An identity recognition method, device and computer readable storage medium

Abstract

The embodiment of the application discloses an identity recognition method and device, the method comprises the following steps: when any target person performs identity recognition at a first entrance, recording recognition information; the recognition information comprises a recognition time; calculating the expected entrance time corresponding to other entrances of the target person after identity recognition according to the recognition time; the other entrances are all entrances contained in the current scene except the first entrance; between the recognition time and the entrance time, identity recognition is performed at the other entrances according to the reduced identity personnel database of the target person. Through the embodiment, the identity recognition speed is improved.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to information detection technology, and in particular to an identity recognition method and device and a computer readable storage medium. BACKGROUND

[0002] The related identity recognition technology is to extract the feature value of the identity data, compare it with the identity data in the database one by one, get the similarity value and then sort it, and if the similarity is the highest and exceeds the set threshold, it is determined that the two identities match, and the information of successful recognition is returned, otherwise the recognition fails.

[0003] For example, when identity recognition is performed by face recognition technology, the feature value of the face is extracted, compared with the face data in the database one by one, the similarity value is obtained and then sorted, and if the similarity is the highest and exceeds the set threshold, it is determined that the two faces are the same person, and the information of successful recognition is returned, otherwise the recognition fails. The four key steps of face recognition are as follows: first, face detection; second, face living body detection; third, face feature extraction; fourth, face feature search comparison.

[0004] In the current identity recognition scheme, as the identity data (such as face) stored in the database becomes more and more, the feature search comparison will also become slower, and when the data is large enough, the search amount increases, and the time also increases, for example, the average time consumption of current face recognition has reached more than 1s, and as the database capacity increases, the time consumption will certainly be longer. Therefore, how to optimize the search structure under large database capacity to improve the identity recognition speed is a problem to be solved at present. SUMMARY

[0005] Embodiments of the present application provide an identity recognition method, device and computer readable storage medium, which can improve the identity recognition speed.

[0006] Embodiments of the present application provide an identity recognition method, which can include:

[0007] When any target person performs identity recognition at a first entrance, record the recognition information; the recognition information includes: a recognition time;

[0008] According to the recognition time, calculate the expected entry and exit time of the target person at other entrances after identity recognition; the other entrances are all entrances in the current scene except the first entrance;

[0009] Between the recognition time and the entry and exit time, identity recognition is performed at other entrances in the current scene according to the reduced recognition personnel database of the target person.

[0010] In the example embodiment of the present application, the calculating the expected access time of the target person at the other access gate according to the identification time can comprise:

[0011] obtaining a moving duration of the target person moving from the first access gate to the other access gate;

[0012] calculating the access time of the target person at the other access gate according to the identification time and the moving duration.

[0013] In the example embodiment of the present application, the obtaining the moving duration of the target person moving from the first access gate to the other access gate can comprise:

[0014] obtaining a walking speed of the target person collected in advance and a distance between the first access gate and the other access gate;

[0015] calculating the moving duration according to the walking speed and the distance.

[0016] In the example embodiment of the present application, when the other access gate is multiple, the distance can be the distance corresponding to the other access gate with the minimum distance from the first access gate.

[0017] In the example embodiment of the present application, the identification information can further comprise personnel identity information; and before the identity of the target person is identified according to the identification personnel database with reduced identification priority at the other access gate, the method can further comprise:

[0018] changing the identification priority of the label corresponding to the personnel identity information of the target person from a first identification to a second identification in the identification personnel database; wherein the identification priority indicated by the first identification is higher than the identification priority indicated by the second identification.

[0019] In the example embodiment of the present application, the method can further comprise: after the time exceeds the access time, performing the following operation on the personnel identity information of the target person:

[0020] changing the identification priority of the target person from the second identification to the first identification in the identification personnel database.

[0021] In the example embodiment of the present application, when the first identification device is arranged at the first access gate and the other identification device is arranged at the other access gate, after the identification information is recorded by the first identification device, the method can further comprise:

[0022] publish the identification information to the other identification device, so that the other identification device marks the target person.

