is added to the second file;

[0022] If it is determined that the second file does not exist among the multiple files that have been archived with identity verification, a third file is created, and the third image is added to the third file.

[0023] Optionally, the method further includes:

[0024] Obtain historical files that have the same identity information as the first file;

[0025] When the first file meets the preset conditions, the first file and the historical file are merged.

[0026] Secondly, an identity archiving device is provided, the device comprising:

[0027] The acquisition module is used to acquire a first image set whose image quality is higher than a first preset threshold from the collected face image set;

[0028] The processing module is used to add identity information to each image in the first image set according to a static standard database; wherein, the static standard database is used to store identity verification images;

[0029] The processing module is also used to cluster the images in the face image set to generate multiple profiles; wherein each profile corresponds to a person's identity.

[0030] The processing module is also used to determine whether each of the plurality of files contains an image with added identification information;

[0031] The processing module is further configured to determine, if there is a first image in the first file that has been added with identification information, that the identification information of the first image is the identification information of the first file; wherein, the first image belongs to the first image set;

[0032] The processing module is also used to archive the first file based on the identity information.

[0033] Optionally, the acquisition module is specifically used for:

[0034] After the processing module performs a quality score on each image in the face image set, it obtains the image quality score for each image in the face image set.

[0035] Obtain a first set of images whose image quality scores are higher than the first preset threshold.

[0036] Optionally, the processing module is specifically used for:

[0037] The similarity score is obtained by comparing the second image in the first image set with the images in the static standard base library.

[0038] Identify the identity information of the first person whose similarity exceeds a second preset threshold;

[0039] Add the identity information corresponding to the first person to the second image.

[0040] Optionally, the processing module is further configured to:

[0041] After the acquisition module acquires the third image with added identity information, it determines whether there is a second file among the multiple archived files with the same identity information as the third image.

[0042] If it is determined that the second file exists among the multiple files that have been identified and archived, then the third image is added to the second file;

[0043] If it is determined that the second file does not exist among the multiple files that have been archived with identity verification, a third file is created, and the third image is added to the third file.

[0044] Optionally, the processing module is further configured to:

[0045] After the acquisition module acquires historical files with the same identity information as the first file, it merges the first file and the historical files when it determines that the first file meets the preset conditions.

[0046] Thirdly, an electronic device is provided, the electronic device comprising:

[0047] Memory, used to store program instructions;

[0048] A processor is configured to invoke program instructions stored in the memory and execute the steps included in any of the methods described in the first aspect, according to the obtained program instructions.

[0049] Fourthly, a computationally readable storage medium is provided, the computationally readable storage medium storing computer-executable instructions for causing a computer to perform the steps included in any of the methods described in the first aspect.

[0050] Fifthly, a computer program product containing instructions is provided, which, when run on a computer, causes the computer to execute the identity archiving method described in the various possible implementations above.

[0051] In this embodiment of the application, a first image set with image quality higher than a first preset threshold is obtained from the collected face image set. Identity identification information is added to each image in the first image set according to a static standard base library. The images in the face image set are clustered to generate multiple files corresponding to individuals. Then, it is determined whether each file in the multiple files contains an image with added identity identification information. If the first file contains a first image with added identity identification information, the identity identification information of the first image is determined as the identity identification information of the first file. The first file is then archived based on the identity identification information.

[0052] In other words, firstly, high-quality images are selected from the face image set for priority archiving and identification information is added. Then, using face image clustering technology, it is determined whether the archived high-quality images are included in the clustered archives. If so, the archives containing the archived images are directly archived. In this way, only the high-quality images need to be compared with the static standard database, which can effectively improve the efficiency of image archiving. At the same time, identification information is added to the archived images according to the static standard database, thereby realizing identity archiving and reducing the probability of archiving the same person's image in multiple archives. Attached Figure Description

[0053] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of this application.

