Personnel identification method and device, electronic equipment and storage medium

Abstract

Embodiments of the present application disclose a personnel identification method and device, electronic equipment and storage medium, belonging to the technical field of biometric identification. The personnel identification method comprises: acquiring a biometric image of a person to be identified; performing 1:N comparison on the biometric image by using a first algorithm; if a matching person is searched in the 1:N comparison, performing 1:1 comparison on a preset number of persons in the matching person with a high ranking by using a second algorithm, wherein the identification speed of the first algorithm is higher than that of the second algorithm but the identification accuracy of the first algorithm is lower than that of the second algorithm; and if the 1:1 comparison is passed, the personnel identification is passed. Embodiments of the present application have fast identification speed and high identification accuracy.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of biometric identification, in particular to a person identification method and device, electronic equipment and storage medium. BACKGROUND

[0002] In a strict security check scene, on the one hand, it is required to quickly identify the personnel to avoid congestion at the gate, and on the other hand, it is required to prevent dangerous situations caused by misidentification.

[0003] In the existing gate technology, if an algorithm with fast recognition speed is used, there is a problem of high misidentification rate; if an algorithm with high recognition accuracy is used, it is easy to cause slow recognition speed, unable to respond in seconds, and prone to cause congestion of people flow at the gate, so as to be unable to adapt to the gate security check scene with large flow of people. SUMMARY

[0004] The technical problem to be solved by the embodiments of the present application is to provide a person identification method and device with fast recognition speed and high accuracy, electronic equipment and storage medium.

[0005] To solve the above technical problem, the technical solutions of the embodiments of the present application are as follows:

[0006] On the one hand, a person identification method is provided, comprising:

[0007] obtaining a biometric image of a person to be identified;

[0008] performing 1:N comparison on the biometric image by using a first algorithm;

[0009] if a matching person is searched in the 1:N comparison, performing 1:1 comparison on a preset number of persons with high ranking in the matching person by using a second algorithm, wherein the recognition speed of the first algorithm is higher than that of the second algorithm but the recognition accuracy of the first algorithm is lower than that of the second algorithm;

[0010] if the 1:1 comparison is passed, the person identification is passed.

[0011] In some embodiments of the present application, the 1:N comparison on the biometric image by using the first algorithm comprises:

[0012] extracting biometric features of the biometric image by using the first algorithm to obtain first biometric features;

[0013] performing 1:N comparison on the first biometric features and biometric feature templates of persons stored in a database and obtained by the first algorithm.

[0014] In some embodiments of the present application, if a matching person is searched in the 1:N comparison, performing 1:1 comparison on a preset number of persons with high ranking in the matching person by using a second algorithm comprises:

[0015] If a matching person is searched, a biometric feature template corresponding to a person ranked first in the matching person obtained by the second algorithm is acquired from the database;

[0016] A biometric feature of the biometric feature image is extracted by using the second algorithm to obtain a second biometric feature;

[0017] The biometric feature template corresponding to the person ranked first in the matching person obtained by the second algorithm is compared with the second biometric feature, and if the comparison passes, the person recognition passes.

[0018] In some embodiments of the present application, the comparison of the biometric feature template corresponding to the person ranked first in the matching person obtained by the second algorithm and the second biometric feature, and if the comparison passes, the person recognition passes, includes:

[0019] If the comparison does not pass, a biometric feature template corresponding to a person ranked next in the matching person obtained by the second algorithm is acquired from the database;

[0020] The biometric feature template corresponding to the person ranked next in the matching person obtained by the second algorithm is compared with the second biometric feature, and if the comparison passes, the person recognition passes, and if the comparison does not pass, the previous step is returned until the person recognition passes or the persons ranked in the front of the matching person are traversed.

[0021] In another aspect, a person recognition device is provided, including:

[0022] An acquisition module is configured to acquire a biometric feature image of a person to be recognized;

[0023] A first comparison module is configured to perform 1:N comparison on the biometric feature image by using a first algorithm;

[0024] A second comparison module is configured to perform 1:1 comparison on persons ranked in the front of a matching person by using a second algorithm if a matching person is searched in the 1:N comparison, wherein the recognition speed of the first algorithm is higher than that of the second algorithm, but the recognition accuracy of the first algorithm is lower than that of the second algorithm;

[0025] A passing module is configured to pass the person recognition if the 1:1 comparison passes.

