Face base map updating method, device and system and storage medium

Abstract

The invention discloses a face base map updating method, device and system and a storage medium. The method comprises the steps that a first face image is collected in real time, the first face image is recognized based on a face database, and a target face base map matched with the first face image is determined from the face database; when it is determined that the target face base map is the to-be-updated face image, collecting a reference face image of the first face image, and determining at least one reference user of the target user corresponding to the first face image based on the reference face image; determining the intimacy of the target user relative to each reference user based on the reference face image, and taking the reference user with the maximum intimacy as the intimacy user of the target user; and when it is detected that an updating event of the target face base map is triggered, obtaining a second face image of the user before or after the intimate user, and updating the target face base map based on the second face image. According to the scheme, the to-be-updated face base map in the face database can be automatically updated.

Description

Technical Field

[0001] The present invention relates to the technical field of face recognition, and particularly to a method, device, system and storage medium for updating a face base map. Background Art

[0002] With the development of the security industry, the functional applications of face recognition are becoming more and more extensive. Face recognition is achieved by comparing the captured target face image with the face base map in the face database. Generally, after the face base map is imported into the face database, the face base map in the face database will not be replaced anymore. However, a person's appearance may change over time, especially for children, which will lead to a decrease in the face recognition rate of children. Summary of the Invention

[0003] The present invention provides a method, device, system and storage medium for updating a face base map, which can automatically update the face base map to be updated in the face database, thereby effectively improving the accuracy of face recognition.

[0004] According to one aspect of the present invention, there is provided a method for updating a face base map, the method comprising:

[0005] Real-time collecting a first face image, and recognizing the first face image based on a pre-stored face database, and determining a target face base map matching the first face image from the face database;

[0006] When it is determined that the target face base map is a face image to be updated, collecting a reference face image of the first face image within a preset time period, and determining at least one reference user of the target user corresponding to the first face image based on the reference face image;

[0007] Determining the intimacy of the target user with respect to each of the at least one reference user based on the reference face image, and using the reference user with the maximum intimacy as the intimate user of the target user;

[0008] When it is detected that an update event of the target face base map is triggered, acquiring a second face image of a user before or after the intimate user, and updating the target face base map based on the second face image.

[0009] According to another aspect of the present invention, there is provided a face base map updating device, comprising:

[0010] A target face base map determining module, configured to real-time collect a first face image, and recognize the first face image based on a pre-stored face database, and determine a target face base map matching the first face image from the face database;

[0011] A reference face image determination module, configured to, when determining that the target face base map is a face image to be updated, collect a reference face image of the first face image within a preset time period, and determine at least one reference user of the target user corresponding to the first face image based on the reference face image;

[0012] An intimate user determination module, configured to determine the intimacy of the target user with respect to each reference user among the at least one reference user based on the reference face image, and use the reference user with the maximum intimacy as the intimate user of the target user;

[0013] A face base map update module, configured to, when detecting that an update event of the target face base map is triggered, obtain a second face image of a user before or after the intimate user, and update the target face base map based on the second face image.

[0014] According to another aspect of the present invention, there is provided a face recognition system, the face recognition system comprising:

[0015] At least one processor; and

[0016] A memory communicatively connected to the at least one processor; wherein,

[0017] The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the face base map update method according to any embodiment of the present invention.

[0018] According to another aspect of the present invention, there is provided a computer-readable storage medium storing computer instructions for causing a processor to implement the face base map method according to any embodiment of the present invention when executed.

[0019] The face base map update solution according to the embodiments of the present invention collects a first face image in real time, and recognizes the first face image based on a pre-stored face database, and determines a target face base map matching the first face image from the face database; when it is determined that the target face base map is a face image to be updated, a reference face image of the first face image is collected within a preset time period, and at least one reference user of the target user corresponding to the first face image is determined based on the reference face image; the intimacy of the target user relative to each reference user among the at least one reference user is determined based on the reference face image, and the reference user with the maximum intimacy is used as the intimate user of the target user; when it is detected that an update event of the target face base map is triggered, a second face image of the user before or after the intimate user is obtained, and the target face base map is updated based on the second face image. Through the technical solution provided by the embodiments of the present invention, the face base map to be updated in the face database can be automatically updated, thereby effectively improving the accuracy of face recognition.