[0054] Figure 1 A flowchart illustrating an identity archiving method provided in this application embodiment;

[0055] Figure 2 A structural block diagram of an identity archiving device provided in an embodiment of this application;

[0056] Figure 3 This is a schematic diagram of the structure of a computer device in an embodiment of the present invention. Detailed Implementation

[0057] To make the objectives, technical solutions, and advantages of this application clearer, the technical solutions in the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only a part of the embodiments of this application, and not all of them. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application. Unless otherwise specified, the embodiments and features in the embodiments of this application can be arbitrarily combined with each other. Furthermore, although a logical order is shown in the flowchart, in some cases, the steps shown or described may be performed in a different order than that shown here.

[0058] The terms "first" and "second" in the specification, claims, and accompanying drawings of this application are used to distinguish different objects, not to describe a specific order. Furthermore, the term "comprising" and any variations thereof are intended to cover non-exclusive protection. For example, a process, method, system, product, or device that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units not listed, or may optionally include other steps or units inherent to these processes, methods, products, or devices. The term "multiple" in this application can mean at least two, for example, two, three, or more, and the embodiments of this application do not impose limitations.

[0059] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0060] Before introducing the embodiments of this application, some technical features of this application will be introduced first to facilitate understanding by those skilled in the art.

[0061] Face clustering: The process of grouping face images belonging to the same person into a set of images.

[0062] Archive: A collection generated by face clustering, identifying a virtual person.

[0063] Centroid: The reference image corresponding to the file, i.e., a representative image.

[0064] File merging: Merging multiple files to create a new file.

[0065] Identity verification: By performing image recognition on facial information in videos or images, and through other correlation methods, the identity and other detailed information of the person are determined.

[0066] Standard static database: A personnel information database that changes slowly (e.g., permanent resident database, temporary resident database, special personnel database, etc.). Images in the static standard database are stored in descending order of ID card processing time.

[0067] The following is a brief introduction to the application scenarios to which the technical solutions of the embodiments of this application are applicable. It should be noted that the application scenarios described below are only for illustrating the embodiments of this application and are not intended to limit the scope. In specific implementation, the technical solutions provided by the embodiments of this application can be flexibly applied according to actual needs.

[0068] The identity archiving method provided in this application can be applied to an image archiving system, which includes a terminal and a server, and the server and terminal transmit data through a network. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud services, cloud databases, cloud computing, etc. The terminal can be a monitoring device or a face recognition camera, etc., that can be used for image acquisition.

[0069] In this embodiment, the terminal device sends the collected images to the server. The server obtains a first image set with a quality higher than a first preset threshold from the face image set sent by the terminal device, compares the images in the first image set with the images in the static standard database, adds identity identification information to the images in the first image set according to the comparison results, and clusters the images in the face image set sent by the terminal device to generate multiple files. Then, it determines whether there is an image with added identity identification information in each file. If there is, the file corresponding to the image with added identity identification information is directly archived.

[0070] The identity archiving method provided in this application will be described below with reference to the accompanying drawings. Please refer to... Figure 1 As shown, the flowchart of the identity archiving method in this application embodiment is described as follows:

[0071] Step 101: Obtain a first image set whose image quality is higher than a first preset threshold from the collected face image set;

[0072] The face image set can be, for example, an image set captured by devices such as face checkpoints or vehicle checkpoints. In this embodiment, after obtaining the face image set, each image in the face image set is quality-scored to obtain an image quality score for each image, and a first image set with an image quality score higher than a first preset threshold is obtained. The first preset threshold is a value obtained based on the analysis of historical data. The methods for scoring the quality of each image in the face image set include, but are not limited to, the following two:

[0073] The first approach involves analyzing historically captured images and training a pre-built model using machine learning and deep learning algorithms to obtain an initial paradigm. Then, the initial paradigm is optimized using archived data generated through clustering. For example, the sub-terms and weights of the initial paradigm are continuously modified to obtain the final paradigm used for quality scoring.

[0074] Then, the image parsing operator is used to obtain the relevant attributes of the image (such as quality score, sharpness, elevation angle, side angle, depression angle, confidence level, length, width, whether a hat is worn, whether glasses are worn, etc.). For some non-numerical attributes (such as whether a hat is worn, whether glasses are worn, whether a mask is worn, whether bangs are worn, etc.), normalization processing is performed, and the image quality score is calculated for each image in the face image set based on the normalization processing result and other numerical attribute information.