[0023] In the example embodiments of the present application, the method can further comprise:

[0024] When the identity recognition behavior of the target person is an entry identity recognition behavior, the personnel identity information containing the identification information of the target person is put into a preset exit personnel library, and the exit personnel library is used as a personnel library for priority comparison when exit identity recognition is performed;

[0025] When the identity recognition behavior of the target person is an exit identity recognition behavior, the personnel identity information containing the identification information of the target person is put into a preset entry personnel library, and the entry personnel library is used as a personnel library for priority comparison when entry identity recognition is performed.

[0026] In the example embodiments of the present application, the identification mode of the target person when performing identity recognition can include any one or more of the following: face recognition, fingerprint recognition, palm print recognition, iris recognition, and vein recognition.

[0027] The example embodiments of the present application also provide an identity recognition device, which can include a processor and a computer readable storage medium, and the computer readable storage medium stores instructions, when the instructions are executed by the processor, the identity recognition method of any one of the above is implemented.

[0028] The example embodiments of the present application also provide a computer readable storage medium, which stores a computer program capable of running on a processor, and when the computer program is executed by the processor, the identity recognition method of any one of the above is implemented.

[0029] Compared with the related art, the example embodiments of the present application can include: when any target person performs identity recognition at a first entrance and exit, recording identification information; the identification information includes: an identification time; calculating a predicted entry and exit time corresponding to other entrances and exits of the target person after identity recognition according to the identification time; the other entrances and exits are all entrances and exits contained in the current scene except the first entrance and exit; between the identification time and the entry and exit time, identity recognition is performed at the other entrances and exits according to a reduced identification personnel library of the target person. Through the embodiment scheme, the identity recognition speed is improved.

[0030] Other features and advantages of the present application will be described in the following description, and some will become apparent from the description, or will be learned from the practice of the present application. Other advantages of the present application can be achieved and obtained through the schemes described in the specification and the drawings. BRIEF DESCRIPTION OF DRAWINGS

[0031] The accompanying drawings are included to provide a further understanding of the present application, and constitute a part of this specification that is made of the description of the embodiments of the present application, and are used to explain the technical scheme of the present application, and do not constitute a limitation to the technical scheme of the present application.

[0032] Figure 1 The flow chart of the identity recognition method of the embodiment of the present application is shown in Figure 1.

[0033] Figure 2 The block diagram of the identity recognition device of the embodiment of the present application is shown in Figure 2. DETAILED DESCRIPTION

[0034] The present application describes a plurality of embodiments, but the description is exemplary rather than limiting, and it is obvious to those skilled in the art that there can be more embodiments and implementation schemes within the scope of the embodiments described in the present application. Although many possible combinations of features are shown in the accompanying drawings and discussed in the specific embodiments, many other combinations of the disclosed features are also possible. Unless specifically limited, any feature or element of any embodiment can be used in combination with any other feature or element of any other embodiment, or can replace any other feature or element of any other embodiment.

[0035] The present application includes and contemplates the combination of features and elements known to those skilled in the art. The embodiments, features and elements disclosed in the present application can also be combined with any conventional features or elements to form a unique inventive scheme defined by the claims. Any feature or element of any embodiment can also be combined with features or elements from other inventive schemes to form another unique inventive scheme defined by the claims. Therefore, it should be understood that any feature shown and / or discussed in the present application can be implemented alone or in any appropriate combination. Therefore, the embodiments are not limited other than according to the limitations made according to the appended claims and their equivalent replacements. In addition, various modifications and changes can be made within the scope of protection of the appended claims.

[0036] Moreover, in describing representative embodiments, the specification can have presented the method and / or process as a particular sequence of steps. However, to the extent that the method or process depends on the performance of certain steps, the method or process is not limited to the order of steps presented nor to performing some specific steps before other specific steps have been performed. One of ordinary skill in the art would recognize various modifications. As such, the order of exemplary steps in which they are presented makes no limitation as to the scope of the claims. Moreover, the specification's representation of a method and / or process by the description of a particular sequence of steps does not limit claims that cover any other sequence of steps in which the steps are performed at least substantially the same way nor require that they be performed in any particular sequence. Additionally, the specification's representation of a method and / or process by the description of a particular sequence of steps does not limit claims that cover at least some steps performed in another particular sequence nor require that they be performed in any particular sequence.