[0020] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present invention, nor is it used to limit the scope of the present invention. Other features of the present invention will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] 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 the description of the embodiments. Obviously, the drawings in the following description are only some embodiments of the present invention, and those of ordinary skill in the art can obtain other drawings without creative efforts based on these drawings.

[0022] Figure 1 is a flowchart of a face base map update method according to Embodiment 1 of the present invention;

[0023] Figure 2 is a flowchart of a face base map update method according to Embodiment 2 of the present invention;

[0024] Figure 3 is a schematic structural diagram of a face base map update device according to Embodiment 3 of the present invention;

[0025] Figure 4 is a schematic structural diagram of a face recognition system for implementing the face base map update method of the embodiments of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0026] To enable those skilled in the art to better understand the solution of the present invention, the technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those of ordinary skill in the art without creative efforts shall fall within the protection scope of the present invention.

[0027] It should be noted that the terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish similar objects, and do not necessarily need to describe a specific order or sequence. It should be understood that such data can be interchanged under appropriate circumstances so that the embodiments of the present invention described herein can be implemented in an order other than those illustrated or described herein. In addition, the terms "comprising" and "having" and any variations thereof are intended to cover non-exclusive inclusion. For example, a process, method, system, product or device comprising a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but may include other steps or units not clearly listed or inherent to these processes, methods, products or devices.

[0028] Embodiment 1

[0029] Figure 1 FIG. 10 is a flowchart of a method for updating a face base map according to Embodiment 1 of the present invention. This embodiment is applicable to the case of automatically updating the face base map in a face database. This method can be executed by a face base map updating device, which can be implemented in the form of hardware and / or software, and the face base map updating device can be configured in a face recognition system. As Figure 1 shown, the method includes:

[0030] S110. Real-time collect a first face image, and identify the first face image based on a pre-stored face database, and determine a target face base map matching the first face image from the face database.

[0031] In the embodiment of the present invention, a first face image is collected in real time. Among them, the first face image can be a face image of any user, such as a face image of a child, or a face image of an elderly person, or a face image of an adult. The first face image is identified based on a pre-stored face database, that is, the first face image is respectively matched with each face base map in the face database, and the face base map matching the first face image is determined from the face database. For the convenience of description, the face base map in the face database matching the first face image is used as the target face base map.

[0032] S120. When it is determined that the target face base map is a face image to be updated, collect a reference face image of the first face image within a preset time period, and determine at least one reference user of the target user corresponding to the first face image based on the reference face image.

[0033] In the embodiments of the present invention, determining whether the target face base map is a face image to be updated is also to determine whether the target face base map matching the first face image in the face database is a face image to be updated. Optionally, determining that the target face base map is a face image to be updated includes: when it is determined that the first face image is a child face image, determining that the target face base map is a face image to be updated. Exemplarily, analyze the first face image to determine whether the first face image is a child face image. If so, determine that the target face base map matching the first face image in the face database is a face image to be updated. For example, the face database includes at least one face base map and the age information corresponding to the face base map. Determine the target face base map matching the first face image from the face database, and determine the age information corresponding to the target face base map. When the age information is less than 18 years old, determine that the first face image is a child face image. Another example is to input the first face image into a pre-trained child recognition model, and determine whether the first face image is a child face image according to the output result of the child recognition model. It can be understood that due to the continuous growth and development of children, their appearances will change slightly. Therefore, when it is determined that the first face image is a child face image, the target face base map matching the first face image in the face database can be determined as a face image to be updated. In some embodiments, based on the judgment of the age information, the time interval for the last update of the face base map can be counted. For example, when it is determined that the first face image is a child face image, the face base map that has not been updated for more than 3 months is determined as a face image to be updated.

[0034] Optionally, the face database includes at least one face base map and identification information indicating whether the at least one face base map is a face image to be updated; determining that the target face base map is a face image to be updated includes: determining the target identification information corresponding to the target face base map in the face database; when the target identification information is the identification of the face image to be updated, determining that the target face base map is a face image to be updated. Exemplarily, the face database not only includes at least one face base map, but also includes identification information indicating whether each face base map is a face image to be updated. For example, when the face base map is a child face base map or an elderly face base map or a face base map with facial defects, the identification information of the face image to be updated can be added to these face base maps in the face database. Obtain the target identification information corresponding to the target face base map that matches the first face image in the face database, and determine whether the target identification information is the identification of the face image to be updated. If so, determine that the target face base map is a face image to be updated.

