A method, device and storage medium for dynamically constructing a face feature database

Abstract

A method, device, and storage medium for dynamically constructing a face feature database. The method includes the steps of: obtaining a basic face feature library; obtaining a first face picture; generating a first fused feature vector according to the first face picture; generating a first dynamic face feature database according to the basic face feature library and the first fused feature vector; obtaining a second face picture; generating a second fused feature vector according to the second face picture; and generating a second dynamic face feature database according to the first dynamic face feature database and the second fused feature vector. The method, device, and storage medium for dynamically constructing a face feature database provided in this application meet the new requirements for constructing a face feature database in the current mobile Internet environment, reduce the impact brought by the input of person pictures in different input devices and input environments, improve the recognition accuracy of the face recognition model, and provide support for the further engineering implementation of the face recognition function.

Description

Technical Field

[0001] The present invention belongs to the technical field of facial feature databases, and in particular relates to a method, device and storage medium for dynamically constructing a facial feature database. Background Art

[0002] Most current facial feature libraries generate character features based on a single frontal face image, which results in very high requirements for frontal face images when entering facial database information, and is greatly affected by the entry device and environment. In the past, when constructing facial feature libraries, the selection of character images to be entered first required ensuring that the resolution and encoding and decoding methods of the images were unified, and then selecting images that could show individual differences in the characters, so that the feature vectors constructed from different characters could be as non-overlapping as possible, thereby improving the differentiation of facial features.

[0003] Ensuring the uniformity of the input device and environment can often provide better input results. However, with the development of mobile devices, camera technology has developed rapidly, and directly deploying high-definition camera devices on mobile devices has become the mainstream development direction. Mobile devices have gradually acquired the hardware capabilities to input facial information, and the input of facial feature information has changed from unified input to autonomous input. By using the camera of a mobile device and the guidance of some software, the input of facial information can be completed, which simplifies and facilitates the input work on the one hand, and ensures the privacy and security of user information on the other.

[0004] Different recording devices lead to different resolutions, quality, and encoding and decoding methods of the recorded images, and different recording environments lead to different ambient brightness, angles, and degrees of occlusion. In the past, the construction of face feature libraries relied on the input of a single image-like information, which was unable to process the image standards and information generated in the ever-changing mobile Internet scenario. Summary of the invention

[0005] In view of the above problems, the present invention provides a method, device and storage medium for dynamically constructing a facial feature database that overcomes the above problems or at least partially solves the above problems.

[0006] In order to solve the above technical problems, the present invention provides a method for dynamically constructing a facial feature database, the method comprising the steps of:

[0007] Get the basic facial feature library;

[0008] Get the first face image;

[0009] generating a first fused feature vector according to the first face image;

[0010] Generate a first dynamic facial feature database according to the basic facial feature database and the first fused feature vector;

[0011] Obtain a second face image;

[0012] Generate a second fusion feature vector according to the second face image;

[0013] Generate a second dynamic face feature database according to the first dynamic face feature database and the second fusion feature vector.

[0014] Preferably, the obtaining of the basic face feature library includes the steps of:

[0015] Create an empty database;

[0016] Initialize the database;

[0017] Obtain the identity address and face image data;

[0018] Create a mapping between the identity address and the face image data;

[0019] Store the mapping into the control database and obtain the basic face feature library.

[0020] Preferably, the generating of the first fusion feature vector according to the first face image includes the steps of:

[0021] Obtain the spatial dimension face image in the first face image;

[0022] Extract the spatial dimension feature vector of the spatial dimension face image;

[0023] Summarize all the spatial dimension feature vectors and obtain a spatial dimension feature vector set;

[0024] Evaluate all the spatial dimension feature vectors and determine the corresponding spatial dimension weights;

[0025] Combine all the spatial dimension feature vectors corresponding to the same first identity address and obtain a spatial dimension fusion feature vector.