[0037] The embodiments of the present application provide an identity recognition method, which can include steps S101-S103 as shown in the following table: Figure 1

[0038] S101, when any target person performs identity recognition at a first entrance, record recognition information; the recognition information includes: a recognition time; the target person refers to any person currently performing identity recognition at the first entrance;

[0039] S102, calculate a predicted access time corresponding to other entrances of the target person after identity recognition according to the recognition time; the other entrances are all entrances in a current scene except the first entrance;

[0040] S103, between the recognition time and the access time, perform identity recognition at the other entrances according to a reduced identity person database of the target person.

[0041] In the exemplary embodiments of the present application, in order to improve the access efficiency in a specific time period (for example, morning and evening peak, entrance peak, etc.) in a park, a theater or the like, the embodiments of the present application propose an identity recognition method based on time difference.

[0042] In the exemplary embodiments of the present application, the recognition mode of the target person when performing identity recognition can include but is not limited to any one or more of the following: face recognition, fingerprint recognition, palm print recognition, iris recognition and vein recognition. The embodiment scheme does not limit the specific identity recognition mode.

[0043] In the exemplary embodiments of the present application, the current scene can include multiple entrances, an identity recognition device can be arranged at each entrance, and each identity recognition device can have respective attribute information, for example, number information, geographical position information, etc.

[0044] ​In the example embodiments of the present application, each identity recognition device of the current scene can be connected with a preset recognition platform, which can be a central controller or a preset cloud platform, and the specific implementation of the recognition platform is not limited herein. The embodiment scheme of the present application can be realized by mutual cooperation of the recognition platform and each identity recognition device.

[0045] In the example embodiments of the present application, after the target person enters any first entrance for identity recognition and is recognized to pass, the recognition information of the target person can be recorded first, which can include but is not limited to: recognition time, recognition location, number of recognition device, type of recognition device, and personnel identity information of the target person, etc.

[0046] In the example embodiments of the present application, when the first entrance is provided with a first recognition device and the other entrances are provided with other recognition devices, after the recognition information is recorded by the first recognition device, the method can further include:

[0047] publishing the recognition information to the other recognition devices, so that the other recognition devices mark the target person.

[0048] In the example embodiments of the present application, based on the above-mentioned recognition time, a time difference can be calculated, and within the time difference, it is ensured that the current target person will not be recognized again at any other entrance in the current scene, so that the identity recognition at the other entrances included in the current scene can be performed according to the reduced recognition personnel database of the target person. In a special time period of personnel-intensive identity recognition, because a large number of personnel pass through identity recognition within a certain time (which is much shorter than the above-mentioned time difference), the recognition information of a large number of personnel can be ignored within the time difference, that is, within the calculated time difference, a large number of personnel can have their recognition priorities reduced when performing identity recognition at the other entrances, so that the personnel information that has not yet been recognized is preferentially recognized, thereby improving the identity recognition efficiency.

[0049] In the example embodiments of the present application, the time difference can be the time difference between the recognition time and the entering and exiting time of the target person at the other entrances. In order to obtain the time difference, the entering and exiting time can be calculated first according to the average walking speed of the target person.

[0050] In the example embodiments of the present application, the calculation of the expected entering and exiting time of the target person at the other entrances after identity recognition based on the recognition time can include:

[0051] obtaining the moving duration of the target person from the first entrance to the other entrances.

[0052] According to the identification time and the moving duration, the access time of the target person at the other access gate is calculated.

[0053] In the exemplary embodiments of the present application, the expected access time at the other access gate refers to the access time at which the target person is likely to access the other access gate.

[0054] In the exemplary embodiments of the present application, the acquiring of the moving duration of the target person moving from the first access gate to the other access gate can include:

[0055] acquiring the walking speed of the target person collected in advance and the distance between the first access gate and the other access gate;

[0056] According to the walking speed and the distance, the moving duration is calculated.