[0035] When it is determined that the target face base map that matches the first face image in the face database is a face image to be updated, collect a reference face image of the first face image within a preset time period. Exemplarily, n face images collected before the acquisition time of the first face image can be used as the reference face image of the first face image, or n face images collected after the acquisition time of the first face image can be used as the reference face image of the first face image, or n face images collected before the acquisition time of the first face image and n face images collected after the acquisition time of the first face image can both be used as the reference face image of the first face image.

[0036] Optionally, collecting a reference face image of the first face image within a preset time period includes: within the preset time period, obtaining a third face image collected within a first time period before the acquisition time corresponding to the first face image and a fourth face image collected within a second time period after the acquisition time; using the third face image and the fourth face image as the reference face image of the first face image. Exemplarily, when it is determined that the target face template in the face database that matches the currently collected first face image is a face image to be updated, within the preset time period, obtain a third face image within the first time period before the acquisition time corresponding to the first face image, and a fourth face image within the second time period after the acquisition time corresponding to the first face image. Among them, the first time period and the second time period may be the same or different, and the number of third face images and the number of fourth face images may be the same or different. Both the third face image and the fourth face image are used as the reference face image of the first face image. It can be understood that when it is determined that the target face template is a face image to be updated, obtain third face images of at least one user who appeared before the target user corresponding to the first face image and fourth face images of at least one user who appeared after the target user corresponding to the first face image, and the time difference between the third face image and the first face image and the time difference between the first face image and the fourth face image are both less than a preset time threshold. That is, the reference face image of the first face image is the face image of the users who appeared before and after the target user corresponding to the first face image, and the interval time between the users who appeared before and after the target user and the target user through the face recognition system is within the preset time period.

[0037] After a preset time period, reference face images of all the first face images that match one or more face templates to be updated in the face database can be collected. Based on the face database, the reference face images are recognized, so that the users corresponding to the reference face images can be determined. Since the users corresponding to all the reference face images of the first face image may be one user or multiple users, all the users involved in all the reference face images of the first face image are used as the reference users of the target user corresponding to the first face image.

[0038] S130. Determine the intimacy of the target user with respect to each of the at least one reference user based on the reference face image, and use the reference user with the highest intimacy as the intimate user of the target user.

[0039] Optionally, determining the intimacy of the target user with respect to each of the at least one reference user based on the reference face images includes: for each of the at least one reference user, counting the number of occurrences of the reference face image corresponding to the reference user, and using the number of occurrences as the intimacy of the target user with respect to the reference user. Exemplarily, for each of the at least one reference user, counting the number of occurrences of the reference face image corresponding to the reference user, that is, counting the number of reference face images corresponding to the same reference user that appear before or after the target user within a preset time period. Using the number of occurrences of the reference face image corresponding to the reference user as the intimacy of the target user with respect to the reference user. It can be understood that the more times the reference user and the target user appear before and after each other within the preset time period, the higher the intimacy between the target user and the reference user. Exemplarily, within two weeks, the reference face images of the face image corresponding to the target user A include the face images of user B, user C, and user D, and within two weeks, two face images of user B, three face images of user C, and five face images of user D are collected. Then, it can be determined that the intimacy of the target user A with respect to the reference user B is 2, the intimacy of the target user A with respect to the reference user C is 3, and the intimacy of the target user A with respect to the reference user D is 5. In some embodiments, the intimacy can also be pre-bound. For example, children are associated with relatives such as parents according to household registration relationships, or the kinship is actively reported by relatives during initial entry.

[0040] In the embodiments of the present invention, the reference user with the highest intimacy among all the reference users of the target user is used as the intimate user of the target user. For example, if the target user is a child, the intimate user of the child, such as the guardian of the child, can be determined through the intimacy of the target user with respect to each reference user. It can be understood that since the first face image matches the target face base map in the face database, the target user corresponding to the first face image is also the user corresponding to the target face base map in the face database. Therefore, the reference user of the target user can also be understood as the reference user of the user corresponding to the target face base map in the face database.