[0026] Preferably, the generating of the first fusion feature vector according to the first face image includes the steps of:

[0027] Obtain the temporal dimension face image in the first face image;

[0028] Extract the temporal dimension feature vector of the temporal dimension face image;

[0029] Summarize all the temporal dimension feature vectors and obtain a temporal dimension feature vector set;

[0030] Evaluate all the temporal dimension feature vectors and determine the corresponding temporal dimension weights;

[0031] Combine all the time dimension feature vectors corresponding to the same first identity address to obtain a time dimension fusion feature vector.

[0032] Preferably, the generating the first dynamic face feature database according to the basic face feature library and the first fusion feature vector includes the steps of:

[0033] Obtain the spatial dimension fusion feature vector in the first fusion feature vector;

[0034] Obtain the basic face feature library;

[0035] Use the spatial dimension fusion feature vector to optimize the basic face feature library and obtain a spatial dimension face feature database;

[0036] Obtain the time dimension fusion feature vector in the first fusion feature vector;

[0037] Obtain the spatial dimension face feature database;

[0038] Use the time dimension fusion feature vector to optimize the spatial dimension face feature database and obtain the first dynamic face feature database.

[0039] Preferably, the generating the second fusion feature vector according to the second face image includes the steps of:

[0040] Obtain the second face image;

[0041] Extract the second face feature vector of the second face image;

[0042] Summarize all the second face feature vectors to obtain a second face feature vector set;

[0043] Evaluate all the second face feature vectors and determine the corresponding second face weight;

[0044] Combine all the second face feature vectors corresponding to the same second identity address to obtain a second face fusion feature vector.

[0045] Preferably, the generating the second dynamic face feature database according to the first dynamic face feature database and the second fusion feature vector includes the steps of:

[0046] Obtain the first identity address of the first dynamic face feature database;

[0047] Obtain the second identity address corresponding to the second fusion feature vector;

[0048] Judge whether the first identity address and the second identity address are the same;

[0049] If so, optimize the first dynamic face feature database using the first fusion feature vector corresponding to the first identity address;

[0050] If so, optimize the first dynamic face feature database using the second fusion feature vector.

[0051] This application also provides a device for dynamically constructing a face feature database, and the device includes:

[0052] A basic face feature library acquisition module, configured to acquire a basic face feature library;

[0053] A first face image acquisition module, configured to acquire a first face image;

[0054] A first fusion feature vector generation module, configured to generate a first fusion feature vector according to the first face image;

[0055] A first dynamic face feature database generation module, configured to generate a first dynamic face feature database according to the basic face feature library and the first fusion feature vector;

[0056] A second face image acquisition module, configured to acquire a second face image;

[0057] A second fusion feature vector generation module, configured to generate a second fusion feature vector according to the second face image;

[0058] A second dynamic face feature database generation module, configured to generate a second dynamic face feature database according to the first dynamic face feature database and the second fusion feature vector.

[0059] This application also provides an electronic device, and the electronic device includes:

[0060] At least one processor; and,

[0061] A memory communicatively connected to the at least one processor; wherein,

[0062] The memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute any one of the foregoing face feature database dynamic construction methods.

[0063] This application also provides a non-transitory computer-readable storage medium, and the non-transitory computer-readable storage medium stores computer instructions for causing the computer to execute any one of the foregoing face feature database dynamic construction methods.

[0064] One or more technical solutions in the embodiments of the present invention have at least the following technical effects or advantages: A method, device, and storage medium for dynamically constructing a face feature database provided by the present application meet the new requirements for constructing a face feature database in the current mobile Internet environment, reduce the impact of input of person pictures in different input devices and input environments, improve the recognition accuracy of a face recognition model, and provide support for further engineering implementation of the face recognition function. BRIEF DESCRIPTION OF THE DRAWINGS

[0065] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following will briefly introduce the drawings required for description in the embodiments. Obviously, the following described drawings are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0066] Figure 1 is a schematic flowchart of a method for dynamically constructing a face feature database provided by the present invention;

[0067] Figure 2 is a schematic structural diagram of a device for dynamically constructing a face feature database provided by the present invention;

[0068] Figure 3 is a schematic structural diagram of an electronic device provided by the present invention;

[0069] Figure 4 is a schematic structural diagram of a non-transitory computer-readable storage medium provided by the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0070] The following will specifically describe the present invention in combination with specific embodiments and examples, and the advantages and various effects of the present invention will be presented more clearly therefrom. Those skilled in the art should understand that these specific embodiments and examples are used to illustrate the present invention, rather than to limit the present invention.

