WO2018014851A1 - 一种生物特征识别的方法，装置及存储介质 - Google Patents

一种生物特征识别的方法，装置及存储介质 Download PDF

Info

Publication number
WO2018014851A1
WO2018014851A1 PCT/CN2017/093588 CN2017093588W WO2018014851A1 WO 2018014851 A1 WO2018014851 A1 WO 2018014851A1 CN 2017093588 W CN2017093588 W CN 2017093588W WO 2018014851 A1 WO2018014851 A1 WO 2018014851A1
Authority
WO
WIPO (PCT)
Prior art keywords
heart rate
current
data
user
rate data
Prior art date
Application number
PCT/CN2017/093588
Other languages
English (en)
French (fr)
Inventor
陈杰
Original Assignee
腾讯科技（深圳）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 腾讯科技（深圳）有限公司 filed Critical 腾讯科技（深圳）有限公司
Priority to EP17830485.3A priority Critical patent/EP3489850B1/en
Publication of WO2018014851A1 publication Critical patent/WO2018014851A1/zh
Priority to US16/201,701 priority patent/US10824848B2/en

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/161—Detection; Localisation; Normalisation
    • G06V40/162—Detection; Localisation; Normalisation using pixel segmentation or colour matching
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
    • G06F21/31—User authentication
    • G06F21/32—User authentication using biometric data, e.g. fingerprints, iris scans or voiceprints
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F21/00—Security arrangements for protecting computers, components thereof, programs or data against unauthorised activity
    • G06F21/30—Authentication, i.e. establishing the identity or authorisation of security principals
    • G06F21/31—User authentication
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
    • G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
    • G06F3/015—Input arrangements based on nervous system activity detection, e.g. brain waves [EEG] detection, electromyograms [EMG] detection, electrodermal response detection
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T7/00—Image analysis
    • G06T7/90—Determination of colour characteristics
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/16—Human faces, e.g. facial parts, sketches or expressions
    • G06V40/168—Feature extraction; Face representation
    • G06V40/169—Holistic features and representations, i.e. based on the facial image taken as a whole
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/40—Spoof detection, e.g. liveness detection
    • G06V40/45—Detection of the body part being alive
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/70—Multimodal biometrics, e.g. combining information from different biometric modalities
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
    • G06T2207/00—Indexing scheme for image analysis or image enhancement
    • G06T2207/30—Subject of image; Context of image processing
    • G06T2207/30196—Human being; Person
    • G06T2207/30201—Face
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
    • G06V40/15—Biometric patterns based on physiological signals, e.g. heartbeat, blood flow