[0041] S140. When it is detected that the update event of the target face base map is triggered, obtain the second face image of the user before or after the intimate user, and update the target face base map based on the second face image.

[0042] In an embodiment of the present invention, when an update instruction for a target face template in the face database is received from a manager, it can be determined that an update event for the target face template is triggered. Optionally, the similarity between the first face image and the target face template is obtained in real time; when it is detected that the similarity is less than a preset similarity threshold, it is determined that the update event for the target face template is triggered. Since the first face image is collected in real time and the first face image is recognized based on the face database, during the process of recognizing the first face image, the similarity between the target face template in the face database that matches the first face image and the first face image can be calculated. It can be understood that during the process of recognizing the first face image based on the face database, the similarity between the first face image and each face template in the face database can be calculated, and the face template in the face database with the largest similarity to the first face image and the largest similarity greater than the preset threshold is used as the target face template that matches the first face image. It is judged whether the similarity between the first face image and the target face template is less than the preset similarity threshold. If so, it indicates that the similarity may decrease due to a slight change in the appearance of the target user corresponding to the first face image. At this time, it is determined that the update event for the target face template is triggered.

[0043] In an embodiment of the present invention, in response to the triggering of the update event for the target face template, the second face image of the user before or after the close user of the target user corresponding to the target face template is obtained. Exemplarily, multiple second face images can be obtained within a certain time period, and the second face image with the highest image quality is selected as the current face image of the target user corresponding to the target face template, and the target face template in the face database is updated based on the second face image with the highest image quality.

[0044] Optionally, when it is detected that the update event for the target face template is triggered, obtaining the second face image of the user before or after the close user and updating the target face template based on the second face image includes: when it is detected that the update event for the target face template is triggered, obtaining at least two second face images of the user before or after the close user; judging whether the at least two second face images correspond to the same user. If so, determining the target face image with the highest image quality from the at least two second face images; and updating the target face template based on the target face image. The advantage of such a setting is that it can effectively ensure that the current high-quality face image of the target user corresponding to the target face template can be obtained, thereby ensuring the effectiveness of the update of the target face template in the face database.

[0045] Exemplarily, when the detection of the target face base map update event is triggered, if the intimate user of the target user corresponding to the target face base map is user D, then obtain the second face image of the user before or after user D, and the time interval between the acquisition time of the second face image and the acquisition time of the face image corresponding to user D is less than a preset threshold. It can be understood that the time difference between the appearance time of user D and the appearance time of the user before or after user D is less than the preset threshold. Within a certain time period, collect the second face images that meet the above conditions multiple times. That is, within a certain time period, whenever an intimate user (not limited to D, it can also be another intimate user) is detected, collect the second face image of the user who appears within the time range before and after the appearance time of the intimate user, so as to obtain multiple second face images. Determine whether the multiple second face images are of the same user. For example, calculate the similarity between the multiple second face images. If the similarity is greater than the preset threshold, it means that the multiple second face images are the face images of the same user. At this time, select the face image with the highest image quality from the multiple second face images as the target face image. Update the target face base map in the face database based on the target face image, that is, replace the target face base map in the face database with the target face image.

[0046] The face base map update method according to the embodiment of the present invention collects the first face image in real time, and performs recognition on the first face image based on the pre-stored face database, and determines the target face base map matching the first face image from the face database; when it is determined that the target face base map is the face image to be updated, collect the reference face image of the first face image within a preset time period, and determine at least one reference user of the target user corresponding to the first face image based on the reference face image; determine the intimacy of the target user relative to each reference user among the at least one reference user based on the reference face image, and use the reference user with the greatest intimacy as the intimate user of the target user; when it is detected that the update event of the target face base map is triggered, obtain the second face image of the user before or after the intimate user, and update the target face base map based on the second face image. Through the technical solution provided by the embodiment of the present invention, the face base map to be updated in the face database can be automatically updated, thereby effectively improving the accuracy of face recognition.

[0047] Embodiment 2

[0048] Figure 2 It is a flowchart of a face base map update method provided by Embodiment 2 of the present invention. As Figure 2 shown, the method includes:

[0049] S210. Collect the first face image in real time, identify the first face image based on the pre-stored face database, and determine the target face template matching the first face image from the face database.