[0026] In still another aspect, an electronic device is provided, which includes a housing, a processor, a memory, a circuit board and a power supply circuit, wherein the circuit board is disposed inside a space enclosed by the housing, the processor and the memory are arranged on the circuit board; the power supply circuit is configured to supply power to each circuit or device of the electronic device; the memory is configured to store executable program codes; and the processor is configured to run a program corresponding to the executable program codes by reading the executable program codes stored in the memory, and execute any of the above methods.

[0027] In still another aspect, a computer readable storage medium is provided, which stores one or more programs executable by one or more processors to implement any of the above methods.

[0028] In still another aspect, a personnel identification device is provided, which includes a device body and an edge computing terminal connected to the device body, wherein:

[0029] The device body is configured to acquire a biometric image of a to-be-identified person;

[0030] The edge computing terminal is configured to perform 1:N matching on the biometric image by using a first algorithm; if a matching person is searched in the 1:N matching, then 1:1 matching is performed on a preset number of persons with a high ranking in the matching person by using a second algorithm, wherein the identification speed of the first algorithm is higher than that of the second algorithm but the identification accuracy of the first algorithm is lower than that of the second algorithm; and if the 1:1 matching is passed, the personnel identification is passed.

[0031] The device body is further configured to give a corresponding instruction after the personnel identification is passed.

[0032] In some embodiments of the present application, the device body is configured to acquire a biometric image of a to-be-identified person, and perform biometric live detection, biometric angle detection and / or biometric quality detection.

[0033] The device body is further configured to give a corresponding instruction after the personnel identification is passed and each of the biometric detections is passed.

[0034] In some embodiments of the present application, the biometric image is a face image, and / or the corresponding instruction is a gate opening instruction.

[0035] The embodiments of the present application have the following beneficial effects:

[0036] The personnel identification method, device, electronic equipment and storage medium provided by the embodiment of the present application first acquire a biological feature image of a to-be-identified person, then perform 1:N comparison on the biological feature image by using a first algorithm, and then if a matching person is searched in the 1:N comparison, perform 1:1 comparison on a preset number of persons in the matching person by using a second algorithm, wherein the identification speed of the first algorithm is higher than that of the second algorithm but the identification accuracy of the first algorithm is lower than that of the second algorithm, and finally if the 1:1 comparison is passed, the personnel identification is passed. In this way, the embodiment of the present application uses two algorithms to jointly compare and decide, the first algorithm with fast identification speed is used as primary authentication, and the second algorithm with high identification accuracy is used as secondary authentication, so that the whole scheme has the advantages of fast identification speed of the first algorithm and high identification accuracy of the second algorithm, so as to greatly reduce the false recognition rate and improve the identification speed. BRIEF DESCRIPTION OF DRAWINGS

[0037] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or the prior art description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative labor on the basis of the drawings shown.

[0038] Figure 1 Flowchart of an embodiment of the personnel identification method of the present application;

[0039] Figure 2 Flowchart of another embodiment of the personnel identification method of the present application;

[0040] Figure 3 Structure diagram of an embodiment of the personnel identification device of the present application;

[0041] Figure 4 Structure diagram of an embodiment of the electronic equipment of the present application;

[0042] Figure 5 Architecture diagram of an embodiment of the personnel identification device of the present application. DETAILED DESCRIPTION

[0043] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only some embodiments of the present application, not all embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0044] It should be noted that all direction indications (such as up, down, left, right, front, back, etc.) in the embodiments of the present application are only used to explain the relative position relationship, movement condition, etc. between components in a certain posture (as shown in the drawings), and if the certain posture changes, the direction indications will also change accordingly.