[0071] Throughout the specification, unless otherwise specifically stated, the terms used herein should be understood as having the meaning commonly used in the art. Therefore, unless otherwise defined, all technical and scientific terms used herein have the same meaning as the general understanding of those skilled in the art to which the present invention belongs. In case of contradiction, this specification shall prevail.

[0072] Unless otherwise specifically stated, all raw materials, reagents, instruments, equipment, etc. used in the present invention can be obtained through market purchase or can be prepared by existing methods.

[0073] As Figure 1 , in the embodiments of the present application, the present invention provides a method for dynamically constructing a face feature database, and the method includes the steps:

[0074] S1: Obtain the basic face feature library;

[0075] In the embodiment of the present application, the obtaining of the basic face feature library includes the steps of:

[0076] Create an empty database;

[0077] Initialize the database;

[0078] Obtain the identity address and face image data;

[0079] Create a mapping between the identity address and the face image data;

[0080] Store the mapping into the control database to obtain the basic face feature library.

[0081] In the embodiment of the present application, the basic face feature library can be created through the following steps: first, create an empty database, then clear and initialize the database, and then obtain the identity address and face image data. The identity address (ID) represents the position of the corresponding face image data in the basic face database, and is in one-to-one correspondence with the corresponding face image data. Through the identity address (ID), the corresponding face image data can be directly searched in the basic face database. For example, the identity address of A is ID(A), and the corresponding face image data is Face(A).

[0082] S2: Obtain the first face image;

[0083] In the embodiment of the present application,

[0084] S3: Generate a first fusion feature vector according to the first face image;

[0085] In the embodiment of the present application, the generating of the first fusion feature vector according to the first face image includes the steps of:

[0086] Obtain the spatial dimension face image in the first face image;

[0087] Extract the spatial dimension feature vector of the spatial dimension face image;

[0088] Summarize all the spatial dimension feature vectors to obtain a spatial dimension feature vector set;

[0089] Evaluate all the spatial dimension feature vectors and determine the corresponding spatial dimension weights;

[0090] Combine all the spatial dimension feature vectors corresponding to the same first identity address to obtain a spatial dimension fusion feature vector.

[0091] In the embodiment of the present application, a first fusion feature vector can be generated in the spatial dimension according to the first face image. Specifically, first, obtain the spatial dimension face images in the first face image (such as spatial dimension face images under different spatial dimensions of input devices, input environments, etc.), then extract the spatial dimension feature vectors of the spatial dimension face images (such as device feature vectors corresponding to the input device, environmental feature vectors corresponding to the input environment), then summarize all the spatial dimension feature vectors to obtain a set of spatial dimension feature vectors, and then evaluate and select these spatial dimension feature vectors, evaluate all the spatial dimension feature vectors and determine the corresponding spatial dimension weights, and construct the fusion of these feature information without losing the feature information carried by different feature vectors, so as to construct the face feature data content of the corresponding person, combine all the spatial dimension feature vectors corresponding to the same first identity address and obtain the spatial dimension fusion feature vector.

[0092] In the embodiment of the present application, generating the first fusion feature vector according to the first face image includes the steps of:

[0093] Obtain the temporal dimension face image in the first face image;

[0094] Extract the temporal dimension feature vector of the temporal dimension face image;

[0095] Summarize all the temporal dimension feature vectors to obtain a set of temporal dimension feature vectors;

[0096] Evaluate all the temporal dimension feature vectors and determine the corresponding temporal dimension weights;

[0097] Combine all the temporal dimension feature vectors corresponding to the same first identity address and obtain the temporal dimension fusion feature vector.