[0057] In the exemplary embodiments of the present application, before the embodiments of the present application are applied, the walking speed (which can be the average walking speed) of each target person can be collected in advance. The walking speed can be collected specially when each target person registers information, or can be collected temporarily before the target person enters the access gate. For example, the walking speed of the target person can be calculated by collecting a video, an image or other information of the target person walking for a period of time. For the behavior of the target person running quickly due to time constraints, the walking speed can be estimated according to the step length of the target person when walking normally, so as to calculate the walking speed. Alternatively, a preset correction value is added to the running speed of the target person to obtain the walking speed, wherein the correction value can be obtained according to the height, leg length or other information of the target person.

[0058] In the exemplary embodiments of the present application, based on the walking speed and the distance between the first access gate and the other access gate at present, the moving duration of the target person moving to the other access gate, i.e. the time difference, can be calculated.

[0059] In the exemplary embodiments of the present application, according to the time difference and the identification time recorded at the first access gate, the access time of the target person accessing the other access gate can be determined.

[0060] In the exemplary embodiments of the present application, the identity recognition device at the other access gate can be directly controlled to perform identity recognition according to the reduced identification personnel database of the target person according to the moving duration (i.e. the time difference). That is, within a certain duration (moving duration) from the identification time, the identity recognition device at the other access gate can be controlled to perform identity recognition according to the reduced identification personnel database of the target person. In the exemplary embodiments of the present application, the identity recognition device at the other access gate can be directly controlled to perform identity recognition according to the reduced identification personnel database of the target person according to the moving duration (i.e. the time difference). That is, within a certain duration (moving duration) from the identification time, the identity recognition device at the other access gate can be controlled to perform identity recognition according to the reduced identification personnel database of the target person.

[0061] In the example embodiments of the present application, the identity recognition device at other entrances and exits can also be controlled to perform identity recognition according to the reduced identification personnel database of the target personnel at the entrance and exit time. That is, before the entrance and exit time, the identity recognition device at other entrances and exits can be controlled to perform identity recognition according to the reduced identification personnel database of the target personnel.

[0062] In the example embodiments of the present application, when the other entrances and exits are multiple, the distance can be the distance corresponding to the other entrance and exit with the minimum distance to the first entrance and exit.

[0063] In the example embodiments of the present application, in order to ensure that the target person does not appear at other entrances and exits within the time difference, the above-mentioned distance can be the minimum distance among the distances between the first entrance and exit and multiple other entrances and exits, thereby improving the accuracy and effectiveness of the embodiments of the present application.

[0064] In the example embodiments of the present application, the identification information can further include personnel identity information, and before performing identity recognition at other entrances and exits according to the reduced identification personnel database of the target personnel, the method can further include:

[0065] changing the identification priority corresponding to the personnel identity information of the target person in the identification personnel database from a first identification to a second identification; wherein the identification priority indicated by the first identification is higher than the identification priority indicated by the second identification.

[0066] In the example embodiments of the present application, the method can further include: after the time exceeds the entrance and exit time, performing the following operation on the personnel identity information of the target person: changing the identification priority corresponding to the personnel identity information of the target person in the identification personnel database from the second identification to the first identification.

[0067] In the example embodiments of the present application, in order to further reduce the comparison amount and improve the recognition efficiency, identity recognition can also be performed at other entrances and exits according to an identification personnel database that does not contain the target personnel between the identification time and the entrance and exit time.

[0068] In the example embodiments of the present application, the identification information can further include personnel identity information, and before performing identity recognition at other entrances and exits in the current scene according to an identification personnel database that does not contain the target personnel, the method can further include any one of the following:

[0069] deleting the personnel identity information of the target person from the identification personnel database;

[0070] setting the personnel identity information of the target person in the identification personnel library to an unreadable state; and

[0071] setting a label of the personnel identity information of the target person in the identification personnel library to a first label; the first label is used to represent that the personnel identity information is not used as comparison information when identity identification is performed.

