WO2023173661A1 - 人脸识别方法及装置、电子设备、存储介质、计算机程序、计算机程序产品 - Google Patents

人脸识别方法及装置、电子设备、存储介质、计算机程序、计算机程序产品 Download PDF

Info

Publication number
WO2023173661A1
WO2023173661A1 PCT/CN2022/110281 CN2022110281W WO2023173661A1 WO 2023173661 A1 WO2023173661 A1 WO 2023173661A1 CN 2022110281 W CN2022110281 W CN 2022110281W WO 2023173661 A1 WO2023173661 A1 WO 2023173661A1
Authority
WO
WIPO (PCT)
Prior art keywords
signal
target
face information
preset
face recognition
Prior art date
Application number
PCT/CN2022/110281
Other languages
English (en)
French (fr)
Inventor
程前
杨浩
张帅
伊帅
Original Assignee
上海商汤智能科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 上海商汤智能科技有限公司 filed Critical 上海商汤智能科技有限公司
Publication of WO2023173661A1 publication Critical patent/WO2023173661A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/23—Updating
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
    • G06F16/24—Querying
    • G06F16/245—Query processing
    • G06F16/2455—Query execution
    • G06F16/24552—Database cache management
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
    • G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
    • G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
    • G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q20/00—Payment architectures, schemes or protocols
    • G06Q20/38—Payment protocols; Details thereof
    • G06Q20/40—Authorisation, e.g. identification of payer or payee, verification of customer or shop credentials; Review and approval of payers, e.g. check credit lines or negative lists
    • G06Q20/401—Transaction verification
    • G06Q20/4014—Identity check for transactions
    • G06Q20/40145—Biometric identity checks