[0045] In addition, the descriptions involving "first", "second", etc. in the present application are only for the purpose of description, and cannot be understood as indicating or implying the relative importance or implicitly indicating the number of the indicated technical features. Therefore, the features defined as "first", "second" can explicitly or implicitly include at least one of the features. In addition, the technical solutions of each embodiment can be combined with each other, but it must be based on the realization of ordinary skilled in the art, when the combination of technical solutions appears contradictory or cannot be realized, it should be considered that the combination of technical solutions does not exist, nor within the protection scope required by the present application.

[0046] In the face recognition algorithm of the applicant in the delivery process of the face recognition gate application scenario, there are more frequent misidentification situations:

[0047] 1. In the above scene examples, misidentification situations (more than threshold 86) occur under the face recognition algorithm A (A algorithm), but the recognition speed meets the requirements;

[0048] 2. In the above scene examples, no misidentification situation (default threshold 85) occurs under the face recognition algorithm B (B algorithm), but the recognition speed does not meet the requirements;

[0049] 3. Through the roc (Receiver Operator characteristic Curve, Receiver Operator characteristic Curve) pass rate verification, at each point of the misidentification rate (1 / 100000, 1 / 1000000, 1 / 10000000) of A algorithm, the pass rate is higher than that of B algorithm (see Table 1 and Table 2 below).

[0050] Table 1 Misidentification rate of B algorithm

[0051] False acceptance rate Pass rate Threshold 1 / 100 0.9919 46.4301 1 / 1000 0.9895 54.1360 1 / 10000 0.9778 60.1672 1 / 100000 0.9422 65.1765 1 / 1000000 0.8650 69.2516 1 / 10000000 0.7795 71.8974 Equal error rate EER 0.9919 47.2629 0 0.5600 76.1918

[0052] Table 2 Misidentification rate of A algorithm

[0053]

[0054]

[0055] Note:

[0056] 1, Compare the number of gallery: 10787 pairs;

[0057] 2. The gallery comparison collects the human evidence comparison from the airport scene, and has not been trained by the algorithm.

[0058] Conclusion: both B algorithm and A algorithm have high recognition pass rate, but a single algorithm cannot meet the application scene requirement of the face recognition gate, only using B algorithm, although the recognition accuracy meets the requirement, the recognition speed does not meet the requirement, only using A algorithm, although the recognition speed meets the requirement, the recognition accuracy does not meet the requirement. In order to solve the problem, the technical scheme of the embodiment of the present application is proposed, two algorithms are used for common comparison and decision (A algorithm with fast recognition speed is used as primary authentication, and B algorithm with high recognition accuracy is used as secondary authentication), so as to greatly reduce the false recognition rate and improve the recognition speed.

[0059] On the one hand, the embodiment of the present application provides a personnel recognition method, as shown in the figure, Figure 1 The method of the embodiment can include:

[0060] Step 101: acquiring a biological feature image of a to-be-recognized person;

[0061] In this step, the biological feature can be various biological features, including but not limited to face, iris, fingerprint, palmprint, finger vein, palm vein and the like.

[0062] Step 102: using a first algorithm to perform 1:N comparison on the biological feature image;

[0063] In this step, the first algorithm is used to extract biological features from the image, for example, it can be the applicant's existing face recognition algorithm A (A algorithm).

[0064] Step 103: if a matching person is searched in 1:N comparison, then using a second algorithm to perform 1:1 comparison on the top-ranked preset number of persons in the matching person, wherein the recognition speed of the first algorithm is higher than that of the second algorithm but the recognition accuracy is lower than that of the second algorithm;

[0065] In this step, the ranking is according to the matching degree, the higher the matching degree, the higher the ranking; the preset number can be flexibly set according to the needs, for example, it can be 1, 2, 3 and the like. The second algorithm is used to extract biological features from the image, for example, it can be the applicant's existing face recognition algorithm B (B algorithm).

[0066] Step 104: if 1:1 comparison is passed, the personnel recognition is passed.