[0098] In the embodiment of the present application, a first fusion feature vector can be generated in the temporal dimension according to the first face image. Specifically, first, obtain the temporal dimension face images in the first face image (such as temporal dimension face images under different temporal dimensions such as different input times), then extract the temporal dimension feature vectors of the temporal dimension face images (such as temporal feature vectors corresponding to the input time), then summarize all the temporal dimension feature vectors to obtain a set of temporal dimension feature vectors, and then evaluate and select these temporal dimension feature vectors, evaluate all the temporal dimension feature vectors and determine the corresponding temporal dimension weights, and dynamically construct the face feature information that best matches the user's characteristics at present, so as to combine all the temporal dimension feature vectors corresponding to the same first identity address and obtain the temporal dimension fusion feature vector.

[0099] S4: Generate a first dynamic face feature database according to the basic face feature library and the first fusion feature vector;

[0100] In an embodiment of the present application, the generation of the first dynamic face feature database according to the basic face feature library and the first fusion feature vector includes the steps of:

[0101] Obtain the spatial dimension fusion feature vector in the first fusion feature vector;

[0102] Obtain the basic face feature library;

[0103] Optimize the basic face feature library using the spatial dimension fusion feature vector and obtain the spatial dimension face feature database;

[0104] Obtain the temporal dimension fusion feature vector in the first fusion feature vector;

[0105] Obtain the spatial dimension face feature database;

[0106] Optimize the spatial dimension face feature database using the temporal dimension fusion feature vector and obtain the first dynamic face feature database.

[0107] In an embodiment of the present application, when generating the first dynamic face feature database according to the basic face feature library and the first fusion feature vector, first obtain the basic face feature library obtained in step S1, and then sequentially optimize the basic face feature library using the spatial dimension fusion feature vector and the temporal dimension fusion feature vector, and finally the first dynamic face feature database can be obtained.

[0108] S5: Obtain a second face picture;

[0109] S6: Generate a second fusion feature vector according to the second face picture;

[0110] In an embodiment of the present application, the generation of the second fusion feature vector according to the second face picture includes the steps of:

[0111] Obtain the second face picture;

[0112] Extract the second face feature vector of the second face picture;

[0113] Summarize all the second face feature vectors and obtain a second face feature vector set;

[0114] Evaluate all the second face feature vectors and determine the corresponding second face weights;

[0115] Combine all the second face feature vectors corresponding to the same second identity address and obtain a second face fusion feature vector.

[0116] In the embodiment of the present application, the step of generating the second fusion feature vector according to the second face picture may specifically refer to step S3, which will not be elaborated here.

[0117] S7: Generate a second dynamic face feature database according to the first dynamic face feature database and the second fusion feature vector.

[0118] In the embodiment of the present application, the generating of the second dynamic face feature database according to the first dynamic face feature database and the second fusion feature vector includes the steps of:

[0119] Obtain the first identity address of the first dynamic face feature database;

[0120] Obtain the second identity address corresponding to the second fusion feature vector;

[0121] Determine whether the first identity address and the second identity address are the same;

[0122] If so, optimize the first dynamic face feature database with the first fusion feature vector corresponding to the first identity address;

[0123] If so, optimize the first dynamic face feature database with the second fusion feature vector.

[0124] In the embodiment of the present application, the first face picture stored in the first dynamic face feature database corresponds to the first identity address, and the second face picture corresponding to the second fusion feature vector corresponds to the second identity address. When the first identity address is the same as the second identity address, it can be analyzed that the second face picture has been previously stored in the first dynamic face feature database. At this time, directly optimize the first dynamic face feature database with the first fusion feature vector corresponding to the first identity address, and the optimization result is the second dynamic face feature database; when the first identity address is different from the second identity address, it can be analyzed that the second face picture has not been previously stored in the first dynamic face feature database. At this time, optimize the first dynamic face feature database with the second fusion feature vector, and the optimization result is the second dynamic face feature database.