[0072] In the exemplary embodiments of the present application, between the identification moment and the access moment, in order to achieve the identity identification at the other access points according to the identification personnel library not containing the target person, the personnel identity information can be deleted from the identification personnel library, the readable state or the label of the personnel identity information can be modified, etc. Here, the detailed scheme is not limited, and any method capable of achieving the identity identification at all access points according to the identification personnel library not containing the target person is within the protection scope of the embodiments of the present application.

[0073] In the exemplary embodiments of the present application, the method can further include: after a time exceeds the access moment, performing any one of the following operations on the personnel identity information of the target person:

[0074] restoring the personnel identity information of the target person in the identification personnel library;

[0075] setting the personnel identity information of the target person in the identification personnel library to an unreadable state; and

[0076] setting a label of the personnel identity information of the target person in the identification personnel library to a second label; the second label is used to represent that the personnel identity information is used as comparison information when identity identification is performed.

[0077] In the exemplary embodiments of the present application, the time exceeding the access moment can include a preset time length after the identification moment, and the preset time length can be the aforementioned time difference, that is, after the aforementioned time difference, the personnel identity information of the target person in the identification personnel library can be restored, so that the target person can still be successfully identified when identity identification is performed at any one access point.

[0078] In the exemplary embodiments of the present application, in some scenes requiring identity identification only once, for example, a clock-in scene, a ticket checking scene, the preset time length can also be defined according to different application scenes. For example, in the clock-in scene of each day, the preset time length can be set based on the working time (for example, 8 hours), such as 7-10 hours. In the access scene of a movie or a performance, the preset time length can be set based on the performance time (for example, 2 hours), such as 0.5-2 hours.

[0079] In the example embodiments of the present application, the method can further comprise:

[0080] When the identity recognition behavior of the target person is an entry identity recognition behavior, the personnel identity information of the target person is put into a preset exit personnel database, and the exit personnel database is used as a personnel database for priority comparison when exit identity recognition is performed;

[0081] When the identity recognition behavior of the target person is an exit identity recognition behavior, the personnel identity information of the target person is put into a preset entry personnel database, and the entry personnel database is used as a personnel database for priority comparison when entry identity recognition is performed.

[0082] In the example embodiments of the present application, when the identity recognition behavior of the target person is an entry identity recognition behavior, the aforementioned identification personnel database is used as an entry personnel identification database, and after the identification of any target person is passed, the personnel identity information of the person can be put into another preset personnel database, which can be used as an exit personnel database, i.e., the personnel database can be first called for comparison when exit personnel identity recognition is performed next time.

[0083] In the example embodiments of the present application, when the identity recognition behavior of the target person is an exit identity recognition behavior, the aforementioned identification personnel database is used as an exit personnel identification database, and after the identification of any target person is passed, the personnel identity information of the person can be put into another preset personnel database, which can be used as an entry personnel database, i.e., the personnel database can be first called for comparison when entry personnel identity recognition is performed next time.

[0084] In the example embodiments of the present application, the example embodiments of the present application have at least the following advantages:

[0085] 1. The order of comparison in the personnel database is adjusted based on the distance between the identity recognition devices, and the overall recognition efficiency of the equipment is improved.

[0086] 2. Based on multiple personnel databases, the problem of low recognition efficiency of the current large-capacity identity recognition scheme of the recognition equipment in different entry and exit directions under the personnel entry and exit business model is solved.

[0087] 3. The recognition efficiency in a closed environment such as a park is solved, and the overall traffic efficiency is effectively improved.

[0088] The present application also provides an identity recognition device 1, as shown in Figure 2As shown, the apparatus can include a processor 11 and a computer readable storage medium 12 having instructions stored therein that, when executed by the processor 11, implement any of the identity recognition methods described above. In exemplary embodiments of the present application, any of the method embodiments described above are applicable to this apparatus embodiment, and thus will not be repeated here.

[0089] The present application also provides a computer readable storage medium having stored thereon a computer program executable by a processor, the computer program, when executed by the processor, implementing any of the identity recognition methods described above.

[0090] In exemplary embodiments of the present application, any of the method embodiments described above are applicable to this computer readable storage medium embodiment, and thus will not be repeated here.