[0050] S220. Determine whether the first face image is a child face image. If so, execute S230; otherwise, execute S210.

[0051] S230. Determine the target face template as the face image to be updated.

[0052] S240. Within a preset time period, obtain the third face image collected within the first time period before the collection time corresponding to the first face image and the fourth face image collected within the second time period after the collection time.

[0053] S250. Use the third face image and the fourth face image as the reference face images of the first face image.

[0054] S260. Determine at least one reference user of the target user corresponding to the first face image based on the reference face images.

[0055] S270. For each reference user among the at least one reference user, count the number of occurrences of the reference face image corresponding to the reference user, and use the number of occurrences as the intimacy degree of the target user relative to the reference user.

[0056] S280. Use the reference user with the highest intimacy degree as the intimate user of the target user.

[0057] S290. When it is detected that the update event of the target face template is triggered, obtain the second face images of at least two users before or after the intimate user.

[0058] S2100. When at least two second face images correspond to the same user, determine the target face image with the highest image quality from the at least two second face images, and update the target face template based on the target face image.

[0059] Through the face template update method provided by the embodiments of the present invention, the child face templates in the face database can be automatically updated, thereby effectively improving the accuracy of child face recognition.

[0060] Embodiment III

[0061] Figure 3 It is a schematic structural diagram of a face template update device provided by Embodiment III of the present invention.

[0062] As Figure 3 shown, the device includes:

[0063] The target face base map determination module 310 is configured to collect the first face image in real time, identify the first face image based on a pre-stored face database, and determine a target face base map that matches the first face image from the face database;

[0064] The reference face image determination module 320 is configured to, when it is determined that the target face base map is a face image to be updated, collect a reference face image of the first face image within a preset time period, and determine at least one reference user of the target user corresponding to the first face image based on the reference face image;

[0065] The intimate user determination module 330 is configured to determine the intimacy of the target user with respect to each reference user among the at least one reference user based on the reference face image, and use the reference user with the maximum intimacy as the intimate user of the target user;

[0066] The face base map update module 340 is configured to, when it is detected that an update event of the target face base map is triggered, obtain a second face image of the user before or after the intimate user, and update the target face base map based on the second face image.

[0067] Optionally, the reference face image determination module is configured to:

[0068] When it is determined that the first face image is a child face image, determine that the target face base map is a face image to be updated.

[0069] Optionally, the face database includes at least one face base map and identification information on whether the at least one face base map is a face image to be updated;

[0070] The reference face image determination module is configured to:

[0071] Determine the target identification information corresponding to the target face base map in the face database;

[0072] When the target identification information is an identification of a face image to be updated, determine that the target face base map is a face image to be updated.

[0073] Optionally, the reference face image determination module is configured to:

[0074] Within the preset time period, obtain a third face image collected within a first time period before the acquisition moment corresponding to the first face image and a fourth face image collected within a second time period after the acquisition moment;

[0075] Use the third face image and the fourth face image as the reference face image of the first face image.

[0076] Optionally, the intimate user determination module is configured to:

[0077] For each reference user among the at least one reference user, count the number of occurrences of the reference face image corresponding to the reference user, and use the number of occurrences as the intimacy of the target user relative to the reference user.

[0078] Optionally, the face background map update module is configured to:

[0079] Obtain the similarity between the first face image and the target face background map in real time;

[0080] When it is detected that the similarity is less than a preset similarity threshold, determine that the update event of the target face background map is triggered.

[0081] Optionally, the face background map update module is configured to:

[0082] When it is detected that the update event of the target face background map is triggered, obtain at least two second face images of the users before or after the intimate user;

[0083] Determine whether the at least two second face images correspond to the same user. If so, determine the target face image with the highest image quality from the at least two second face images;

[0084] Update the target face background map based on the target face image.

[0085] The face background map update device provided by the embodiments of the present invention can execute the face background map update method provided by any embodiment of the present invention, and has the corresponding functional modules and beneficial effects for executing the method.