[0125] Such as Figure 2 , the present application also provides a device for dynamically constructing a face feature database, and the device includes:

[0126] A basic face feature library acquisition module 10, configured to acquire a basic face feature library;

[0127] A first face picture acquisition module 20, configured to acquire a first face picture;

[0128] The first fusion feature vector generation module 30 is configured to generate a first fusion feature vector according to the first face image;

[0129] The first dynamic face feature database generation module 40 is configured to generate a first dynamic face feature database according to the basic face feature library and the first fusion feature vector;

[0130] The second face image acquisition module 50 is configured to acquire a second face image;

[0131] The second fusion feature vector generation module 60 is configured to generate a second fusion feature vector according to the second face image;

[0132] The second dynamic face feature database generation module 70 is configured to generate a second dynamic face feature database according to the first dynamic face feature database and the second fusion feature vector.

[0133] A face feature database dynamic construction device provided by the present application can execute a face feature database dynamic construction method provided by the above steps.

[0134] Next, refer to Figure 3 , which shows a schematic structural diagram of an electronic device 100 suitable for implementing the embodiments of the present disclosure. The electronic device in the embodiments of the present disclosure may include, but is not limited to, mobile terminals such as mobile phones, laptop computers, digital broadcast receivers, PDAs (Personal Digital Assistants), PADs (Tablet Computers), PMPs (Portable Multimedia Players), vehicle terminals (such as vehicle navigation terminals), etc., and fixed terminals such as digital TVs, desktop computers, etc. Figure 3 The electronic device shown is only an example and should not impose any limitations on the functions and usage scopes of the embodiments of the present disclosure.

[0135] As Figure 3 shown, the electronic device 100 may include a processing device (such as a central processing unit, a graphics processing unit, etc.) 101, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 102 or a program loaded from a storage device 108 into a random access memory (RAM) 103. In the RAM 103, various programs and data required for the operation of the electronic device 100 are also stored. The processing device 101, the ROM 102, and the RAM 103 are connected to each other through a bus 104. An input / output (I / O) interface 105 is also connected to the bus 104.

[0136] Typically, the following devices can be connected to the I / O interface 105: an input device 106 including, for example, a touch screen, a touchpad, a keyboard, a mouse, an image sensor, a microphone, an accelerometer, a gyroscope, etc.; an output device 107 including, for example, a liquid crystal display (LCD), a speaker, a vibrator, etc.; a storage device 108 including, for example, a magnetic tape, a hard disk, etc.; and a communication device 109. The communication device 109 can allow the electronic device 100 to communicate with other devices wirelessly or wiredly to exchange data. Although the electronic device 100 with various devices is shown in the figure, it should be understood that it is not required to implement or have all the shown devices. More or fewer devices can be alternatively implemented or had.

[0137] In particular, according to an embodiment of the present disclosure, the process described above with reference to the flowchart can be implemented as a computer software program. For example, an embodiment of the present disclosure includes a computer program product, which includes a computer program carried on a computer-readable medium, and the computer program contains program codes for executing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network through the communication device 109, or installed from the storage device 108, or installed from the ROM 102. When the computer program is executed by the processing device 101, the above functions defined in the method of the embodiment of the present disclosure are executed.

[0138] Next, refer to Figure 4 , which shows a schematic structural diagram of a computer-readable storage medium suitable for implementing the embodiment of the present disclosure. The computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, it can implement the method for dynamically constructing a face feature database as described in any one of the above.

[0139] It should be noted that the above-mentioned computer-readable medium in the present disclosure can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. The computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of the computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In the present disclosure, the computer-readable storage medium can be any tangible medium that contains or stores a program, and this program can be used by or in combination with an instruction execution system, apparatus, or device. In the present disclosure, the computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. The computer-readable signal medium can also be any computer-readable medium other than the computer-readable storage medium, and this computer-readable signal medium can send, propagate, or transmit a program for use by or in combination with an instruction execution system, apparatus, or device. The program code contained on the computer-readable medium can be transmitted by any appropriate medium, including but not limited to: wires, optical cables, RF (radio frequency), etc., or any suitable combination of the above.