Definitions

  • the present disclosure relates to but is not limited to the technical field of face recognition, and in particular, to a face recognition method and device, electronic equipment, storage media, computer programs, and computer program products.
  • Face recognition is a biometric technology that performs identity recognition based on people's facial feature information.
  • the face recognition system faces a very large number of objects. It needs to accurately identify objects from tens of millions or even hundreds of millions of objects. Find the object undergoing face recognition; since the face recognition process requires face comparison in a large range of object libraries, the efficiency of face recognition is low.
  • the present disclosure provides a face recognition method and device, electronic equipment, storage media, computer programs, and computer program products, which can reduce the face comparison range in the face recognition process and improve the efficiency of face recognition.
  • the technical solutions of the present disclosure are as follows:
  • Embodiments of the present disclosure provide a face recognition method, including:
  • the target signal is a communication signal that stays in the target area for a duration greater than or equal to a preset duration
  • the target device Based on the device identification of the target device, obtain the preset face information corresponding to the target signal, and cache the preset face information in a local cache;
  • the target device is the device that sends the target signal;
  • the face information to be recognized of the object to be recognized is compared with the preset face information in the local cache to obtain the face recognition result corresponding to the object to be recognized.
  • the communication signal whose stay duration in the target area is greater than or equal to the preset duration is the target signal, and the preset face information corresponding to the target signal is obtained, and the preset face information is obtained.
  • the face information is cached in the local cache, so that when performing face recognition, the face information to be recognized can first be compared with the preset face information in the local cache to further narrow the scope of face comparison and improve the facial recognition quality. The efficiency of face recognition.
  • An embodiment of the present disclosure provides a face recognition device, including:
  • the first acquisition module is configured to acquire a target signal;
  • the target signal is a communication signal that stays in the target area for a duration greater than or equal to a preset duration;
  • the second acquisition module is configured to acquire the preset face information corresponding to the target signal based on the device identification of the target device, and cache the preset face information in a local cache; the target device is to send the Target signal equipment;
  • the face recognition module is configured to compare the face information to be recognized of the object to be recognized with the preset face information in the local cache to obtain the face recognition result corresponding to the object to be recognized.
  • An embodiment of the present disclosure provides an electronic device, including: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement any of the above. method described.
  • Embodiments of the present disclosure provide a computer-readable storage medium.
  • the electronic device can perform any of the above methods in the embodiments of the present disclosure.
  • Embodiments of the present disclosure provide a computer program that includes computer readable code.
  • the computer readable code is read and executed by a computer, part of the method in any embodiment of the present disclosure is implemented or All steps.
  • Embodiments of the present disclosure provide a computer program product.
  • the computer program product includes a non-transitory computer-readable storage medium storing a computer program.
  • any embodiment of the present disclosure is implemented. some or all of the steps in the method.
  • Figure 1 is a schematic diagram of an implementation environment according to an exemplary embodiment.
  • Figure 2 is a flow chart of a face recognition method according to an exemplary embodiment.
  • Figure 3 is a flow chart of a target signal determination method according to an exemplary embodiment.
  • Figure 4 is a flow chart of a face information matching method according to an exemplary embodiment.
  • Figure 5 is a flow chart of a face information matching priority adjustment method according to an exemplary embodiment.
  • Figure 6 is a flow chart of a resource transfer method according to an exemplary embodiment.
  • Figure 7 is a schematic diagram of a face recognition device according to an exemplary embodiment.
  • FIG. 8 is a block diagram of an electronic device for face recognition according to an exemplary embodiment.
  • FIG. 1 is a schematic diagram of an application environment according to an exemplary embodiment.
  • the application environment may include a face recognition front end 100 and a face recognition back end 200 .
  • the face recognition front-end 100 can be used to collect the face information of the object to be recognized to obtain the face information to be recognized; and then compare the face information to be recognized with the locally cached preset face information to obtain the face recognition result;
  • the face recognition backend 200 can be used to store and manage all face recognition information.
  • the preset face information cached locally by the face recognition front end 100 can be obtained from the face before the face recognition front end 100 performs face recognition.
  • the identification backend 200 obtains and caches them locally.
  • the face recognition front end 100 can be a device with face information collection and face recognition functions, which can include but is not limited to smartphones, desktop computers, tablets, laptops, smart speakers, digital assistants, enhanced Reality (Augmented Reality, AR)/Virtual Reality (VR) devices, smart wearable devices and other types of electronic devices.
  • the operating system running on the electronic device may include but is not limited to Android system, IOS system, Linux, Windows, etc.
  • the face recognition backend 200 can be an independent server, or a server cluster or distributed system composed of multiple servers.
  • face recognition front-end 100 and face recognition back-end 200 can be connected directly or indirectly through wired or wireless communication methods, and the disclosure is not limited here.
  • FIG. 2 is a flow chart of a face recognition method according to an exemplary embodiment.
  • the face recognition method can be used in electronic devices such as terminals, servers, edge computing nodes, etc., and can be the above Face recognition front-end.
  • the electronic device can also be user equipment (User Equipment, UE), mobile device, user terminal, cellular phone, cordless phone, personal digital assistant (Personal Digital Assistant, PDA), handheld device, computing device, vehicle-mounted device, wearable device Equipment etc.
  • the face recognition method can be implemented by a processor calling computer-readable instructions stored in a memory. The method can include:
  • the target signal is a communication signal that stays in the target area for a duration greater than or equal to a preset duration.
  • the target area can be an area that is suitable for the face recognition scene.
  • the target area can be determined based on the data processing capabilities of the face recognition front-end. For example, when the data processing index of the face recognition front-end is greater than or equal to the preset processing index, determine The range of the target area is the first range; when the data processing index of the face recognition front-end is less than the preset processing index, the range of the target area is determined to be the second range, where the first range is greater than the second range, and the communication within the first range The number of signals is greater than the number of communication signals within the second range.
  • the target area can also be determined based on the signal density of the communication signal.
  • an area with a signal density greater than or equal to the preset density can be determined as the target area.
  • the signal density can be determined based on the number of communication signals in the target area and the scope of the target area. That is, the area where the signal density of the communication signal is greater than the preset density may have gathered objects that need to be identified for face recognition, so that the communication signals in the area can be processed, and the objects to be identified corresponding to these communication signals can be identified as quickly as possible. Face recognition.
  • the target signal can be determined from the communication signals in the target area.
  • the communication signal that stays in the target area for longer than or equal to the preset time period can be determined as the target signal; the target signal It is emitted by the target device of the object to be identified.
  • the duration of the target signal staying in the target area is greater than or equal to the preset duration, which can indicate that the object to be identified corresponding to the target signal has the intention of performing face recognition, so that further processing can be performed based on the target signal. deal with.
  • S220 Based on the device identification of the target device, obtain the preset face information corresponding to the target signal, and cache the preset face information in a local cache; the target device is the device that sends the target signal.
  • the preset face information corresponding to the target signal can be obtained from the face recognition backend based on the device identification of the target device in advance, and cached locally.
  • the face information to be recognized can be compared with the locally cached preset face information.
  • the face recognition backend maintains a full face information database.
  • the full face information database stores the corresponding relationship between face information and device identification. Therefore, when the device identification of the target device is known, it can be based on the target device's identification.
  • the device identification determines the preset face information corresponding to the target signal; the corresponding relationship between the face information and the device identification may be created when each object registers in the face recognition system.
  • the face recognition system can notify each subject to update the face information at a preset time interval, thereby re-creating the updated face information and Correspondence between device identifiers.
  • the device identification in the full face information database is updated, so as to re- Create an updated correspondence between the device identification and the face information.
  • the collected face information to be recognized can be compared with the preset face information in the local cache to obtain the corresponding face recognition results.
  • the communication signal whose stay duration in the target area is greater than or equal to the preset duration is the target signal, and the preset face information corresponding to the target signal is obtained, and the preset face information is obtained.
  • the face information is cached in the local cache, so that when performing face recognition, the face information to be recognized can first be compared with the preset face information in the local cache to further narrow the scope of face comparison and improve the facial recognition quality. The efficiency of face recognition.
  • the target signal can be determined based on the signal detection results of multiple detection periods; please refer to Figure 3, which shows a target signal determination method, which method can include:
  • S320 Compare the communication signal in the current detection period with the communication signal in the previous detection period to obtain a repeated signal, wherein the previous detection period is before the current detection period and is the same as the previous detection period. The detection period adjacent to the current detection period.
  • S330 Accumulate the historical accumulated residence time of the repetitive signal in the target area and the detection period interval to obtain the current accumulated residence time of the repeated signal.
  • the detection period can be a period for detecting communication signals in the target area, and the detection period interval can be a preset interval; in each detection period, the communication signals in the current detection period and the communication signals in the previous detection period are compared. By comparison, the communication signals that are detected in the current detection cycle and the communication signals that are detected in the previous detection cycle are determined as repeated signals; where the previous detection cycle can be before the current detection cycle and is the same as For detection cycles adjacent to the current detection cycle, the detection cycle interval may be the time interval between the end time of the previous detection cycle and the start time of the current detection cycle.
  • the repetitive signal in this embodiment may be a communication signal that is detected in at least two detection periods. If the communication signal is detected in two consecutive detection periods, the communication signal may be detected in the second detection period. Determined as a repetitive signal; if the communication signal is not detected in the third detection cycle, the communication signal is no longer a repetitive signal; if the communication signal is detected again in the fourth detection cycle, the communication signal is not Repeating signal; if the communication signal is detected in the fourth detection period and detected again in the fifth detection period, the detection signal can be determined to be a repetitive signal in the fifth detection period.
  • the cumulative stay time of the repeated signal in the target area is calculated to obtain the current cumulative stay time of the repeated signal; for example, the current cumulative stay time can be calculated based on the historical accumulation of the repeated signal in the target area.
  • the residence time is accumulated with the detection cycle interval.
  • the historical accumulated residence time can be the residence time of the repeated signal in the target area before the end of the previous detection cycle.
  • the repetitive signal is determined as the target signal.
  • repeated signals are determined and the corresponding dwell time is calculated in each detection cycle, and the target signal is determined based on the calculation results, thereby determining the target signal in time, thereby facilitating the timely acquisition of the preset person corresponding to the target signal.
  • Face information achieving periodic acquisition of preset face information and timely updating of preset face information in the local cache.
  • multiple target signals there may be multiple target signals, so that multiple preset face information corresponding to multiple target signals may be cached in the local cache.
  • multiple preset face information may be determined.
  • the matching sequence of face information please refer to Figure 4, which shows a face information matching method.
  • Multiple preset face information can have their corresponding matching priorities, and the target signal can also include the signal of the target signal. Intensity so that the method may include:
  • S410 Determine the matching priority of each item of the preset face information based on the signal strength change information of the target signal.
  • S420 Match the face information to be recognized with each item of preset face information according to the matching priority of each item of preset face information from high to low to obtain the face recognition result. .
  • the signal strength change information of the target signal can represent the distance change information between the target device corresponding to the target signal and the face recognition front-end, and the distance change information between the target device and the face recognition front-end is adapted to the face recognition intention of the object to be recognized. .
  • the distance between the object to be recognized and the face recognition front-end may be getting closer and closer, that is, it may be in a waiting state for face recognition.
  • the preset person corresponding to the target signal can be increased.
  • the matching priority of face information when the slight signal change information of the target signal gradually weakens, the distance between the object to be recognized and the front end of face recognition may be getting farther and farther, which means that the object to be recognized does not have a face in a short period of time.
  • the matching priority of the preset face information corresponding to the target signal can be reduced; and then the matching priority of each preset face information can be determined.
  • the face information is matched in the order of matching priority from high to low.
  • the preset face information with the highest matching priority can be used first.
  • the face information to be recognized is matched. If the match is successful, the face recognition is determined to be successful; if the match fails, the preset face information with the next matching priority is used to match the face information to be recognized, and so on, we get Face recognition results of the object to be recognized.
  • the matching priority is determined based on the intensity change information of the target signal, so that face matching is performed based on the order of matching priority from high to low, which can further improve the efficiency of face recognition.
  • the signal strength change information of the target signal can be determined based on changes in signal strength within a continuous time period; please refer to Figure 5, which shows a face information matching priority adjustment method. Methods may include:
  • S510 Obtain the signal strength of the target signal within a preset number of consecutive detection periods.
  • S520 Determine the signal strength change information of the target signal based on the signal strength of the target signal within a consecutive preset number of detection periods.