[0067] In this way, the embodiment of the present application uses two algorithms for common comparison and decision, the first algorithm with fast recognition speed is used as primary authentication, and the second algorithm with high recognition accuracy is used as secondary authentication, so that the whole scheme has the advantages of both the first algorithm with fast recognition speed and the second algorithm with high recognition accuracy, so as to greatly reduce the false recognition rate and improve the recognition speed.

[0068] As an optional embodiment, the 1:N matching of the biometric image by using the first algorithm (step 102) can specifically include:

[0069] Step 1021: extracting the biometric feature of the biometric image by using the first algorithm to obtain a first biometric feature;

[0070] Step 1022: 1:N matching of the first biometric feature with the biometric feature template of the personnel obtained by the first algorithm stored in the database.

[0071] The above steps 1021-1022 can conveniently realize one-time authentication (i.e. 1:N matching).

[0072] Figure 2 For a flowchart of a specific example of the personnel identification method of the present application, in which the biometric image is a face image and the application scenario is a gate. The foregoing step 101 corresponds to step 201 in Figure 2 , and the above steps 1021-1022 correspond to steps 203 and 204 in Figure 2 , respectively.

[0073] As another optional embodiment, if a matching personnel is searched in the 1:N matching, then 1:1 matching of the personnel with a preset number of top-ranking personnel in the matching personnel by using a second algorithm (step 103) can be performed, which can specifically include:

[0074] Step 1031: if a matching personnel is searched, then obtaining the biometric feature template of the personnel with the first ranking in the matching personnel corresponding to the second algorithm from the database;

[0075] Step 1032: extracting the biometric feature of the biometric image by using the second algorithm to obtain a second biometric feature;

[0076] Step 1033: matching the biometric feature template of the personnel with the first ranking in the matching personnel corresponding to the second algorithm with the second biometric feature, and if the matching is passed, then the personnel identification is passed.

[0077] The above steps 1031-1033 can conveniently realize secondary authentication (i.e. 1:1 matching). The above step 1031 corresponds to step 205 and steps 640-642 (related processing steps of the TOP1 personnel) in Figure 2 , the above step 1032 corresponds to step 202 in Figure 2 , and the above step 1033 corresponds to steps 651-652 in Figure 2 .

[0078] Figure 2 In the example, step 202 uses the second algorithm (algorithm B) to complete the feature extraction of the image and can store it persistently. The step 202 can also be executed asynchronously to improve the efficiency of the program operation; steps 203-204 use the first algorithm (algorithm A) to perform 1:N search and comparison according to conventional logic (one-time authentication); steps 205, 640-642 are to search for the personnel number identified by algorithm A and obtain the feature data of algorithm B through the personnel number; step 651 is to perform 1:1 comparison (secondary authentication) through algorithm B. For requests that pass the secondary authentication of algorithm B, the system determines that it is the same person. For requests that fail the secondary authentication of algorithm B, the system determines that it is not the same person. If the TOP1 image 1:1 matching fails, the TOP2 image 1:1 matching can also be used, and so on, until the top N people are selected from the searched people for 1:1 matching ( Figure 2 Finally, according to the secondary authentication result, a response result can be fed back to control whether the gate is opened or not.

[0079] Furthermore, the step of comparing the biometric template obtained by the second algorithm and the second biometric corresponding to the first-ranked person among the matched persons, and if the comparison is successful, then the person identification is successful (step 1033), may include:

[0080] Step 10331: If the matching fails, obtaining the biometric template obtained by the second algorithm and corresponding to the next matched person from the database;

[0081] Step 10332: Compare the biometric template obtained by the second algorithm and the second biometric corresponding to the next person ranked among the matching persons. If the comparison is successful, the person identification is successful. If the comparison is unsuccessful, go to the previous step until the person identification is successful or the preset number of people ranked first among the matching persons are traversed.

[0082] The above step 10331 corresponds to Figure 2 Step 652 and steps 640'-642' in (the relevant processing steps for TOP2 personnel), the above step 10332 corresponds to Figure 2 Steps 651'-652', 640"-642", 651"-652" (relevant processing steps for TOP3 personnel).