[0075] The second method involves clustering historically captured images to generate multiple sample subsets, each corresponding to a person's identity, with each subset containing more than one image. Then, a face recognition model is used to obtain feature vectors from these historically captured images. Based on these feature vectors, the similarity distribution between the same person and the different persons is calculated for each image. The image quality score for each image is determined based on the distance between the similarity distributions. Finally, the pre-built model is trained using each image and its corresponding quality score to obtain a face image quality assessment model. This model is then used to score the image quality of the collected face image set.

[0076] In one possible implementation, high-quality image identifiers can be added to the images in the first image set. For example, images with image quality scores greater than a first preset threshold can be identified as "1", and images with image quality scores less than or equal to the first preset threshold can be identified as "0". Alternatively, the image quality score corresponding to each image can be used as the identifier for each image quality.

[0077] Step 102: Add identification information to each image in the first image set based on the static standard database;

[0078] The static standard database is used to store images of identity documents, such as ID cards, passports, and driver's licenses. Within the static standard database, corresponding image parsing interfaces can be called to obtain image attribute information, such as feature values, quality scores, location reliability, sharpness, eyeglass style, and hairstyle, and to extract other image information, such as the date the identity document was issued, the ID number, age, the image of the name on the ID card, gender, and address.

[0079] In the specific implementation process, the images in the first image set (e.g., the second image) are compared with the images in the static standard base library to obtain the similarity. The identity information of the first person whose similarity is higher than the second preset threshold is determined and the identity information of the first person is added to the second image.

[0080] For example, if the second preset threshold is 97%, after comparing the similarity of the second image in the first image set with the images in the static standard database, and the similarity between the second image and the image of person A in the static standard database is 97.3%, then the identity information corresponding to person A is added to the second image. The identity information can be at least one of the following: name, age, gender, ID number, identity certificate image, address, etc.

[0081] Step 103: Cluster the images in the face image set to generate multiple profiles;

[0082] In this embodiment of the application, the images in the collected face image set are clustered using face clustering technology to generate multiple profiles, with each profile corresponding to a person's identity.

[0083] In one possible implementation, after generating a file corresponding to each person's identity, the images in each file can be classified according to the acquisition angle using a classification recommendation algorithm based on image feature values. For example, front-facing facial images can be classified into one category, and side-facing facial images into another category. Centroids can be determined from each category for file search based on the acquired images. When determining centroids, images with added identity information are preferentially selected as centroids for the corresponding categories.

[0084] Step 104: Determine if each of the multiple files contains an image with added identification information;

[0085] Step 105: If the first file contains a first image with added identification information, then determine that the identification information of the first image is the identification information of the first file;

[0086] Step 106: Archive the identity of the first file based on the identity information.

[0087] In this embodiment of the application, when it is determined that there is a first image with added identity information in the first file, it indicates that the first image has been archived. At this time, the first file can be archived directly, and the images contained in the first file can be compared with the static standard database, thereby improving the efficiency of file archiving.

[0088] In one possible implementation, if there is no image with added identification information in the first file, a centroid corresponding to the first file is generated, the centroid is compared with a static standard base library to determine the identification information corresponding to the centroid, and the corresponding identification information is determined as the identification information of the first file, and the first file is archived according to the identification information.

[0089] In some other embodiments, after all the clustered files are archived, a new third image with added identity information can be obtained. It is determined whether there is a second file with the same identity information as the third image among the multiple archived files. If there is, the third image is added to the second file. If not, a new third file is created and the third image is added to the third file. The identity information of the third image is determined as the identity information of the third file.

[0090] In one possible implementation, if a second file exists among multiple archived files, after adding a third image to the second file, it can be determined whether the image quality of the third image is higher than the image quality of the centroid image in the corresponding category. If the image quality of the third image is higher than the image quality of the centroid image in the corresponding category, the third image is used as another centroid. When the number of other centroids reaches a threshold, the centroid of the corresponding category is re-determined. This can effectively reduce the operational burden and ensure operational efficiency.

[0091] For example, if the third image is a frontal image, after the third image is added to the second file, it can be classified into the frontal image category. If the image quality score of the third image is 92, which is higher than the image quality score of 90 for the centroid of the frontal image category in the second file, then the third image is used as another centroid. When the number of other centroids is higher than the threshold, a new centroid is selected from the other centroids as the centroid of the frontal image category in the second file.