  • the preset number can be two or more, so that when determining the signal strength change information of the target signal, the target signal can be detected in each detection cycle to obtain the corresponding signal strength of the target signal. , and then determine the signal strength change information of the target signal based on the signal strength of the target signal within a consecutive preset number of detection periods.
  • the signal strength of the target signal can be determined by the signal strength value or the signal strength level identification, so that the target signal can further be determined by the signal strength value change information or the signal strength level identification change information of the target signal within a consecutive preset number of detection cycles.
  • signal strength change information Determine the target signal strength when the signal strength value of the target signal gradually increases within a consecutive preset number of detection periods, or when the signal strength level identification gradually changes to a high intensity level identification within a continuous preset number of detection periods.
  • the change information is that the signal strength gradually increases; when the signal strength value of the target signal gradually decreases within a continuous preset number of detection cycles, or the signal strength level mark within a continuous preset number of detection cycles gradually changes to a low intensity level. When marked, determine the target signal strength change information as the signal strength gradually decreases.
  • the signal strength of the target signal detected in two consecutive detection cycles gradually increases.
  • the target signal can be temporarily not processed, and detection can continue in the fourth detection cycle.
  • the signal strength of the target signal When the signal strength in the fourth detection period increases and is greater than the signal strength in the second detection period, the signal strength detected in the third detection period can be ignored, and it is determined that the signal strength of the target signal gradually increases;
  • the signal strength detected in the third detection cycle may be due to an error in the detection result caused by interference factors, thereby reducing errors in determining signal strength change information due to the presence of interference factors and improving the accuracy of determining signal change information.
  • the situation where the signal strength of the target signal gradually weakens is similar and will not be described again here.
  • the matching priority of the preset face information corresponding to the target signal is increased; when the signal strength change information indicates that the signal strength of the target signal gradually weakens, the matching priority of the target signal is reduced.
  • the matching priority of the preset facial information is increased.
  • the change information of the target signal strength can be used to represent the change information of the face recognition intention of the object to be recognized, and then the matching priority of the preset face information can be reasonably adjusted based on the signal strength change information, so that the preset face information
  • the matching priority matches the face recognition intention of the object to be recognized, thereby improving the face recognition efficiency.
  • the face recognition method provided in this embodiment can also be applied to resource transfer scenarios.
  • the method may include:
  • S620 Perform resource transfer processing based on the target account.
  • corresponding resource transfer operations need to be performed based on the face recognition results.
  • Face recognition can be used as the object identity verification for resource transfer.
  • the object to be identified passes the face recognition, the object to be identified is completed.
  • Authentication In the resource transfer system, the association between the human face information and the target account can be stored, so that the associated target account can be determined based on the successfully matched target face information, and then the object to be identified can perform resource transfer operations based on the target account.
  • the face recognition method is applied to the resource transfer scenario.
  • the face recognition method provided by this embodiment can improve the face recognition efficiency, applying it to the resource transfer scenario can improve the efficiency of resource transfer.
  • Efficiency on the other hand, resource transfer can only be carried out through face recognition, thus improving the security of resource transfer.
  • the above face recognition method may also include:
  • At least one piece of preset face information can be deleted from the local cache.
  • it can reduce the number of preset face information and further narrow the information comparison range, thereby improving Facial recognition efficiency; on the other hand, deleting preset face information from the local cache can reduce the pressure on the local end of information caching and further improve the local end's data processing efficiency.
  • the above face recognition method also includes:
  • the target face information is deleted from the local cache.
  • the object to be recognized corresponding to the target face information may not undergo face recognition again in a short period of time, and it can be deleted from the local cache.
  • it can reduce the amount of preset face information and further narrow the range of information comparison, thereby improving the efficiency of face recognition; on the other hand, by deleting face information, it can reduce the information storage pressure on the local end and improve the data processing efficiency on the local end. .
  • the face recognition method is applied to a payment terminal, and the payment terminal includes:
  • Main control chip memory, network communication module, wireless probe, main touch screen, secondary touch screen, and lens module;
  • the main control chip, the memory, the network communication module, and the wireless probe are integrated on the circuit board, and the main touch screen, the secondary touch screen, and the lens module are fixed by a bracket.
  • the wireless probe of the payment terminal can detect the communication signal sent by the smart device in the target area and determine the target signal in the target area; and then use the network communication module to obtain the target signal from the face.
  • the recognition backend obtains the preset face information corresponding to the target signal, and the memory caches the preset face information.
  • the payment information is confirmed through the secondary touch screen.
  • the lens module collects the face information of the subject to be recognized and obtains the face information to be recognized.
  • the subject to be recognized faces the main touch screen and operates to perform face recognition; main control
  • the chip compares the face information to be recognized with the preset face information in the cache to obtain the face recognition results, and sends the face recognition results and payment results to the face recognition backend.
  • the payment terminal in this embodiment can be used in scenarios such as smart retail or station ticket checking.
  • the face recognition method is applied to the payment terminal, and the object to be identified can complete face recognition and payment operations based on the payment terminal.
  • the face recognition method realizes the practical application of the face recognition method, and on the other hand, it can improve the payment process. efficiency.
  • Figure 7 is a face recognition device according to an exemplary embodiment, including:
  • the first acquisition module 710 is configured to acquire the target signal; the target signal is a communication signal that stays in the target area for a duration greater than or equal to the preset duration; the second acquisition module 720 is configured to acquire the target signal based on the device identification of the target device.
  • the preset face information corresponding to the target signal is cached in a local cache; the target device is the device that sends the target signal; the face recognition module 730 is configured to cache the preset face information to be recognized The face information to be recognized of the object is compared with the preset face information in the local cache to obtain the face recognition result corresponding to the object to be recognized.
  • the device further includes: a communication signal acquisition module configured to acquire the communication signal in the target area within the current detection period; a signal comparison module configured to obtain the communication signal within the current detection period.
  • the communication signal is compared with the communication signal in the previous detection period to obtain a repeated signal, wherein the previous detection period is the detection period before the current detection period and adjacent to the current detection period;
  • the residence time calculation module is configured to accumulate the historical accumulated residence time of the repetitive signal in the target area with the detection period interval to obtain the current accumulated residence time of the repeated signal;
  • the target signal determination module is configured as If the current cumulative stay duration of the repetitive signal is greater than or equal to the preset duration, the repetitive signal is determined to be the target signal.
  • the preset face information has a matching priority
  • the target signal includes the signal strength of the target signal
  • the face recognition module 730 includes: a matching priority determination module, The information matching module is configured to determine the matching priority of each item of the preset face information based on the signal strength change information of the target signal; the information matching module is configured to determine the matching priority of each item of the preset face information from high to high based on the signal strength change information of the target signal.
  • the face information to be recognized is matched with each item of the preset face information to obtain the face recognition result.
  • the matching priority determination module includes: a signal strength acquisition module configured to acquire the signal strength of the target signal within a continuous preset number of detection cycles; a signal strength change information determination module, configured to determine the signal strength change information of the target signal based on the signal strength of the target signal within a consecutive preset number of detection cycles; a matching priority adjustment module configured to adjust the signal strength change information based on the signal strength change information The matching priority of the preset face information corresponding to the target signal.
  • the device further includes: a target account determination module configured to match the face information corresponding to the face to be recognized in the preset face information when the face recognition result indicates When the target face information is obtained, the target account associated with the target face information is determined; the resource transfer module is configured to perform resource transfer processing based on the target account.
  • the device further includes: a first deletion module configured to delete at least one item from the local cache according to the cache time when a comparison delay occurs during the face recognition process. Item preset face information.
  • the device further includes: a second deletion module configured to match the face information corresponding to the face to be recognized in the preset face information when the face recognition result indicates When the target face information is obtained, the target face information is deleted from the local cache.
  • a second deletion module configured to match the face information corresponding to the face to be recognized in the preset face information when the face recognition result indicates When the target face information is obtained, the target face information is deleted from the local cache.
  • the face recognition device is applied to a payment terminal
  • the payment terminal includes: a main control chip, a memory, a network communication module, a wireless probe, a main touch screen, a secondary touch screen, and a lens module ;
  • the main control chip, the memory, the network communication module, and the wireless probe are integrated on the circuit board, and the main touch screen, the secondary touch screen, and the lens module are fixed by a bracket.
  • FIG. 8 is a block diagram of an electronic device for face recognition according to an exemplary embodiment.
  • the electronic device (800) may be a terminal, and its internal structure diagram may be as shown in FIG. 8 .
  • the electronic device (800) includes a processor (802), memory, network interface (803), display (804) and input device (805) connected through a system bus (801).
  • the processor (802) of the electronic device (800) is used to provide computing and control capabilities.
  • the memory of the electronic device (800) includes a non-volatile storage medium (806) and internal memory (807).
  • the non-volatile storage medium (806) stores an operating system (8061) and a computer program (8062).
  • the internal memory (807) provides an environment for the execution of the operating system (8061) and computer programs (8062) in the non-volatile storage medium (806).
  • the network interface (803) of the electronic device (800) is used to communicate with an external terminal through a network connection.
  • the computer program (8062) is executed by the processor (802) to implement a face recognition method.
  • the display (804) of the electronic device (800) can be a liquid crystal display or an electronic ink display, and the input device (805) of the electronic device (800) can be a touch layer covered on the display screen, or it can be an electronic device ( 800)
  • the buttons, trackball or touch pad provided on the casing can also be an external keyboard, touch pad or mouse.
  • FIG. 8 is only a block diagram of a partial structure related to the disclosed solution, and does not constitute a limitation on the electronic equipment to which the disclosed solution is applied.
  • Specific electronic devices can May include more or fewer parts than shown, or combine certain parts, or have a different arrangement of parts.
  • an electronic device including: a processor; a memory for storing instructions executable by the processor; wherein the processor is configured to execute the instructions to implement implementations as described in the present disclosure. Face recognition method in the example.
  • a computer-readable storage medium is also provided.
  • the instructions in the computer-readable storage medium are executed by a processor of the electronic device, the electronic device can perform the face recognition method in the embodiment of the present disclosure. recognition methods.
  • a computer-readable storage medium may be a tangible device that can retain and store instructions for use by an instruction execution device, and may be a volatile storage medium or a non-volatile storage medium.
  • the computer-readable storage medium may be, for example, but not limited to, an electronic storage device, a magnetic storage device, an optical storage device, an electromagnetic storage device, a semiconductor storage device, or any suitable combination of the above.
  • Non-exhaustive list of computer-readable storage media include: portable computer disks, hard disks, random access memory (RAM), read-only memory (ROM), Erasable programmable read-only memory (EPROM or flash memory), static random access memory (SRAM), portable compact disk read-only memory (CD-ROM), digital versatile disk (DVD), memory stick, floppy disk, mechanical encoding equipment , such as a punched card or a raised structure in a groove with instructions stored thereon, and any suitable combination of the above.
  • RAM random access memory
  • ROM read-only memory
  • EPROM or flash memory Erasable programmable read-only memory
  • SRAM static random access memory
  • CD-ROM compact disk read-only memory
  • DVD digital versatile disk
  • memory stick floppy disk
  • mechanical encoding equipment such as a punched card or a raised structure in a groove with instructions stored thereon, and any suitable combination of the above.
  • computer-readable storage media are not to be construed as transient signals per se, such as radio waves or other freely propagating electromagnetic waves, electromagnetic waves propagating through waveguides or other transmission media (e.g., light pulses through fiber optic cables), or through electrical wires transmitted electrical signals.
  • Embodiments of the present disclosure also provide a computer program.
  • the computer program includes computer readable code.
  • the computer readable code is read and executed by a computer, part of the method in any embodiment of the present disclosure is implemented. or all steps.
  • Embodiments of the present disclosure also provide a computer program product, including computer readable code, or a non-volatile computer readable storage medium carrying the computer readable code.
  • computer readable code When the computer readable code is stored in a processor of an electronic device, When running, the processor in the electronic device executes part or all of the steps of the above method.
  • Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (Erasable Programmable Read-Only Memory, EPROM), electrically erasable programmable ROM (Electrically Erasable Programmable Read Only Memory) ,EEPROM) or flash memory.
  • Volatile memory may include random access memory (RAM) or external cache memory.
  • RAM is available in many forms, such as Static Random-Access Memory (SRAM), Dynamic Random Access Memory (DRAM), and Synchronous Dynamic Random-Access Memory (SDRAM).
  • Double-Data-Rate Two Synchronous Dynamic Random Access Memory DDRSDRAM
  • Enhanced SDRAM Enhanced Synchronous Dynamic Random-Access Memory, ESDRAM
  • Synchlink DRAM Synchlink Dynamic Random-Access Memory, SLDRAM
  • memory bus Radbus
  • direct RAM Random-Access Memory
  • DRDRAM Direct Rambus Dynamic Random-Access Memory