[0083] On the other hand, an embodiment of the present invention provides a personnel identification device, such as Figure 3 Shown, including:

[0084] An acquisition module 11 is used to acquire a biometric image of a person to be identified;

[0085] A first comparison module 12, configured to perform a 1:N comparison on the biometric image using a first algorithm;

[0086] A second comparison module 13 is configured to, if matching persons are found during the 1:N comparison, perform a 1:1 comparison on a preset number of persons ranked first among the matching persons using a second algorithm, wherein the recognition speed of the first algorithm is higher than that of the second algorithm but the recognition accuracy is lower than that of the second algorithm;

[0087] The passing module 14 is used to pass the personnel identification if the 1:1 comparison passes.

[0088] The device of this embodiment can be used to perform Figure 1 The technical solution of the method embodiment shown has similar implementation principles and technical effects, which will not be repeated here.

[0089] Preferably, the first comparison module 12 includes:

[0090] a first extraction unit, configured to extract a biometric feature from the biometric feature image using the first algorithm to obtain a first biometric feature;

[0091] The first comparison unit is configured to perform a 1:N comparison between the first biometric feature and a biometric feature template of a person obtained by the first algorithm and stored in a database.

[0092] Preferably, the second comparison module 13 includes:

[0093] a first acquiring unit, configured to acquire, from the database, a biometric template obtained by the second algorithm and corresponding to the first-ranked matched person if a matched person is found;

[0094] a second extraction unit, configured to extract a biometric feature from the biometric feature image using the second algorithm to obtain a second biometric feature;

[0095] The second comparison unit is used to compare the biometric template obtained by the second algorithm and the second biometric corresponding to the first-ranked person among the matching persons. If the comparison is successful, the person identification is successful.

[0096] Preferably, the second comparison unit includes:

[0097] an acquisition subunit, configured to acquire, from the database, a biometric template obtained by the second algorithm and corresponding to the next person in the matching order if the comparison fails;

[0098] The comparing sub-unit is configured to compare the biological feature template obtained by the second algorithm corresponding to the person ranked next in the matching persons with the second biological feature, and if the comparison passes, the person recognition passes, and if the comparison fails, the process turns to the acquiring sub-unit until the person recognition passes or the persons ranked in the front of the matching persons are traversed.

[0099] The embodiment of the electronic device of the present application also provides a method for identifying a person, Figure 4 The structure diagram of an embodiment of the electronic device of the present application can realize the present application Figure 1 The flow of the embodiment shown as above, as shown in the flowchart of the method for identifying a person, Figure 4 The electronic device can include a housing 41, a processor 42, a memory 43, a circuit board 44 and a power supply circuit 45, wherein the circuit board 44 is arranged inside the space surrounded by the housing 41, the processor 42 and the memory 43 are arranged on the circuit board 44; the power supply circuit 45 is configured to supply power to each circuit or device of the electronic device; the memory 43 is configured to store executable program codes; the processor 42 is configured to run the program corresponding to the executable program codes by reading the executable program codes stored in the memory 43, and execute the method described in any of the method embodiments.

[0100] The specific execution process of the processor 42 for the above steps and the steps further executed by the processor 42 by running the executable program codes can be referred to the description of the embodiment shown as above, and will not be repeated here. Figure 1

[0101] The electronic device exists in various forms, including but not limited to:

[0102] (1) Mobile communication device: the feature of this kind of device is to have mobile communication function and to provide voice and data communication as the main target. This kind of terminal includes: smart phone (such as iPhone), multimedia phone, functional phone, and low-end phone, etc.

[0103] (2) Ultra-mobile personal computer device: this kind of device belongs to the category of personal computer, has computing and processing functions, and generally has the feature of mobile Internet. This kind of terminal includes: PDA, MID and UMPC device, such as iPad.

[0104] (3) Portable entertainment device: this kind of device can display and play multimedia content. This kind of device includes: audio and video player (such as iPod), palm game machine, electronic book, and smart toy and portable car navigation device.

[0105] ​(4) Server: a device providing computing services, the configuration of the server includes a processor, a hard disk, a memory, a system bus, etc., the server is similar to a general computer architecture, but since it needs to provide high-reliable services, it has higher requirements in processing capability, stability, reliability, security, scalability, manageability, etc.