[0092] In some other embodiments, considering that when clustering images in a face image set using face clustering technology, it is possible that face images of different people may be clustered into one set. For example, after clustering, the first file contains images of person A and person B. However, when archiving identities based on high-quality images, the identity information of the first file is determined to be the identity information corresponding to person A. That is, the first file is the image file set corresponding to person A. At this time, if the proportion of images that do not belong to person A in the first file is high, it will lead to identity archiving anomalies and cause centroid drift.

[0093] Therefore, after all the clustered archives are archived, relevant indicator values ​​of the archived archives can be obtained, such as the number of images, and a corresponding weight can be defined for each indicator value. When the calculation results of the relevant indicator values ​​meet the threshold, the archived archives can be merged with the corresponding historical archives. Alternatively, the threshold corresponding to each indicator value can be determined, and when the relevant indicator values ​​meet the corresponding thresholds, the archived archives can be merged with the corresponding historical archives.

[0094] For example, if the threshold for the number of images is 1000, the threshold for the gender ratio is 90%, and the threshold for the age is 85%, then if the number of images in the first file is 1100, it is determined whether the corresponding gender ratio and age ratio meet the corresponding thresholds. If they meet the corresponding thresholds, the first file is merged with the corresponding historical file.

[0095] In this way, when the number of images meets the corresponding threshold, and the number of images that are the same gender and age as the person corresponding to the first file reaches the corresponding threshold, it indicates that the proportion of images belonging to other people is small. At this time, other images have little impact on determining the centroid of the first file, thus effectively avoiding centroid drift. At the same time, by obtaining the historical files corresponding to the first file, the files that have been archived with the identity are merged with the corresponding historical files in an incremental manner, which can effectively avoid comparing with the full set of archived files each time, thereby effectively reducing the number of comparisons and improving the efficiency of identity archiving.

[0096] In the specific implementation process, prioritizing the archiving of high-quality images and directly archiving the files based on the identity information corresponding to the high-quality images can effectively improve the efficiency of image archiving. Furthermore, the use of identity information to attract new images to files that have already been archived can effectively reduce the probability of the same person corresponding to multiple files.

[0097] Based on the same inventive concept, embodiments of this application provide an identity archiving device capable of implementing the functions corresponding to the aforementioned identity archiving method. This identity archiving device can be a hardware structure, a software module, or a hardware structure plus a software module. The identity archiving device can be implemented using a chip system, which can consist of chips or include chips and other discrete components. Please refer to... Figure 2 As shown, the identity archiving device includes an acquisition module 201 and a processing module 202. Wherein:

[0098] The acquisition module 201 is used to acquire a first image set whose image quality is higher than a first preset threshold from the acquired face image set;

[0099] Processing module 202 is used to add identity information to each image in the first image set according to a static standard database; wherein, the static standard database is used to store identity verification images;

[0100] The processing module 202 is further configured to cluster the images in the face image set to generate multiple profiles; wherein each profile corresponds to a person's identity;

[0101] The processing module 202 is further configured to determine whether each of the plurality of files contains an image with added identification information;

[0102] The processing module 202 is further configured to determine, if there is a first image in the first file that has been added with identification information, that the identification information of the first image is the identification information of the first file; wherein, the first image belongs to the first image set;

[0103] The processing module 202 is further configured to archive the first file based on the identity information.

[0104] In one possible implementation, the acquisition module 201 is specifically used for:

[0105] After the processing module performs a quality score on each image in the face image set, it obtains the image quality score for each image in the face image set.

[0106] Obtain a first set of images whose image quality scores are higher than the first preset threshold.

[0107] In one possible implementation, the processing module 202 is specifically used for:

[0108] The similarity score is obtained by comparing the second image in the first image set with the images in the static standard base library.

[0109] Identify the identity information of the first person whose similarity exceeds a second preset threshold;

[0110] Add the identity information corresponding to the first person to the second image.

[0111] In one possible implementation, the processing module 202 is further configured to:

[0112] After the acquisition module 201 acquires the third image with added identity information, it determines whether there is a second file among the multiple archived files with the same identity information as the third image.