Abstract

本公开提供了一种人脸识别方法及装置、电子设备、存储介质、计算机程序、计算机程序产品，所述方法包括：获取目标信号；所述目标信号为在目标区域中停留时长大于或等于预设时长的通信信号；基于目标设备的设备标识，获取与所述目标信号对应的预设人脸信息，将所述预设人脸信息缓存到本地缓存中；所述目标设备为发送所述目标信号的设备；将待识别对象的待识别人脸信息与本地缓存中的预设人脸信息进行比对，得到对所述待识别对象对应的人脸识别结果。

Description

人脸识别方法及装置、电子设备、存储介质、计算机程序、计算机程序产品
相关申请的交叉应用
本公开实施例基于申请号为202210270625.4、申请日为2022年03月18日、申请名称为“人脸识别方法、装置、电子设备及存储介质”的中国专利申请提出，并要求该中国专利申请的优先权，该中国专利申请的全部内容在此引入本公开作为参考。
技术领域
本公开涉及但不限于人脸识别技术领域，尤其涉及一种人脸识别方法及装置、电子设备、存储介质、计算机程序、计算机程序产品。
背景技术
人脸识别是基于人的脸部特征信息进行身份识别的一种生物识别技术，人脸识别系统所面对的对象基数十分庞大，其需要解决从千万甚至上亿规模的对象库中，准确找出正在进行人脸识别的对象；由于人脸识别过程中需要在大范围的对象库中进行人脸比对，从而使得人脸识别的效率较低。
发明内容
本公开提供一种人脸识别方法及装置、电子设备、存储介质、计算机程序、计算机程序产品，可以缩小人脸识别过程中的人脸比对范围，提高人脸识别的效率。本公开的技术方案如下：
本公开实施例提供一种人脸识别方法，包括：
获取目标信号；所述目标信号为在目标区域中停留时长大于或等于预设时长的通信信号；
基于目标设备的设备标识，获取与所述目标信号对应的预设人脸信息，将所述预设人脸信息缓存到本地缓存中；所述目标设备为发送所述目标信号的设备；
将待识别对象的待识别人脸信息与本地缓存中的预设人脸信息进行比对，得到对所述待识别对象对应的人脸识别结果。
上述技术方案中，在获取在通信信号的基础上，确定在目标区域的停留时长大于或等于预设时长的通信信号为目标信号，并获取与目标信号对应的预设人脸信息，将预设 人脸信息缓存到本地缓存中，从而当进行人脸识别时，可首先将待识别人脸信息与本地缓存中的预设人脸信息进行比对，进一步缩小人脸比对的范围，提高人脸识别的效率。
本公开实施例提供一种人脸识别装置，包括：
第一获取模块，配置为获取目标信号；所述目标信号为在目标区域中停留时长大于或等于预设时长的通信信号；
第二获取模块，配置为基于目标设备的设备标识，获取与所述目标信号对应的预设人脸信息，将所述预设人脸信息缓存到本地缓存中；所述目标设备为发送所述目标信号的设备；
人脸识别模块，配置为将待识别对象的待识别人脸信息与本地缓存中的预设人脸信息进行比对，得到对所述待识别对象对应的人脸识别结果。
本公开实施例提供一种电子设备，包括：处理器；用于存储所述处理器可执行指令的存储器；其中，所述处理器被配置为执行所述指令，以实现如上述任一项所述的方法。
本公开实施例提供一种计算机可读存储介质，当所述存储介质中的指令由电子设备的处理器执行时，使得所述电子设备能够执行本公开实施例上述任一所述方法。
本公开实施例提供一种计算机程序，所述计算机程序包括计算机可读代码，在所述计算机可读代码被计算机读取并执行的情况下，实现本公开任一实施例中的方法的部分或全部步骤。
本公开实施例提供一种计算机程序产品，所述计算机程序产品包括存储了计算机程序的非瞬时性计算机可读存储介质，所述计算机程序被计算机读取并执行时，实现本公开任一实施例中的方法的部分或全部步骤。
应当理解的是，以上的一般描述和后文的细节描述仅是示例性和解释性的，并不能限制本公开。
附图说明
此处的附图被并入说明书中并构成本说明书的一部分，示出了符合本公开的实施例，并与说明书一起用于解释本公开的原理，并不构成对本公开的不当限定。
图1是根据一示例性实施例示出的实施环境示意图。
图2是根据一示例性实施例示出的一种人脸识别方法流程图。
图3是根据一示例性实施例示出的一种目标信号确定方法流程图。
图4是根据一示例性实施例示出的一种人脸信息匹配方法流程图。
图5是根据一示例性实施例示出的一种人脸信息匹配优先级调整方法流程图。
图6是根据一示例性实施例示出的一种资源转移方法流程图。
图7是根据一示例性实施例示出的一种人脸识别装置示意图。
图8是根据一示例性实施例示出的一种用于人脸识别的电子设备的框图。
具体实施方式
为了使本领域普通人员更好地理解本公开的技术方案，下面将结合附图，对本公开实施例中的技术方案进行清楚、完整地描述。
需要说明的是，本公开的说明书和权利要求书及上述附图中的术语“第一”、“第二”等是用于区别类似的对象，而不必用于描述特定的顺序或先后次序。应该理解这样使用的数据在适当情况下可以互换，以便这里描述的本公开的实施例能够以除了在这里图示或描述的那些以外的顺序实施。以下示例性实施例中所描述的实施方式并不代表与本公开相一致的所有实施方式。相反，它们仅是与如所附权利要求书中所详述的、本公开的一些方面相一致的装置和方法的例子。
请参阅图1，图1是根据一示例性实施例示出的一种应用环境的示意图，如图1所示，该应用环境可以包括人脸识别前端100和人脸识别后端200。
人脸识别前端100可用于对待识别对象的人脸信息进行采集，得到待识别人脸信息；然后将待识别人脸信息与本地缓存的预设人脸信息进行比对，得到人脸识别结果；人脸识别后端200可用于对全量人脸识别信息进行存储以及管理，其中人脸识别前端100本地缓存的预设人脸信息可以为在人脸识别前端100进行人脸识别之前，从人脸识别后端200获取并缓存到本地的。
本公开实施例中，人脸识别前端100可以为具备人脸信息采集以及人脸识别功能的设备，可以包括但不限于智能手机、台式计算机、平板电脑、笔记本电脑、智能音箱、数字助理、增强现实(Augmented Reality，AR)/虚拟现实(Virtual Reality，VR)设备、智能可穿戴设备等类型的电子设备。可选的，电子设备上运行的操作系统可以包括但不限于安卓系统、IOS系统、Linux、Windows等。
人脸识别后端200可以是独立服务器，也可以是多个服务器构成的服务器集群或者分布式系统。
此外，需要说明的是，图1所示的仅仅是本公开提供的一种应用环境，在实际应用中，还可以包括其他应用环境，例如人脸识别也可在人脸识别后端200进行。
本说明书实施例中，上述人脸识别前端100以及人脸识别后端200可以通过有线或无线通信方式进行直接或间接地连接，本公开在此不做限制。
图2是根据一示例性实施例示出的一种人脸识别方法的流程图，如图2所示，该人脸识别方法可用于终端、服务器、边缘计算节点等电子设备中，可以为上述的人脸识别前端。其中，电子设备还可以为用户设备(User Equipment，UE)、移动设备、用户终端、蜂窝电话、无绳电话、个人数字处理(Personal Digital Assistant，PDA)、手持设备、计算设备、车载设备、可穿戴设备等。在一些可能的实现方式中，该人脸识别方法可以通过处理器调用存储器中存储的计算机可读指令的方式来实现。该方法可以包括：
S210，获取目标信号；所述目标信号为在目标区域中停留时长大于或等于预设时长的通信信号。
目标区域可以为和人脸识别场景相适配的区域，目标区域可基于人脸识别前端的数据处理能力来确定，例如，在人脸识别前端的数据处理指标大于等于预设处理指标时，确定目标区域的范围为第一范围；在人脸识别前端的数据处理指标小于预设处理指标时，确定目标区域的范围为第二范围，其中第一范围大于第二范围，第一范围内的通信信号的数量大于第二范围内的通信信号的数量。
在一些实施例中，目标区域也可基于通信信号的信号密度来确定，为了降低通信信号处理数量，以及实现对通信信号的及时处理，可将信号密度大于等于预设密度的区域确定为目标区域；其中信号密度可基于目标区域内通信信号的数量与目标区域的范围进行确定。即通信信号的信号密度大于预设密度的区域中可能聚集了需要进行人脸识别的待识别对象，从而对该区域内的通信信号进行处理，能够尽快识别对这些通信信号对应的待识别对象进行人脸识别。
另外，在确定了目标区域之后，可从目标区域的通信信号中确定出目标信号，本实施例中，可将在目标区域中停留时长大于等于预设时长的通信信号确定为目标信号；目标信号是由待识别对象的目标设备发出的，目标信号在目标区域内的停留时长大于等于预设时长，可以说明目标信号对应的待识别对象有进行人脸识别的意图，从而可基于目标信号进行进一步处理。
S220，基于目标设备的设备标识，获取与所述目标信号对应的预设人脸信息，将所述预设人脸信息缓存到本地缓存中；所述目标设备为发送所述目标信号的设备。
在目标信号在目标区域内停留时长大于或等于预设时长的情况下，可预先基于目标设备的设备标识，从人脸识别后端获取与目标信号对应的预设人脸信息，并缓存到本地缓存中，从而当进行人脸识别时，可将待识别人脸信息与本地缓存的预设人脸信息进行比对。
其中人脸识别后端维护了全量人脸信息库，全量人脸信息库中存储了人脸信息与设备标识的对应关系，从而在已知目标设备的设备标识的情况下，可基于目标设备的设备标识确定与目标信号对应的预设人脸信息；人脸信息与设备标识的对应关系可以是各对象在人脸识别系统进行注册时所创建的。
另外，为了减少对象的人脸特征发生变化所导致的人脸识别失败的情况，人脸识别系统可以预设时间间隔通知各对象进行人脸信息的更新，从而重新创建更新后的人脸信息与设备标识的对应关系。
在一些实施例中，由于各对象可能存在更换登录设备的情况，从而在各对象更换了登录人脸识别系统的登录设备的情况下，对全量人脸信息库中的设备标识进行更新，从而重新创建更新后的设备标识与人脸信息的对应关系。
S230，将待识别对象的待识别人脸信息与本地缓存中的预设人脸信息进行比对，得到对所述待识别对象对应的人脸识别结果。