[0106] (5) Other electronic devices with data interaction function.

[0107] The embodiment of the present application also provides a computer readable storage medium, the computer readable storage medium stores a computer program, and the computer program is executed by a processor to realize the method steps of any method embodiment of the present application.

[0108] The embodiment of the present application also provides an application program, which is executed to realize the method provided by any method embodiment of the present application.

[0109] The embodiment of the present application also provides a personnel identification device, as shown in the Figure 5 The device of the embodiment can include a device main body and an edge computing terminal connected with the device main body, wherein:

[0110] The device main body is configured to acquire a biological feature image of a to-be-identified person;

[0111] The edge computing terminal is configured to perform 1:N matching on the biological feature image by using a first algorithm; if a matched person is searched in the 1:N matching, the edge computing terminal performs 1:1 matching on a preset number of persons in the matched person by using a second algorithm, wherein the identification speed of the first algorithm is higher than that of the second algorithm, but the identification accuracy of the first algorithm is lower than that of the second algorithm; if the 1:1 matching is passed, the personnel identification is passed.

[0112] The device main body is further configured to give a corresponding instruction after the personnel identification is passed.

[0113] The personnel identification device of the embodiment, wherein the related steps are similar to the steps in the method embodiment shown in Figure 1 The implementation principle and technical effects are similar, and details are not repeated here. The personnel identification device of the embodiment includes a device main body and an edge computing terminal, so that the asynchronous execution of the related process steps can be realized, thereby improving the execution efficiency and the personnel identification speed.

[0114] Preferably, the device main body is configured to acquire a biological feature image of a to-be-identified person, and perform biological feature living body judgment, biological feature angle judgment and / or biological feature quality judgment.

[0115] The device main body is further configured to give a corresponding instruction after the personnel identification is passed and the biological feature judgments are passed.

[0116] In this way, by splitting the device-side detection, the detection process and the back-end comparison process, and asynchronously processing the detection and comparison, the speed of personnel identification is further improved.

[0117] Preferably, the biometric image is a face image, and / or the corresponding instruction is a gate opening instruction.

[0118] The above is the preferred embodiment of the present application, it should be pointed out that, for those skilled in the art, without departing from the principles of the present application, can make a number of improvements and refinements, these improvements and refinements should also be considered as the protection scope of the present application.

Claims

1. A method of recognizing a person, characterized by, The method comprises the following steps: obtaining a biological feature image of a person to be identified; performing 1:N comparison on the biological feature image by using a first algorithm; if a matching person is searched in the 1:N comparison, performing 1:1 comparison on a preset number of persons with high ranking in the matching person by using a second algorithm, wherein the identification speed of the first algorithm is higher than that of the second algorithm but the identification accuracy of the first algorithm is lower than that of the second algorithm; if the 1:1 comparison is passed, the person identification is passed; wherein the 1:N comparison on the biological feature image by using the first algorithm comprises the following steps: extracting biological features of the biological feature image by using the first algorithm to obtain first biological features; performing 1:N comparison on the first biological features and biological feature templates of persons obtained by the first algorithm and stored in a database; wherein if a matching person is searched, the biological feature template corresponding to the person with the first ranking in the matching person obtained by the second algorithm is acquired from the database; extracting biological features of the biological feature image by using the second algorithm to obtain second biological features; performing comparison on the biological feature template corresponding to the person with the first ranking in the matching person obtained by the second algorithm and the second biological features, and if the comparison is passed, the person identification is passed. The comparison on the biological feature template corresponding to the person with the first ranking in the matching person obtained by the second algorithm and the second biological features, and if the comparison is passed, the person identification is passed, comprises the following steps:

2. The method of claim 1, wherein, if the comparison is not passed, the biological feature template corresponding to the person with the next ranking in the matching person obtained by the second algorithm is acquired from the database; performing comparison on the biological feature template corresponding to the person with the next ranking in the matching person obtained by the second algorithm and the second biological features, and if the comparison is passed, the person identification is passed, and if the comparison is not passed, the previous step is returned until the person identification is passed or the persons with the preset number of high rankings in the matching person are traversed. The method comprises the following steps:

3. A person recognition apparatus characterized by comprising: an acquisition module, configured to acquire a biological feature image of a person to be identified; a first comparison module, configured to perform 1:N comparison on the biological feature image by using a first algorithm; a second comparison module, configured to perform 1:1 comparison on a preset number of persons with high ranking in the matching person by using a second algorithm if a matching person is searched in the 1:N comparison, wherein the identification speed of the first algorithm is higher than that of the second algorithm but the identification accuracy of the first algorithm is lower than that of the second algorithm; a passing module, configured to pass the person identification if the 1:1 comparison is passed; wherein the first comparison module comprises: a first extraction unit, configured to extract biological features of the biological feature image by using the first algorithm to obtain first biological features; a first comparison unit, configured to perform 1:N comparison on the first biological features and biological feature templates of persons obtained by the first algorithm and stored in a database; wherein the second comparison module comprises: ​ The first obtaining unit is configured to, if a matching person is searched, obtain a biometric feature template corresponding to a person ranked first in the matching persons and obtained by the second algorithm from the database. The second extracting unit is configured to extract a biometric feature of the biometric feature image by using the second algorithm to obtain a second biometric feature. The second comparing unit is configured to compare the biometric feature template corresponding to the person ranked first in the matching persons and obtained by the second algorithm with the second biometric feature, and if the comparison is passed, the person recognition is passed.

4. An electronic device, comprising: The electronic device comprises a shell, a processor, a memory, a circuit board and a power circuit, wherein the circuit board is arranged inside a space enclosed by the shell, the processor and the memory are arranged on the circuit board; the power circuit is configured to supply power to each circuit or device of the electronic device; the memory is configured to store executable program codes; the processor is configured to run programs corresponding to the executable program codes by reading the executable program codes stored in the memory, and the programs are configured to execute the method of claim 1 or 2.

5. A computer readable storage medium, characterized in that, The computer readable storage medium stores one or more programs, which can be executed by one or more processors to implement the method of claim 1 or 2.

6. A person recognition device, comprising a device body and an edge computing terminal connected to the device body, characterized in that, The device body is configured to obtain a biometric feature image of a person to be recognized. The edge computing terminal is configured to perform 1:N comparison on the biometric feature image by using a first algorithm; if a matching person is searched during the 1:N comparison, perform 1:1 comparison on a preset number of persons ranked in front in the matching persons by using a second algorithm, wherein the recognition speed of the first algorithm is higher than that of the second algorithm but the recognition accuracy of the first algorithm is lower than that of the second algorithm; if the 1:1 comparison is passed, the person recognition is passed; The device body is further configured to give a corresponding instruction after the person recognition is passed. The 1:N comparison on the biometric feature image by using the first algorithm comprises: extracting a biometric feature of the biometric feature image by using the first algorithm to obtain a first biometric feature; performing 1:N comparison on the first biometric feature and biometric feature templates of persons stored in a database and obtained by the first algorithm; The 1:1 comparison on the preset number of persons ranked in front in the matching persons by using the second algorithm comprises: if a matching person is searched, obtaining a biometric feature template corresponding to a person ranked first in the matching persons and obtained by the second algorithm from the database; extracting a biometric feature of the biometric feature image by using the second algorithm to obtain a second biometric feature; comparing the biometric feature template corresponding to the person ranked first in the matching persons and obtained by the second algorithm with the second biometric feature, and if the comparison is passed, the person recognition is passed.

7. The apparatus of claim 6, wherein, The device body is configured to obtain a biometric feature image of a person to be recognized, and perform biometric feature liveliness judgment, biometric feature angle judgment and / or biometric feature quality judgment. The device main body is further configured to give a corresponding instruction after the personnel identification passes and each of the biological feature determinations passes.

8. The apparatus of claim 6 or 7, wherein, The biological feature image is a face image, and / or the corresponding instruction is a gate opening instruction.

Images