[0113] If it is determined that the second file exists among the multiple files that have been identified and archived, then the third image is added to the second file;

[0114] If it is determined that the second file does not exist among the multiple files that have been archived with identity verification, a third file is created, and the third image is added to the third file.

[0115] In one possible implementation, the processing module 202 is further configured to:

[0116] After the acquisition module 201 acquires historical files with the same identity information as the first file, it merges the first file and the historical files when it determines that the first file meets the preset conditions.

[0117] All relevant content of each step involved in the aforementioned embodiments of the identity archiving method can be referenced to the functional description of the corresponding functional module of the identity archiving device in the embodiments of this application, and will not be repeated here.

[0118] The module division in this embodiment is illustrative and represents only one logical functional division. In actual implementation, other division methods may be used. Furthermore, the functional modules in each embodiment of this application can be integrated into a single processor, exist as separate physical entities, or be integrated into a single module. The integrated modules described above can be implemented in hardware or as software functional modules.

[0119] Based on the same inventive concept, embodiments of this application provide an electronic device. Please refer to... Figure 3 As shown, the electronic device includes at least one processor 301 and a memory 302 connected to the at least one processor. In this embodiment, the specific connection medium between the processor 301 and the memory 302 is not limited. Figure 3 Taking the connection between processor 301 and memory 302 via bus 300 as an example, bus 300 in... Figure 3The connections between other components are indicated by thick lines and are for illustrative purposes only, not as limiting information. Bus 300 can be divided into address bus, data bus, control bus, etc., for ease of representation. Figure 3 The bus is represented by a single thick line, but this does not mean that there is only one bus or one type of bus.

[0120] In this embodiment of the application, the memory 302 stores instructions that can be executed by at least one processor 301. By executing the instructions stored in the memory 302, at least one processor 301 can perform the steps included in the aforementioned identity archiving method.

[0121] The processor 301 serves as the control center of the electronic device. It connects to various parts of the device via various interfaces and lines, and performs overall monitoring by running or executing instructions stored in the memory 302 and accessing data stored in the memory 302, thus controlling the various functions and processing data of the electronic device. Optionally, the processor 301 may include one or more processing units. The processor 301 may integrate an application processor and a modem processor. The application processor primarily handles the operating system and applications, while the modem processor primarily handles wireless communication. It is understood that the modem processor may not be integrated into the processor 301. In some embodiments, the processor 301 and the memory 302 may be implemented on the same chip; in other embodiments, they may be implemented on separate chips.

[0122] Processor 301 can be a general-purpose processor, such as a central processing unit (CPU), digital signal processor, application-specific integrated circuit, field-programmable gate array or other programmable logic device, discrete gate or transistor logic device, or discrete hardware component, capable of implementing or executing the methods, steps, and logic block diagrams disclosed in the embodiments of this application. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the identity archiving method disclosed in the embodiments of this application can be directly manifested as execution by a hardware processor, or execution by a combination of hardware and software modules within the processor.

[0123] Memory 302, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules. Memory 302 may include at least one type of storage medium, such as flash memory, hard disk, multimedia card, card-type memory, random access memory (RAM), static random access memory (SRAM), programmable read-only memory (PROM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), magnetic memory, magnetic disk, optical disk, etc. Memory 302 can be any other medium capable of carrying or storing desired program code in the form of instructions or data structures that can be accessed by a computer, but is not limited thereto. In the embodiments of this application, memory 302 may also be a circuit or any other device capable of implementing storage functions for storing program instructions and / or data.

[0124] By designing and programming the processor 301, the code corresponding to the identity archiving method described in the foregoing embodiments can be embedded into the chip, so that the chip can execute the steps of the aforementioned identity archiving method when running. How to design and program the processor 301 is a well-known technique to those skilled in the art, and will not be described in detail here.

[0125] Based on the same inventive concept, embodiments of this application also provide a computationally readable storage medium storing computer instructions that, when executed on a computer, cause the computer to perform the steps of the aforementioned identity archiving method.