[0086] Embodiment 4

[0087] Figure 4 FIG. shows a schematic structural diagram of a face recognition system 10 that can be used to implement the embodiments of the present invention. The face recognition system is intended to represent various forms of digital computers, such as, laptop computers, desktop computers, workstations, personal digital assistants, servers, blade servers, mainframe computers, and other suitable computers. The face recognition system can also represent various forms of mobile devices, such as, personal digital processors, cellular phones, smart phones, wearable devices (such as helmets, glasses, watches, etc.) and other similar computing devices. The components shown herein, their connections and relationships, and their functions are only examples and are not intended to limit the implementation of the present invention described herein and / or claimed.

[0088] As Figure 4As shown, the face recognition system 10 includes at least one processor 11 and a memory communicatively connected to the at least one processor 11, such as a read-only memory (ROM) 12, a random access memory (RAM) 13, etc. The memory stores a computer program executable by the at least one processor. The processor 11 can perform various appropriate actions and processes according to the computer program stored in the read-only memory (ROM) 12 or the computer program loaded from the storage unit 18 into the random access memory (RAM) 13. In the RAM 13, various programs and data required for the operation of the face recognition system 10 can also be stored. The processor 11, the ROM 12, and the RAM 13 are connected to each other via a bus 14. An input / output (I / O) interface 15 is also connected to the bus 14.

[0089] Multiple components in the face recognition system 10 are connected to the I / O interface 15, including: an input unit 16, such as a keyboard, a mouse, etc.; an output unit 17, such as various types of displays, speakers, etc.; a storage unit 18, such as a magnetic disk, an optical disc, etc.; and a communication unit 19, such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 19 allows the face recognition system 10 to exchange information / data with other devices via a computer network such as the Internet and / or various telecommunication networks.

[0090] The processor 11 can be various general-purpose and / or special-purpose processing components with processing and computing capabilities. Some examples of the processor 11 include but are not limited to a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various processors running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The processor 11 executes the various methods and processes described above, such as the face base map update method.

[0091] In some embodiments, the face base map update method can be implemented as a computer program tangibly embodied in a computer-readable storage medium, such as the storage unit 18. In some embodiments, part or all of the computer program can be loaded and / or installed onto the face recognition system 10 via the ROM 12 and / or the communication unit 19. When the computer program is loaded into the RAM 13 and executed by the processor 11, one or more steps of the face base map update method described above can be executed. Alternatively, in other embodiments, the processor 11 can be configured to execute the face base map update method by any other appropriate means (e.g., by means of firmware).

[0092] The various embodiments of the systems and techniques described above in this specification can be implemented in digital electronic circuitry, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on a chip (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various embodiments can include: being implemented in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be a special-purpose or general-purpose programmable processor that receives data and instructions from, and transmits data and instructions to, a storage system, at least one input device, and at least one output device.

[0093] The computer program for implementing the methods of the present invention can be written in any combination of one or more programming languages. These computer programs can be provided to a processor of a general purpose computer, special purpose computer, or other programmable data processing apparatus, such that the computer programs, when executed by the processor, cause the functions / operations specified in the flowchart and / or block diagram to be implemented. The computer program can be executed entirely on the machine, partly on the machine, as a stand-alone software package partly on the machine and partly on a remote machine or entirely on the remote machine or server.

[0094] In the context of the present invention, a computer-readable storage medium can be a tangible medium that can contain, or store a computer program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable storage medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor systems, apparatus, or devices, or any suitable combination of the foregoing. Alternatively, the computer-readable storage medium can be a machine-readable signal medium. More specific examples of the machine-readable storage medium would include an electrical connection based on one or more wires, a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0095] To provide interaction with a user, the systems and techniques described herein can be implemented on a face recognition system having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the face recognition system. Other kinds of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0096] The systems and techniques described herein can be implemented in a computing system including backend components (e.g., as a data server), or a computing system including middleware components (e.g., an application server), or a computing system including frontend components (e.g., a user computer having a graphical user interface or a web browser through which the user can interact with an implementation of the systems and techniques described herein), or a computing system including any combination of such backend components, middleware components, or frontend components. The components of the system can be interconnected by digital data communication in any form or medium (e.g., a communication network). Examples of communication networks include: local area network (LAN), wide area network (WAN), blockchain network, and the Internet.

[0097] The computing system can include a client and a server. The client and the server are generally remote from each other and typically interact through a communication network. The client-server relationship is created by computer programs running on the respective computers and having a client-server relationship with each other. The server can be a cloud server, also known as a cloud computing server or a cloud host, which is a host product in the cloud computing service system and solves the defects of difficult management and weak business scalability existing in traditional physical hosts and VPS services.