在人脸识别前端进行人脸识别时，可将采集到的待识别人脸信息与本地缓存中的预设人脸信息进行比对，得到相应的人脸识别结果。
上述技术方案中，在获取在通信信号的基础上，确定在目标区域的停留时长大于或等于预设时长的通信信号为目标信号，并获取与目标信号对应的预设人脸信息，将预设人脸信息缓存到本地缓存中，从而当进行人脸识别时，可首先将待识别人脸信息与本地缓存中的预设人脸信息进行比对，进一步缩小人脸比对的范围，提高人脸识别的效率。
在一个可选实施例中，目标信号的确定可基于多个探测周期的信号探测结果来确定；可以参阅图3，其示出了一种目标信号确定方法，该方法可包括：
S310，获取当前探测周期内所述目标区域中的通信信号。
S320，将所述当前探测周期内的通信信号与上一探测周期内的通信信号进行比对，得到重复信号，其中，所述上一探测周期为所述当前探测周期之前的，且与所述当前探测周期相邻的探测周期。
S330，将所述重复信号在所述目标区域内的历史累计停留时长，与探测周期间隔进行累加处理，得到所述重复信号的当前累计停留时长。
S340，在所述重复信号的当前累计停留时长大于或等于所述预设时长的情况下，将所述重复信号确定为所述目标信号。
探测周期可以为对目标区域内的通信信号进行探测的周期，探测周期间隔可以为预设间隔；在每个探测周期内，对当前探测周期内的通信信号与上一探测周期内的通信信号进行比对，将既在当前探测周期内被探测出的通信信号，又在上一探测周期被探测出的通信信号，确定为重复信号；其中上一探测周期可以为当前探测周期之前的，且与当前探测周期相邻的探测周期，探测周期间隔可以为上一探测周期结束时刻与当前探测周期起始时刻之间的时间间隔。
需要说明的是，本实施例中的重复信号可以为至少在两个探测周期内被探测出的通信信号，若通信信号在连续两个探测周期被探测出，则在第二个探测周期可被确定为重复信号；若该通信信号在第三个探测周期没有被探测出，则该通信信号不再是重复信号；若该通信信号在第四个探测周期又被探测出，该通信信号也不是重复信号；若该通信信号在第四个探测周期被探测出，且在第五个探测周期又被探测出，则在第五个探测周期可将该探测信号确定为重复信号。
在每个探测周期内，对重复信号在目标区域内的累计停留时长进行计算，得到重复信号的当前累计停留时长；例如，当前累计停留时长的计算方法可通过重复信号在目标区域内的历史累计停留时长与探测周期间隔进行累计处理，历史累计停留时长可以为重复信号在上一探测周期结束之前在目标区域内的停留时长。
当重复信号的当前累计停留时长大于或等于预设时长的情况下，将重复信号确定为目标信号。
上述技术方案中，在每个探测周期内进行重复信号的确定以及相应停留时长的计算，基于计算结果确定出目标信号，从而及时确定出目标信号，进而便于及时获取与目标信号对应的预设人脸信息，实现预设人脸信息的分周期获取，以及本地缓存中预设人脸信息的及时更新。
在一个示例中，目标信号的数量可能有多个，从而本地缓存中可缓存有与多个目标信号各自对应的多项预设人脸信息，在进行人脸识别时，可确定多项预设人脸信息的匹配顺序；可以参阅图4，其示出了一种人脸信息匹配方法，多项预设人脸信息可具备各自对应的匹配优先级，目标信号中还可包括目标信号的信号强度，从而该方法可包括：
S410，根据所述目标信号的信号强度变化信息，确定每项所述预设人脸信息的匹配优先级。
S420，根据每项所述预设人脸信息的匹配优先级从高到底的顺序，将所述待识别人脸信息与每项所述预设人脸信息进行匹配，得到所述人脸识别结果。
目标信号的信号强度变化信息能够表征目标信号对应的目标设备与人脸识别前端的距离变化信息，而目标设备与人脸识别前端的距离变化信息，与待识别对象的人脸识别意图相适配。
当目标信号的信号强度变化信息是逐渐增强时，可能待识别对象与人脸识别前端的距离越来越近，即可能处于人脸识别等待状态，此时可提高该目标信号对应的预设人脸信息的匹配优先级；当目标信号的信号轻度变化信息是逐渐减弱时，可能待识别对象与人脸识别前端的距离越来越远，可说明待识别对象在短时间之内没有人脸识别的意图，此时可降低该目标信号对应的预设人脸信息的匹配优先级；进而可确定各项预设人脸信息的匹配优先级。
在确定了各项预设人脸信息的匹配优先级的情况下，按照匹配优先级由高到低的顺序，进行人脸信息匹配，可以是先采用匹配优先级最高的预设人脸信息与待识别人脸信息进行匹配，若匹配成功，则确定人脸识别成功；若匹配失败，则采用匹配优先级次之的预设人脸信息与待识别人脸信息进行匹配，以此类推，得到对待识别对象的人脸识别结果。
上述技术方案中，通过目标信号的强度变化信息确定匹配优先级，从而基于匹配优先级由高到低的顺序进行人脸匹配，能够进一步提高人脸识别的效率。
在一个可选实施例中，目标信号的信号强度变化信息可基于连续时间段内的信号强度的变化来确定；可以参阅图5，其示出了一种人脸信息匹配优先级调整方法，该方法可包括：
S510，获取所述目标信号在连续预设数量的探测周期内的信号强度。
S520，基于所述目标信号在连续预设数量的探测周期内的信号强度，确定所述目标信号的信号强度变化信息。
S530，基于所述信号强度变化信息，调整所述目标信号对应的预设人脸信息的匹配优先级。
本实施例中，预设数量可以为两个或者两个以上，从而在确定目标信号的信号强度变化信息时，可在每个探测周期内对目标信号进行探测，得到相应的目标信号的信号强度，然后基于目标信号在连续预设数量的探测周期内信号强度，确定目标信号的信号强度变化信息。
目标信号的信号强度可通过信号强度值或者信号强度等级标识进行确定，从而进一步可通过目标信号在连续预设数量的探测周期内的信号强度值变化信息或者信号强度等级标识变化信息，确定目标信号的信号强度变化信息。在目标信号在连续预设数量的探测周期内的信号强度值逐渐增大时，或者在连续预设数量的探测周期内的信号强度等级标识逐渐变化为高强度等级标识的时，确定目标信号强度变化信息为信号强度逐渐增大；在目标信号在连续预设数量的探测周期内的信号强度值逐渐减小时，或者在连续预设数量的探测周期内的信号强度等级标识逐渐变化为低强度等级标识的时，确定目标信号强度变化信息为信号强度逐渐减小。
需要说明的是，在连续两个探测周期内探测到目标信号的信号强度逐渐增强，在第三个探测周期探测到信号强度减弱时，可暂不对目标信号进行处理，在第四探测周期继续探测目标信号的信号强度，当第四探测周期内的信号强度增强，且大于第二探测周期内的信号强度，可忽略第三探测周期内检测到的信号强度，确定目标信号的信号强度逐渐增强；第三探测周期内检测到的信号强度可能是由于干扰因素导致的探测结果出错，从而能够减少由于干扰因素的存在而导致信号强度变化信息确定错误，提高信号变化信息确定的准确性。对于目标信号的信号强度逐渐减弱的情况类似，在此不再赘述。
从而在信号强度变化信息指示目标信号的信号强度逐渐增强时，提高目标信号对应的预设人脸信息的匹配优先级；在信号强度变化信息指示目标信号的信号强度逐渐减弱时，降低目标信号对应的预设人脸信息的匹配优先级。
上述技术方案中，目标信号强度的变化信息可用于表征待识别对象的人脸识别意图变化信息，进而可基于信号强度变化信息合理调整预设人脸信息的匹配优先级，使得预设人脸信息的匹配优先级与待识别对象的人脸识别意图相匹配，从而提高人脸识别效率。
在一些实施例中，对于本实施例提供的人脸识别方法还可应用于资源转移场景，可以参阅图6，其示出了一种资源转移方法，该方法可包括：
S610，在所述人脸识别结果指示在所述预设人脸信息中匹配到与所述待识别人脸信息对应的目标人脸信息时，确定与所述目标人脸信息关联的目标账户。
S620，基于所述目标账户进行资源转移处理。
在资源转移场景中，需要基于人脸识别结果进行相应的资源转移操作，其中人脸识别可作为资源转移的对象身份验证，在待识别对象通过人脸识别时，则完成了对待识别对象的对象身份验证。在资源转移系统中，可存储有人脸信息与目标账户的关联关系，从而可基于匹配成功的目标人脸信息，确定相关联的目标账户，进而待识别对象可基于目标账户进行资源转移操作。
上述技术方案中，将人脸识别方法应用于资源转移场景，一方面，由于通过本实施例提供的人脸识别方法能够提高人脸识别效率，将其应用于资源转移场景，能够提高资源转移的效率；另一方面，在通过人脸识别时，才可进行资源转移，从而提高了资源转移的安全性。
在一可选实施例中，上述人脸识别方法还可包括：
在人脸识别过程中出现比对延时的情况下，根据缓存时间，从所述本地缓存中删除至少一项预设人脸信息。
上述技术方案中，若出现比对延时的情况，可从本地缓存中删除至少一项预设人脸信息，一方面可以减少预设人脸信息的数量，进一步缩小信息比对范围，从而提高人脸识别效率；另一方面，从本地缓存中删除预设人脸信息，能够减轻本地端的信息缓存压力，进一步提高本地端的数据处理效率。
在一个可选的实施例中，上述人脸识别方法还包括：
在所述人脸识别结果指示在所述预设人脸信息中匹配到与所述待识别人脸信息对应的目标人脸信息时，从所述本地缓存中删除所述目标人脸信息。
上述技术方案中，在人脸识别过程中匹配到目标人脸信息时，该目标人脸信息对应的待识别对象短时间内可能不会再次进行人脸识别，可将其从本地缓存中删除，一方面可以减少预设人脸信息的数量，进一步缩小信息比对范围，从而提高人脸识别效率；另一方面，通过删除人脸信息，能够减轻本地端的信息存储压力，提高本地端的数据处理效率。
在一个可选的实施例中，所述人脸识别方法应用于支付终端，所述支付终端包括：
主控芯片、存储器、网络通信模块、无线探针、主触摸屏、副触摸屏，以及镜头模组；
其中，所述主控芯片、所述存储器、所述网络通信模块、所述无线探针集成在电路板上，所述主触摸屏、所述副触摸屏，以及所述镜头模组通过支架固定。