[0126] In some possible implementations, various aspects of the identity archiving method provided in this application may also be implemented as a program product comprising program code that, when the program product is run on an electronic device, causes the detection device to perform the steps of the identity archiving method according to the various exemplary embodiments of this application described above.

[0127] Those skilled in the art will understand that embodiments of this application can be provided as methods, systems, or computer program products. Therefore, this application can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, this application can take the form of a computer program product embodied on one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0128] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program products according to this application. It should be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0129] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0130] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0131] Obviously, those skilled in the art can make various modifications and variations to this application without departing from the spirit and scope of this application. Therefore, if such modifications and variations fall within the scope of the claims of this application and their equivalents, this application also intends to include such modifications and variations.

Claims

1. An identity archiving method, characterized by, The method comprises: obtaining a first image set with image quality higher than a first preset threshold from a collected face image set; adding identity identification information to each image in the first image set according to a static standard library; wherein the static standard library is used to store identity proof images; clustering the images in the face image set to generate a plurality of archives; wherein each archive corresponds to a person identity; determining whether there is an image with added identity identification information in each archive in the plurality of archives; if there is a first image with added identity identification information in a first archive, determining that the identity identification information of the first image is the identity identification information of the first archive; wherein the first image belongs to the first image set; performing identity archiving on the first archive according to the identity identification information; obtaining at least one index value of the archived first archive, and performing archiving on the archived first archive and a corresponding historical archive according to the at least one index value; the at least one index value is used to indicate that the proportion of images belonging to the same identity in the archived first archive is greater than a threshold value.

2. The method of claim 1, wherein, The method comprises: scoring the quality of each image in the face image set to obtain the image quality score of each image in the face image set; obtaining a first image set with image quality score higher than the first preset threshold.

3. The method of claim 1, wherein, The method comprises: comparing the similarity of a second image in the first image set with images in the static standard library to obtain a similarity; determining the identity identification information corresponding to a first person with a similarity higher than a second preset threshold; adding the identity identification information corresponding to the first person to the second image.

4. The method of claim 1, wherein, The method further comprises: obtaining a third image with added identity identification information; determining whether there is a second archive in the plurality of archives with the same identity identification information as the third image; if it is determined that there is the second archive in the plurality of archives with identity identification, adding the third image to the second archive; if it is determined that there is no second archive in the plurality of archives with identity identification, adding a third archive and adding the third image to the third archive.

5. An identity archival apparatus, comprising: The device comprises: an obtaining module, configured to obtain a first image set with image quality higher than a first preset threshold from a collected face image set; a processing module, configured to add identity identification information to each image in the first image set according to a static standard library; wherein the static standard library is used to store identity proof images; the processing module is further configured to cluster the images in the face image set to generate a plurality of archives; wherein each archive corresponds to a person identity; the processing module is further configured to determine whether there is an image with added identity identification information in each archive in the plurality of archives; the processing module is further configured to determine whether there is a first image with added identity identification information in a first archive. The processing module is further configured to determine, if there is a first image in the first file that has been added with identification information, that the identification information of the first image is the identification information of the first file; wherein, the first image belongs to the first image set; The processing module is further configured to archive the first file based on the identity information; The acquisition module is also used to acquire at least one index value of the archived first file; The processing module is further configured to merge the archived first file with the corresponding historical file according to the at least one indicator value, wherein the at least one indicator value is used to indicate that the proportion of images belonging to the same identity in the archived first file is greater than a threshold.

6. The apparatus of claim 5, wherein, The acquisition module is specifically used for: After the processing module performs a quality score on each image in the face image set, it obtains the image quality score for each image in the face image set. Obtain a first set of images whose image quality scores are higher than the first preset threshold.

7. The apparatus of claim 5, wherein, The processing module is specifically used for: The similarity score is obtained by comparing the second image in the first image set with the images in the static standard base library. Identify the identity information of the first person whose similarity exceeds a second preset threshold; Add the identity information corresponding to the first person to the second image.

8. An electronic device, comprising: include: Memory, used to store program instructions; A processor is configured to invoke program instructions stored in the memory and execute the steps of the method according to any one of claims 1-4.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, the computer program including program instructions that, when executed by a computer, cause the computer to perform the method as described in any one of claims 1-4.

Images