Definitions

  • the present invention relates to the field of computer technologies, and in particular, to a method, device and storage medium for biometric identification.
  • biometric devices such as fingerprint recognition and face recognition have emerged, and are widely used in access control and attendance.
  • the front face image of the attendant is pre-recorded.
  • the attendance device recognizes the currently collected face image and the pre-stored image. After the face image of the attendant matches, the attendance will be prompted.
  • the face recognition method of face recognition significantly reduces the chance of being swiped by others, but there will still be some people using photos to take the attendance, and the attendance device reads the features on the photo and pre-stored.
  • the feature similarity is higher than the preset threshold, it will also pass the attendance, which shows that there is still much room for improvement in the application of biometrics.
  • the embodiment of the present invention provides a biometric identification method, which is recognized when the current facial color data of the user matches the current heart rate data. Thereby effectively avoiding the vulnerability of biometrics in the application.
  • Embodiments of the present invention also provide corresponding devices.
  • a first aspect of the embodiments of the present invention provides a method for biometric identification, including:
  • the biometric device acquires a facial image of the user who is performing feature recognition, and current heart rate data of the user;
  • the biometric device determines a current facial color data of the user according to the facial image, and a correspondence relationship between the facial color data of the user and the heart rate data;
  • the biometric identification device determines whether the acquired current facial color data matches the current heart rate data according to the correspondence between the facial color data of the user and the heart rate data;
  • the biometric device determines that the user identification passes
  • the biometric device determines that the user identification does not pass.
  • a second aspect of the embodiments of the present invention provides a device for biometric identification, including:
  • An acquiring unit configured to acquire a facial image of a user who is performing feature recognition, and current heart rate data of the user
  • a first determining unit configured to determine, according to the facial image, current color data of the user, and a correspondence between the color data of the user and the heart rate data
  • a second determining unit configured to determine, according to a correspondence between the face color data of the user and the heart rate data determined by the first determining unit, whether the current face color data acquired by the acquiring unit matches the current heart rate data
  • a determining unit configured to determine, if the second determining unit determines that the current facial color data matches the current heart rate data, the user identification passes, if the current facial color data does not match the current heart rate data, the user The identification does not pass.
  • a third aspect of the embodiments of the present invention provides a biometric device, including: a processor, a memory, a camera, and a heart rate collector;
  • the camera is configured to collect a facial image of a user who is performing feature recognition
  • the heart rate collector is configured to collect current heart rate data of the user
  • the memory is configured to store a correspondence between the color data of the user and the heart rate data
  • the processor is configured to acquire the facial image collected by the camera, determine current facial color data of the user according to the facial image, and a correspondence between the facial color data of the user and heart rate data, and
  • the heart rate collector acquires the current heart rate data of the user; and determines whether the acquired current face color data matches the current heart rate data according to the correspondence between the face color data of the user and the heart rate data; if the current face color data and If the current heart rate data is matched, it is determined that the user recognition passes, and if the current face color data does not match the current heart rate data, it is determined that the user does not recognize. Over.
  • a fourth aspect of embodiments of the present application provides a non-volatile storage medium in which computer readable instructions are stored. When the instructions are executed, the computer is caused to perform the biometric identification method described above.
  • the biometric recognition method provided by the embodiment of the present invention can be passed when the user's current face data matches the current heart rate data. Identification, thereby effectively avoiding loopholes in biometric identification and improving the recognition accuracy of biometric devices.
  • FIG. 1 is a schematic diagram of user face color data and heart rate data collection, and corresponding relationship construction in a scenario where a user runs on a treadmill in an embodiment of the present invention
  • FIG. 2 is a schematic diagram of a correspondence curve between a user's face color data and heart rate data in an embodiment of the present invention
  • FIG. 3 is a schematic diagram of a biometric identification device identifying a user in an embodiment of the present invention.
  • FIG. 4 is a schematic diagram of a relationship curve between a user's face color data and heart rate data in another embodiment of the present invention.
  • FIG. 5 is a schematic diagram of a method for biometric identification in an embodiment of the present invention.
  • FIG. 6 is a schematic diagram of an apparatus for biometric identification in an embodiment of the present invention.
  • Figure 7 is a schematic diagram of an apparatus for biometric identification in another embodiment of the present invention.
  • Figure 8 is a schematic illustration of an apparatus for biometric identification in accordance with yet another embodiment of the present invention.
  • the embodiment of the invention provides a biometric recognition method, which can identify the user's current facial color data and the current heart rate data, thereby effectively avoiding the loophole in the biometric identification and improving the biometric identification.
  • the identification accuracy of the device Embodiments of the present invention also provide corresponding devices. The details are described below separately.
  • an embodiment of the present invention provides a biometrics recognition method.
  • the correspondence between the face color data of the fixed group users and the heart rate data is constructed.
  • the correspondence between the user's face color data and the heart rate data will include the face color data corresponding to the user at different heart rates.