[0091] Those skilled in the art can understand that all or some of the steps in the above disclosed method, the functions of the modules / units in the system and the apparatus can be implemented as software, firmware, hardware or a combination thereof. In hardware implementation, the division between the functional modules / units mentioned in the above description does not necessarily correspond to the division between physical components; for example, one physical component can have multiple functions, or one function or step can be performed by several physical components working together. Some or all of the components can be implemented as software executed by a processor, such as a digital signal processor or a microprocessor, or as hardware, or as an integrated circuit, such as an application specific integrated circuit. Such software can be distributed on computer readable media, which can include computer storage media (or non-transitory media) and communication media (or transitory media). As is well known to those skilled in the art, the term computer storage media includes volatile and non-volatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tapes, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed by a computer. Furthermore, it is common knowledge to those skilled in the art that communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and can include any information delivery media.

Claims

1. An identity recognition method, characterized in that, The method includes: When any target person undergoes identification at the first entrance / exit, the identification information is recorded; the identification information includes: the time of identification. The estimated entry and exit times of the target person at other entrances and exits after identity recognition are calculated based on the recognition time; the other entrances and exits are all entrances and exits included in the current scene except for the first entrance and exit; when there are multiple other entrances and exits, the estimated entry and exit time of the other entrance and exit with the smallest distance from the first entrance and exit is selected. Between the identification time and the entry / exit time, at the other entrances / exits, identity is identified based on a database of identified personnel with reduced identification priority for the target personnel. The identification information also includes: personnel identity information; before performing identity identification at all entrances and exits based on the identification personnel database with reduced identification priority for the target personnel, the method further includes: In the identification personnel database, the identification priority identifier corresponding to the target personnel's identity information is changed from a first identifier to a second identifier; wherein, the identification priority indicated by the first identifier is higher than the identification priority indicated by the second identifier; The method further includes: performing the following operations on the target person's identity information after the time has exceeded the entry / exit time: In the identification personnel database, the identification priority identifier corresponding to the personnel identity information of the target personnel is restored from the second identifier to the first identifier.

2. The identity recognition method according to claim 1, characterized in that, The step of calculating the expected entry / exit time of the target person at other entrances / exits after identity recognition based on the recognition time includes: The time taken for the target person to move from the first entrance / exit to the other entrance / exit is obtained; The entry and exit times of the target person at the other entrances and exits are calculated based on the identification time and the movement duration. The step of obtaining the movement time of the target person from the first entrance / exit to the other entrance / exit includes: The walking speed of the target person, which was collected in advance, and the distance between the first entrance / exit and the other entrances / exits are obtained; the movement time is calculated based on the walking speed and the distance.

3. The identity recognition method according to any one of claims 1-2, characterized in that, When a first identification device is installed at the first entrance / exit, and other identification devices are installed at the other entrances / exits, the method further includes, after the first identification device records the identification information: The identification information is published to the other identification devices so that the other identification devices can mark the target person.

4. The identity recognition method according to any one of claims 1-2, characterized in that, The method further includes: When the identification behavior of the target person is an entry identification behavior, the personnel identity information contained in the identification information of the target person is put into a preset exit personnel database, and the exit personnel database is used as the personnel database to be compared first when performing exit identification. When the identification behavior of the target person is the exit identification behavior, the personnel identity information contained in the identification information of the target person is put into the preset entry personnel database, and the entry personnel database is used as the personnel database that is prioritized for comparison when performing entry identification.

5. The identity recognition method according to any one of claims 1-2, characterized in that, The identification methods used to identify the target person include any one or more of the following: facial recognition, fingerprint recognition, palm print recognition, iris recognition, and vein recognition.

6. An identity recognition device, characterized in that, The device includes a processor and a computer-readable storage medium, wherein the computer-readable storage medium stores instructions that, when executed by the processor, implement the identity recognition method as described in any one of claims 1-5.

7. A computer-readable storage medium having a computer program stored thereon that can run on a processor, characterized in that, When the computer program is executed by the processor, it implements the identity recognition method as described in any one of claims 1-5.

Images