[0140] The above-mentioned computer-readable medium can be included in the above-mentioned electronic device; it can also exist separately without being assembled into the electronic device.

[0141] The above-mentioned computer-readable medium carries one or more programs. When the one or more programs are executed by the electronic device, the electronic device is caused to: obtain at least two Internet protocol addresses; send a node evaluation request including the at least two Internet protocol addresses to a node evaluation device, where the node evaluation device selects an Internet protocol address from the at least two Internet protocol addresses and returns it; receive the Internet protocol address returned by the node evaluation device; where the obtained Internet protocol address indicates an edge node in a content distribution network.

[0142] Alternatively, the computer-readable medium carries one or more programs that, when executed by the electronic device, cause the electronic device to: receive a node evaluation request including at least two Internet Protocol addresses; select an Internet Protocol address from the at least two Internet Protocol addresses; return the selected Internet Protocol address; wherein the received Internet Protocol address indicates an edge node in a content delivery network.

[0143] Computer program code for carrying out operations of the present disclosure may be written in one or more programming languages or combinations thereof. The programming languages include object-oriented programming languages such as Java, Smalltalk, C++, and also include conventional procedural programming languages such as the "C" language or similar programming languages. The program code may execute entirely on the user's computer, partly on the user's computer, as a stand-alone software package, partly on the user's computer and partly on a remote computer, or entirely on the remote computer or server. In the case of a remote computer, the remote computer may be connected to the user's computer through any type of network, including a local area network (LAN) or a wide area network (WAN), or may be connected to an external computer (e.g., through the Internet using an Internet service provider).

[0144] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of the present disclosure. In this regard, each block in the flowchart or block diagram may represent a module, a program segment, or a part of code that contains one or more executable instructions for implementing a specified logical function. It should also be noted that, in some alternative implementations, the functions noted in the blocks may occur in a different order than noted in the drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, or they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and combinations of blocks in the block diagram and / or flowchart, may be implemented by a dedicated hardware-based system that performs the specified functions or operations, or may be implemented by a combination of dedicated hardware and computer instructions.

[0145] The units described in the embodiments of the present disclosure may be implemented in software or in hardware. Wherein, the name of the unit does not constitute a limitation to the unit itself in some cases. For example, the first acquisition unit may also be described as "the unit for acquiring at least two Internet Protocol addresses".

[0146] A method, device, and storage medium for dynamically constructing a face feature database provided by this application meet the new requirements for constructing a face feature database in the current mobile Internet environment, reduce the impact brought by the input of person pictures in different input devices and input environments, improve the recognition accuracy of the face recognition model, and provide support for the further engineering implementation of the face recognition function.

[0147] It should be understood that the above specific embodiments of the present invention are only used for exemplary illustration or explanation of the principles of the present invention, and do not constitute a limitation on the present invention. Therefore, any modifications, equivalent replacements, improvements, etc. made without departing from the spirit and scope of the present invention shall be included within the protection scope of the present invention. In addition, the appended claims of the present invention are intended to cover all changes and modification examples falling within the scope and boundaries of the appended claims, or equivalent forms of such scope and boundaries.