在一些实施例中，在人脸识别场景中，支付终端的无线探针可对目标区域内智能设备发出的通信信号进行探测，确定出目标区域内的目标信号；然后通过网络通信模块从人脸识别后端获取与目标信号对应的预设人脸信息，存储器会对预设人脸信息进行缓存。在进行支付时，通过副触摸屏进行支付信息确认，镜头模组对待识别对象进行人脸信息采集，得到待识别人脸信息，待识别对象面对主触摸屏进行操作，以执行人脸识别；主控芯片对待识别人脸信息与缓存中的预设人脸信息进行比对，得到人脸识别结果，并将人脸识别结果以及支付结果发送至人脸识别后端。
本实施例中的支付终端可应用于智能零售或者车站检票等场景中。
上述技术方案中，将人脸识别方法应用于支付终端，待识别对象可基于支付终端完成人脸识别以及进行支付操作，一方面实现了人脸识别的方法的实际应用，另一方面能够提高支付效率。
图7是根据一示例性实施例示出的一种人脸识别装置，包括：
第一获取模块710，配置为获取目标信号；所述目标信号为在目标区域中停留时长大于或等于预设时长的通信信号；第二获取模块720，配置为基于目标设备的设备标识，获取与所述目标信号对应的预设人脸信息，将所述预设人脸信息缓存到本地缓存中；所述目标设备为发送所述目标信号的设备；人脸识别模块730，配置为将待识别对象的待 识别人脸信息与本地缓存中的预设人脸信息进行比对，得到对所述待识别对象对应的人脸识别结果。
在一个可选的实施例中，所述装置还包括：通信信号获取模块，配置为获取当前探测周期内所述目标区域中的通信信号；信号比对模块，配置为将所述当前探测周期内的通信信号与上一探测周期内的通信信号进行比对，得到重复信号，其中，所述上一探测周期为所述当前探测周期之前的，且与所述当前探测周期相邻的探测周期；停留时长计算模块，配置为将所述重复信号在所述目标区域内的历史累计停留时长，与探测周期间隔进行累加处理，得到所述重复信号的当前累计停留时长；目标信号确定模块，配置为在所述重复信号的当前累计停留时长大于或等于所述预设时长的情况下，将所述重复信号确定为所述目标信号。
在一个可选的实施例中，所述预设人脸信息具有匹配优先级；所述目标信号中包括所述目标信号的信号强度；所述人脸识别模块730包括：匹配优先级确定模块，配置为根据所述目标信号的信号强度变化信息，确定每项所述预设人脸信息的匹配优先级；信息匹配模块，配置为根据每项所述预设人脸信息的匹配优先级从高到底的顺序，将所述待识别人脸信息与每项所述预设人脸信息进行匹配，得到所述人脸识别结果。
在一个可选的实施例中，所述匹配优先级确定模块包括：信号强度获取模块，配置为获取所述目标信号在连续预设数量的探测周期内的信号强度；信号强度变化信息确定模块，配置为基于所述目标信号在连续预设数量的探测周期内的信号强度，确定所述目标信号的信号强度变化信息；匹配优先级调整模块，配置为基于所述信号强度变化信息，调整所述目标信号对应的预设人脸信息的匹配优先级。
在一个可选的实施例中，所述装置还包括：目标账户确定模块，配置为在所述人脸识别结果指示在所述预设人脸信息中匹配到与所述待识别人脸信息对应的目标人脸信息时，确定与所述目标人脸信息关联的目标账户；资源转移模块，配置为基于所述目标账户进行资源转移处理。
在一个可选的实施例中，所述装置还包括：第一删除模块，配置为在人脸识别过程中出现比对延时的情况下，根据缓存时间，从所述本地缓存中删除至少一项预设人脸信息。
在一个可选的实施例中，所述装置还包括：第二删除模块，配置为在所述人脸识别结果指示在所述预设人脸信息中匹配到与所述待识别人脸信息对应的目标人脸信息时，从所述本地缓存中删除所述目标人脸信息。
在一个可选的实施例中，所述人脸识别装置应用于支付终端，所述支付终端包括：主控芯片、存储器、网络通信模块、无线探针、主触摸屏、副触摸屏，以及镜头模组；其中，所述主控芯片、所述存储器、所述网络通信模块、所述无线探针集成在电路板上，所述主触摸屏、所述副触摸屏，以及所述镜头模组通过支架固定。
关于上述实施例中的装置，其中各个模块执行操作的具体方式已经在有关该方法的实施例中进行了详细描述，此处将不做详细阐述说明。
图8是根据一示例性实施例示出的一种用于人脸识别的电子设备的框图，该电子设备(800)可以是终端，其内部结构图可以如图8所示。该电子设备(800)包括通过系统总线(801)连接的处理器(802)、存储器、网络接口(803)、显示器(804)和输入装置(805)。其中，该电子设备(800)的处理器(802)用于提供计算和控制能力。该电子设备(800)的存储器包括非易失性存储介质(806)、内存储器(807)。该非易失性存储介质(806)存储有操作系统(8061)和计算机程序(8062)。该内存储器(807)为非易失性存储介质(806)中的操作系统(8061)和计算机程序(8062)的运行提供环境。该电子设备(800)的网络接口(803)用于与外部的终端通过网络连接通信。该计算机程序(8062)被处理器(802)执行时以实现一种人脸识别方法。该电子设备(800)的显示器(804)可以是液晶显示屏或者电子墨水显示屏，该电子设备(800)的输入装置(805)可以是显示屏上覆盖的触摸层，也可以是电子设备(800)外壳上设置的按键、轨迹球或触控板，还可以是外接的键盘、触控板或鼠标等。
本领域技术人员可以理解，图8中示出的结构，仅仅是与本公开方案相关的部分结构的框图，并不构成对本公开方案所应用于其上的电子设备的限定，具体的电子设备可以包括比图中所示更多或更少的部件，或者组合某些部件，或者具有不同的部件布置。
在示例性实施例中，还提供了一种电子设备，包括：处理器；用于存储该处理器可执行指令的存储器；其中，该处理器被配置为执行该指令，以实现如本公开实施例中的人脸识别方法。
在示例性实施例中，还提供了一种计算机可读存储介质，当该计算机可读存储介质中的指令由电子设备的处理器执行时，使得电子设备能够执行本公开实施例中的人脸识别方法。
计算机可读存储介质可以是可以保持和存储由指令执行设备使用的指令的有形设备，可为易失性存储介质或者非易失性存储介质。计算机可读存储介质例如可以是(但不限于)电存储设备、磁存储设备、光存储设备、电磁存储设备、半导体存储设备或者上述的任意合适的组合。计算机可读存储介质的更具体的例子(非穷举的列表)包括：便携式计算机盘、硬盘、随机存取存储器(Random Access Memory，RAM)、只读存储器(Read-Only Memory，ROM)、可擦式可编程只读存储器(EPROM或闪存)、静态随机存取存储器(SRAM)、便携式压缩盘只读存储器(CD-ROM)、数字多功能盘(DVD)、记忆棒、软盘、机械编码设备、例如其上存储有指令的打孔卡或凹槽内凸起结构、以及上述的任意合适的组合。这里所使用的计算机可读存储介质不被解释为瞬时信号本身，诸如无线电波或者其他自由传播的电磁波、通过波导或其他传输媒介传播的电磁波(例如，通过光纤电缆的光脉冲)、或者通过电线传输的电信号。
本公开实施例还提出一种计算机程序，所述计算机程序包括计算机可读代码，在所述计算机可读代码被计算机读取并执行的情况下，实现本公开任一实施例中的方法的部分或全部步骤。
本公开实施例还提供了一种计算机程序产品，包括计算机可读代码，或者承载有计 算机可读代码的非易失性计算机可读存储介质，当所述计算机可读代码在电子设备的处理器中运行时，所述电子设备中的处理器执行上述方法的部分或全部步骤。
本领域普通技术人员可以理解实现上述实施例方法中的全部或部分流程，是可以通过计算机程序来指令相关的硬件来完成，该计算机程序可存储于一非易失性计算机可读取存储介质中，该计算机程序在执行时，可包括如上述各方法的实施例的流程。其中，本公开所提供的各实施例中所使用的对存储器、存储、数据库或其它介质的任何引用，均可包括非易失性和/或易失性存储器。非易失性存储器可包括只读存储器(ROM)、可编程ROM(PROM)、电可编程ROM(Erasable Programmable Read-Only Memory，EPROM)、电可擦除可编程ROM(Electrically Erasable Programmable Read Only Memory，EEPROM)或闪存。易失性存储器可包括随机存取存储器(RAM)或者外部高速缓冲存储器。作为说明而非局限，RAM以多种形式可得，诸如静态RAM(Static Random-Access Memory，SRAM)、动态RAM(Dynamic Random Access Memory，DRAM)、同步DRAM(Synchronous Dynamic Random-Access Memory，SDRAM)、双数据率SDRAM(Double-Data-Rate Two Synchronous Dynamic Random Access Memory，DDRSDRAM)、增强型SDRAM(Enhanced Synchronous Dynamic Random-Access Memory，ESDRAM)、同步链路(Synchlink)DRAM(Sync Link Dynamic Random-Access Memory，SLDRAM)、存储器总线(Rambus)直接RAM(Rambus Dynamic Random-Access Memory，RDRAM)、以及直接存储器总线动态RAM(Direct Rambus Dynamic Random-Access Memory，DRDRAM)等。
本领域技术人员在考虑说明书及实践这里公开的发明后，将容易想到本公开的其它实施方案。本公开旨在涵盖本公开的任何变型、用途或者适应性变化，这些变型、用途或者适应性变化遵循本公开的一般性原理并包括本公开未公开的本技术领域中的公知常识或惯用技术手段。说明书和实施例仅被视为示例性的，本公开的真正范围和精神由下面的权利要求指出。
应当理解的是，本公开并不局限于上面已经描述并在附图中示出的精确结构，并且可以在不脱离其范围进行各种修改和改变。本公开的范围仅由所附的权利要求来限制。