[0098] It should be understood that various forms of the processes shown above can be used, reordering, adding, or deleting steps. For example, the steps recited in the present invention can be executed in parallel, sequentially, or in a different order, as long as the desired results of the technical solution of the present invention can be achieved, and no limitation is made herein.

[0099] The above specific embodiments do not constitute a limitation on the protection scope of the present invention. Those skilled in the art should understand that various modifications, combinations, sub-combinations, and substitutions can be made according to design requirements and other factors. Any modifications, equivalent substitutions, and improvements made within the spirit and principle of the present invention shall be included within the protection scope of the present invention.

Claims

1. A method for updating a face base map, characterized in that, Including: Collect the first face image in real time, and identify the first face image based on the pre-stored face database, and determine a target face template matching the first face image from the face database; When it is determined that the target face template is a face image to be updated, collect a reference face image of the first face image within a preset time period, and determine at least one reference user of the target user corresponding to the first face image based on the reference face image; Determine the intimacy of the target user with respect to each of the at least one reference user based on the reference face image, and use the reference user with the highest intimacy as the intimate user of the target user; When it is detected that the update event of the target face template is triggered, obtain a second face image of the user before or after the intimate user, and update the target face template based on the second face image.

2. The method according to claim 1, characterized in that, Determining that the target face template is a face image to be updated includes: When it is determined that the first face image is a child face image, determine that the target face template is a face image to be updated.

3. The method according to claim 1, characterized in that, The face database contains at least one face template and identification information on whether the at least one face template is a face image to be updated; Determining that the target face template is a face image to be updated includes: Determine the target identification information corresponding to the target face template in the face database; When the target identification information is an identification of a face image to be updated, determine that the target face template is a face image to be updated.

4. The method according to claim 1, characterized in that, Collecting a reference face image of the first face image within a preset time period includes: Within the preset time period, obtain a third face image collected within a first time period before the acquisition time corresponding to the first face image and a fourth face image collected within a second time period after the acquisition time; Use the third face image and the fourth face image as the reference face image of the first face image.

5. The method according to claim 1, characterized in that, Determining the intimacy of the target user with respect to each of the at least one reference user based on the reference face image includes: For each of the at least one reference user, count the number of occurrences of the reference face image corresponding to the reference user, and use the number of occurrences as the intimacy of the target user with respect to the reference user.

6. The method according to claim 1, characterized in that, Detecting that the update event of the target face template is triggered includes: Obtain the similarity between the first face image and the target face template in real time; When it is detected that the similarity is less than a preset similarity threshold, determine that the update event of the target face template is triggered.

7. The method according to claim 1, characterized in that, When it is detected that the update event of the target face template is triggered, obtain a second face image of the user before or after the intimate user, and update the target face template based on the second face image, includes: When it is detected that the update event of the target face template is triggered, obtain at least two second face images of the user before or after the intimate user; Determine whether the at least two second face images correspond to the same user. If so, determine the target face image with the highest image quality from the at least two second face images; Update the target face base map based on the target face image.

8. A face base map updating device, characterized in that, It includes: A target face base map determination module, configured to collect first face images in real time, and identify the first face images based on a pre-stored face database, and determine a target face base map matching the first face images from the face database; A reference face image determination module, configured to, when determining that the target face base map is a face image to be updated, collect reference face images of the first face images within a preset time period, and determine at least one reference user of the target user corresponding to the first face images based on the reference face images; An intimate user determination module, configured to determine the intimacy of the target user with respect to each reference user among the at least one reference user based on the reference face images, and use the reference user with the maximum intimacy as the intimate user of the target user; A face base map update module, configured to, when detecting that an update event of the target face base map is triggered, obtain second face images of the user before or after the intimate user, and update the target face base map based on the second face images.

9. A face recognition system, characterized in that, The face recognition system includes: At least one processor; and A memory communicatively connected to the at least one processor; wherein, The memory stores a computer program executable by the at least one processor, and the computer program is executed by the at least one processor so that the at least one processor can execute the face base map update method according to any one of claims 1-7.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores computer instructions for causing a processor to implement the face base map update method according to any one of claims 1-7 when executed.

Images