Claims

1. A method for dynamically constructing a human face feature database, characterized in that, The method includes the steps of: Obtain a basic face feature library; Obtain a first face image; Generate a first fusion feature vector according to the first face image; Generate a first dynamic face feature database according to the basic face feature library and the first fusion feature vector; Obtain a second face image; Generate a second fusion feature vector according to the second face image; Generate a second dynamic face feature database according to the first dynamic face feature database and the second fusion feature vector; The step of generating a first dynamic face feature database according to the basic face feature library and the first fusion feature vector includes the steps of: Obtain the spatial dimension fusion feature vector in the first fusion feature vector; Obtain the basic face feature library; Optimize the basic face feature library using the spatial dimension fusion feature vector and obtain a spatial dimension face feature database; Obtain the temporal dimension fusion feature vector in the first fusion feature vector; Obtain the spatial dimension face feature database; Optimize the spatial dimension face feature database using the temporal dimension fusion feature vector and obtain a first dynamic face feature database; The step of generating a second dynamic face feature database according to the first dynamic face feature database and the second fusion feature vector includes the steps of: Obtain the first identity address of the first dynamic face feature database; Obtain the second identity address corresponding to the second fusion feature vector; Determine whether the first identity address and the second identity address are the same; If so, optimize the first dynamic face feature database using the first fusion feature vector corresponding to the first identity address; If so, optimize the first dynamic face feature database using the second fusion feature vector.

2. The method for dynamically constructing a face feature database according to claim 1, characterized in that The step of obtaining a basic face feature library includes the steps of: Create an empty database; Initialize the database; Obtain identity addresses and face image data; Create a mapping between the identity addresses and the face image data; Store the mapping in the control database and obtain the basic face feature library.

3. The method for dynamically constructing a face feature database according to claim 1, wherein The step of generating a first fusion feature vector according to the first face image includes the steps of: Obtain the spatial dimension face image in the first face image; Extract the spatial dimension feature vector of the spatial dimension face image; Summarize all the spatial dimension feature vectors and obtain a spatial dimension feature vector set; Evaluate all the spatial dimension feature vectors and determine the corresponding spatial dimension weights; Combine all the spatial dimension feature vectors corresponding to the same first identity address and obtain a spatial dimension fusion feature vector.

4. The method for dynamically constructing a face feature database according to claim 1, wherein The step of generating a first fusion feature vector according to the first face image includes the steps of: Obtain the temporal dimension face image in the first face image; Extract the temporal dimension feature vector of the temporal dimension face image; Summarize all the temporal dimension feature vectors and obtain a temporal dimension feature vector set; Evaluate all the temporal dimension feature vectors and determine the corresponding temporal dimension weights; Combine all the temporal dimension feature vectors corresponding to the same first identity address and obtain a temporal dimension fusion feature vector.

5. The method for dynamically constructing a face feature database according to claim 1, wherein Said generating a second fusion feature vector according to the second face picture includes the steps of: Obtaining the second face picture; Extracting a second face feature vector of the second face picture; Summarizing all the second face feature vectors and obtaining a second face feature vector set; Evaluating all the second face feature vectors and determining corresponding second face weights; Combining all the second face feature vectors corresponding to the same second identity address and obtaining a second face fusion feature vector.

6. A face feature database dynamic construction device for implementing the method according to any one of claims 1-5, characterized in that, The device includes: A basic face feature library obtaining module, configured to obtain a basic face feature library; A first face picture obtaining module, configured to obtain a first face picture; A first fusion feature vector generating module, configured to generate a first fusion feature vector according to the first face picture; A first dynamic face feature database generating module, configured to generate a first dynamic face feature database according to the basic face feature library and the first fusion feature vector; A second face picture obtaining module, configured to obtain a second face picture; A second fusion feature vector generating module, configured to generate a second fusion feature vector according to the second face picture; A second dynamic face feature database generating module, configured to generate a second dynamic face feature database according to the first dynamic face feature database and the second fusion feature vector.

7. An electronic device, characterized in that, The electronic device includes: At least one processor; and, A memory communicatively connected to the at least one processor; wherein, The memory stores instructions executable by the at least one processor, and when the instructions are executed by the at least one processor, the at least one processor is enabled to execute the face feature database dynamic construction method according to any one of the preceding claims 1-5.

8. A non-transitory computer-readable storage medium, the non-transitory computer-readable storage medium stores computer instructions, and the computer instructions are used to cause the computer to execute the face feature database dynamic construction method according to any one of the preceding claims 1-5.

Images