Claims (20)

  1. 一种人脸识别方法，包括：
    获取目标信号；所述目标信号为在目标区域中停留时长大于或等于预设时长的通信信号；
    基于目标设备的设备标识，获取与所述目标信号对应的预设人脸信息，将所述预设人脸信息缓存到本地缓存中；所述目标设备为发送所述目标信号的设备；
    将待识别对象的待识别人脸信息与本地缓存中的预设人脸信息进行比对，得到对所述待识别对象对应的人脸识别结果。
  2. 根据权利要求1所述的方法，其中，所述获取目标信号之前，所述方法还包括：
    获取当前探测周期内所述目标区域中的通信信号；
    将所述当前探测周期内的通信信号与上一探测周期内的通信信号进行比对，得到重复信号，其中，所述上一探测周期为所述当前探测周期之前的，且与所述当前探测周期相邻的探测周期；
    将所述重复信号在所述目标区域内的历史累计停留时长，与探测周期间隔进行累加处理，得到所述重复信号的当前累计停留时长；
    在所述重复信号的当前累计停留时长大于或等于所述预设时长的情况下，将所述重复信号确定为所述目标信号。
  3. 根据权利要求1或2所述的方法，其中，所述预设人脸信息具有匹配优先级；所述目标信号中包括所述目标信号的信号强度；
    所述将待识别对象的待识别人脸信息与本地缓存中的预设人脸信息进行比对，得到对所述待识别对象对应的人脸识别结果，包括：
    根据所述目标信号的信号强度变化信息，确定每项所述预设人脸信息的匹配优先级；
    根据每项所述预设人脸信息的匹配优先级从高到底的顺序，将所述待识别人脸信息与每项所述预设人脸信息进行匹配，得到所述人脸识别结果。
  4. 根据权利要求3所述的方法，其中，所述根据所述目标信号的信号强度变化信息，确定每项所述预设人脸信息的匹配优先级，包括：
    获取所述目标信号在连续预设数量的探测周期内的信号强度；
    基于所述目标信号在连续预设数量的探测周期内的信号强度，确定所述目标信号的信号强度变化信息；
    基于所述信号强度变化信息，调整所述目标信号对应的预设人脸信息的匹配优先级。
  5. 根据权利要求1至4任一项所述的方法，其中，所述方法还包括：
    在所述人脸识别结果指示在所述预设人脸信息中匹配到与所述待识别人脸信息 对应的目标人脸信息时，确定与所述目标人脸信息关联的目标账户；
    基于所述目标账户进行资源转移处理。
  6. 根据权利要求1至5任一项所述的方法，其中，所述方法还包括：
    在人脸识别过程中出现比对延时的情况下，根据缓存时间，从所述本地缓存中删除至少一项预设人脸信息。
  7. 根据权利要求1至6任一项所述的方法，其中，所述方法还包括：
    在所述人脸识别结果指示在所述预设人脸信息中匹配到与所述待识别人脸信息对应的目标人脸信息时，从所述本地缓存中删除所述目标人脸信息。
  8. 根据权利要求1至7任一项所述的方法，其中，所述人脸识别方法应用于支付终端，所述支付终端包括：
    主控芯片、存储器、网络通信模块、无线探针、主触摸屏、副触摸屏，以及镜头模组；
    其中，所述主控芯片、所述存储器、所述网络通信模块、所述无线探针集成在电路板上，所述主触摸屏、所述副触摸屏，以及所述镜头模组通过支架固定。
  9. 一种人脸识别装置，包括：
    第一获取模块，配置为获取目标信号；所述目标信号为在目标区域中停留时长大于或等于预设时长的通信信号；
    第二获取模块，配置为基于目标设备的设备标识，获取与所述目标信号对应的预设人脸信息，将所述预设人脸信息缓存到本地缓存中；所述目标设备为发送所述目标信号的设备；
    人脸识别模块，配置为将待识别对象的待识别人脸信息与本地缓存中的预设人脸信息进行比对，得到对所述待识别对象对应的人脸识别结果。
  10. 根据权利要求9所述的装置，其中，所述装置还包括：
    通信信号获取模块，配置为获取当前探测周期内所述目标区域中的通信信号；
    信号比对模块，配置为将所述当前探测周期内的通信信号与上一探测周期内的通信信号进行比对，得到重复信号，其中，所述上一探测周期为所述当前探测周期之前的，且与所述当前探测周期相邻的探测周期；
    停留时长计算模块，配置为将所述重复信号在所述目标区域内的历史累计停留时长，与探测周期间隔进行累加处理，得到所述重复信号的当前累计停留时长；
    目标信号确定模块，配置为在所述重复信号的当前累计停留时长大于或等于所述预设时长的情况下，将所述重复信号确定为所述目标信号。
  11. 根据权利要求9或10所述的装置，其中，所述预设人脸信息具有匹配优先级；所述目标信号中包括所述目标信号的信号强度；
    所述人脸识别模块，包括：
    匹配优先级确定模块，配置为根据所述目标信号的信号强度变化信息，确定每项所述预设人脸信息的匹配优先级；
    信息匹配模块，配置为根据每项所述预设人脸信息的匹配优先级从高到底的顺序，将所述待识别人脸信息与每项所述预设人脸信息进行匹配，得到所述人脸识别结果。
  12. 根据权利要求11所述的装置，其中，所述匹配优先级确定模块，包括：
    信号强度获取模块，配置为获取所述目标信号在连续预设数量的探测周期内的信号强度；
    信号强度变化信息确定模块，配置为基于所述目标信号在连续预设数量的探测周期内的信号强度，确定所述目标信号的信号强度变化信息；
    匹配优先级调整模块，配置为基于所述信号强度变化信息，调整所述目标信号对应的预设人脸信息的匹配优先级。
  13. 根据权利要求9至12任一项所述的装置，其中，所述装置还包括：
    目标账户确定模块，配置为在所述人脸识别结果指示在所述预设人脸信息中匹配到与所述待识别人脸信息对应的目标人脸信息时，确定与所述目标人脸信息关联的目标账户；
    资源转移模块，配置为基于所述目标账户进行资源转移处理。
  14. 根据权利要求9至13任一项所述的装置，其中，所述装置还包括：
    第一删除模块，配置为在人脸识别过程中出现比对延时的情况下，根据缓存时间，从所述本地缓存中删除至少一项预设人脸信息。
  15. 根据权利要求9至14任一项所述的装置，其中，所述装置还包括：
    第二删除模块，配置为在所述人脸识别结果指示在所述预设人脸信息中匹配到与所述待识别人脸信息对应的目标人脸信息时，从所述本地缓存中删除所述目标人脸信息。
  16. 根据权利要求9至15任一项所述的装置，其中，所述人脸识别装置应用于支付终端，所述支付终端包括：
    主控芯片、存储器、网络通信模块、无线探针、主触摸屏、副触摸屏，以及镜头模组；
    其中，所述主控芯片、所述存储器、所述网络通信模块、所述无线探针集成在电路板上，所述主触摸屏、所述副触摸屏，以及所述镜头模组通过支架固定。
  17. 一种电子设备，包括：
    处理器；
    用于存储所述处理器可执行指令的存储器；
    其中，所述处理器被配置为执行所述指令，以实现如权利要求1至8中任一项所述的人脸识别方法。
  18. 一种计算机可读存储介质，当所述存储介质中的指令由电子设备的处理器执行时，使得人脸识别设备能够执行如权利要求1至8中任一项所述的人脸识别方法。
  19. 一种计算机程序，包括计算机可读代码，在计算机可读代码在设备上运行的 情况下，设备中的处理器执行用于实现权利要求1至8中任一所述的方法。
  20. 一种计算机程序产品，配置为存储计算机可读指令，所述计算机可读指令被执行时使得计算机执行权利要求1至8中任一所述的方法。
PCT/CN2022/110281 2022-03-18 2022-08-04 人脸识别方法及装置、电子设备、存储介质、计算机程序、计算机程序产品 WO2023173661A1 (zh)

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN202210270625.4 2022-03-18
CN202210270625.4A CN114648797A (zh) 2022-03-18 2022-03-18 人脸识别方法、装置、电子设备及存储介质

Publications (1)

Publication Number Publication Date
WO2023173661A1 true WO2023173661A1 (zh) 2023-09-21

Family

ID=81995976

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2022/110281 WO2023173661A1 (zh) 2022-03-18 2022-08-04 人脸识别方法及装置、电子设备、存储介质、计算机程序、计算机程序产品

Country Status (2)

Country Link
CN (1) CN114648797A (zh)
WO (1) WO2023173661A1 (zh)

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114648797A (zh) * 2022-03-18 2022-06-21 成都商汤科技有限公司 人脸识别方法、装置、电子设备及存储介质

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190286884A1 (en) * 2015-06-24 2019-09-19 Samsung Electronics Co., Ltd. Face recognition method and apparatus
CN110378696A (zh) * 2019-06-26 2019-10-25 深圳市万通顺达科技股份有限公司 一种刷脸支付方法、装置、可读存储介质及终端设备
CN111275448A (zh) * 2020-02-22 2020-06-12 腾讯科技（深圳）有限公司 人脸数据处理方法、装置和计算机设备
CN114648797A (zh) * 2022-03-18 2022-06-21 成都商汤科技有限公司 人脸识别方法、装置、电子设备及存储介质

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20190286884A1 (en) * 2015-06-24 2019-09-19 Samsung Electronics Co., Ltd. Face recognition method and apparatus
CN110378696A (zh) * 2019-06-26 2019-10-25 深圳市万通顺达科技股份有限公司 一种刷脸支付方法、装置、可读存储介质及终端设备
CN111275448A (zh) * 2020-02-22 2020-06-12 腾讯科技（深圳）有限公司 人脸数据处理方法、装置和计算机设备
CN114648797A (zh) * 2022-03-18 2022-06-21 成都商汤科技有限公司 人脸识别方法、装置、电子设备及存储介质

Also Published As

Publication number Publication date
CN114648797A (zh) 2022-06-21

Similar Documents

Publication Publication Date Title
CN109993150B (zh) 用于识别年龄的方法和装置
US20190253760A1 (en) Method and apparatus for recommending video
WO2023173664A1 (zh) 人脸识别方法、装置、电子设备、存储介质、计算机程序及程序产品
EP3893125A1 (en) Method and apparatus for searching video segment, device, medium and computer program product
CN113065614B (zh) 分类模型的训练方法和对目标对象进行分类的方法
CN111104825A (zh) 人脸注册库更新方法、装置、设备及介质
CN110363121B (zh) 指纹图像处理方法及装置、存储介质和电子设备
WO2023173661A1 (zh) 人脸识别方法及装置、电子设备、存储介质、计算机程序、计算机程序产品
WO2020232902A1 (zh) 异常对象识别方法、装置、计算设备和存储介质
US11769507B2 (en) Voice-assistant activated virtual card replacement
CN111737564A (zh) 一种信息查询方法、装置、设备及介质
WO2016028442A1 (en) Systems and methods for detecting sensitive user data on the internet
US20230230089A1 (en) System, Method, and Computer Program Product for Generating Synthetic Data
CN113253878A (zh) 触摸屏的报点确定方法、装置、电子设备及存储介质
CN113627361B (zh) 人脸识别模型的训练方法、装置及计算机程序产品
CN112685799B (zh) 设备指纹生成方法、装置、电子设备和计算机可读介质
CN110955390A (zh) 数据处理方法、装置和电子设备
CN111126159A (zh) 用于实时跟踪行人的方法、装置、电子设备和介质
CN108011936B (zh) 用于推送信息的方法和装置
CN115631514B (zh) 基于掌静脉指纹的用户识别方法、装置、设备与介质
CN107895573B (zh) 用于识别信息的方法及装置
US11662927B2 (en) Redirecting access requests between access engines of respective disk management devices
CN113034580B (zh) 图像信息检测方法、装置和电子设备
CN113051400A (zh) 标注数据确定方法、装置、可读介质及电子设备
CN111401137A (zh) 证件栏位识别的方法和装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 22931683

Country of ref document: EP

Kind code of ref document: A1