  • the correspondence is stored in the biometric device, and the biometric device may be a device such as an attendance machine.
  • Heart rate changes during the running of the user, as well as corresponding facial changes, can be collected by the user running on the treadmill.
  • the biometric device is an attendance machine. If the attendance machine is responsible for attendance for 30 people in the company, then the attendance machine needs to enter the correspondence between the facial data and the heart rate data of the 30 individuals, then for each People need to establish their own correspondence between face data and heart rate data.
  • the user on the treadmill 10 is exemplified by one of the above 30 persons, the user's wrist is provided with a heart rate collector 20, and the treadmill 10 is mounted with a camera 30, and the camera 30 is used for The user's facial image is acquired during the running of the user, and the heart rate collector 20 is configured to collect the user's heart rate data during the running of the user.
  • the heart rate collector 20 can be a smart bracelet. The heart rate can be measured by the pulse.
  • the camera 30 collects the facial image of the user, and after the heart rate collector 20 collects the heart rate data, the facial image and heart rate data of the user can be transmitted to a data collection device 40, which may be a
  • the separate device may also be a biometric device in the embodiment of the present invention.
  • the camera 30 can be in communication with the data collection device 40 by wire, and the heart rate collector 20 can be communicatively coupled to the data collection device 40 by wireless.
  • the face color data can be quantized by the color temperature or the three primary colors, and the three primary colors are: red (R), green (G), and blue (B).
  • R red
  • G green
  • B blue
  • it is not limited to quantification by color temperature or three primary colors, and may be quantized by other physical parameters such as brightness.
  • the color temperature is a measure of the color of the light source, and the unit is Kelvin (K).
  • K Kelvin
  • the color temperature of the light source is determined by comparing its color to the theoretical thermal blackbody radiator.
  • the Kelvin temperature of the hot black body radiator matching the color of the light source is the color temperature of that light source, and the color temperature is directly related to the Planck blackbody radiation law.
  • the color temperature of some common light sources is: standard candlelight is 1930K, tungsten filament lamp is 2760-2900K; fluorescent lamp is 3000K, flashlight is 3800K, noon sunlight is 5600K, and electronic flash is 6000K.
  • the color temperature of the human face can be from ten to several tens of K.
  • RGB Red, green (G), and blue (B)
  • RGB has 256 levels of brightness, expressed as numbers from 0, 1, 2... up to 255. Therefore, the respective values of R, G, and B corresponding to the face image can be determined for each face image.
  • the scheme of determining the face color data from the face image may include a RGB processing method and a color temperature processing method.
  • the RGB processing method is to extract the red (R) value of each pixel on the face image, and then average The average value of R is used as the face color data of the current face image.
  • the color temperature processing method is to first determine the mean value of R, G, and B of each pixel on the face image, and then substitute the mean value of R, G, and B of the face image into the color temperature estimation algorithm according to the color temperature estimation algorithm to find the current The color temperature of the face image.
  • the unit of heart rate is sub/min. Therefore, after the data collection device 40 acquires the face image for three consecutive minutes and the heart rate data for the three minutes, the correspondence relationship can be constructed.
  • the example of the present invention is described by taking three minutes for each person to test, so the data of the present place uses three minutes of data, but three minutes should not be understood as a limitation on the test time.
  • the facial image of the user is analyzed every 20 seconds, and the facial color data of the user, such as the R, G, B value or the color temperature value, is obtained from the facial image.
  • the color temperature is taken as an example for explanation.
  • Table 1 Correspondence between heart rate data and face color data
  • Each user will have a correspondence between face data and heart rate data, and the correspondence can be indexed by the user's face image.
  • the process of the index is similar to the process of existing attendance punching, and each user's facial features are basically It is unique. Therefore, when the user uses the attendance machine provided by the present application, the attendance opportunity collects the facial image of the user, and then performs feature comparison according to the facial image of the user and the face image of each user stored in advance. When the face image of the user matches the user face image stored in advance, the correspondence relationship between the face color data of the user and the heart rate data can be extracted.
  • the correspondence between the color data of the user and the heart rate data is indexed by the number of the user, and the process includes setting a number for the user when the user is pre-recorded.
  • the above feature comparison determines the number of the user who is attending the attendance, and then indexes the correspondence between the face data of the user and the heart rate data according to the number.
  • a corresponding face color value can be found on the curve shown in Fig. 2 by a heart rate value, of course, through a face color value on the curve shown in Fig. 2. You can also find a corresponding heart rate value.
  • the correspondence between the user's face color data and the heart rate data is stored.
  • the biometric device in the embodiment of the present invention To the biometric device in the embodiment of the present invention.
  • the biometric device 40 provided by the embodiment of the present invention includes a processor 401, a memory 402, a camera 403, and a heart rate collector 404.
  • the user's face is facing the camera 403, the camera 403 captures the current facial image of the user who is performing feature recognition, and the user wears the heart rate collector 404 on the wrist.
  • the heart rate collector 404 is configured to collect current heart rate data of the user, and the memory 402 stores a correspondence relationship between the face color data of the user and the heart rate data. This correspondence can be understood by referring to the corresponding descriptions in the sections of FIGS. 1 and 2.
  • the processor 401 is configured to acquire the facial image collected by the camera, determine the current facial color data from the current facial image, and acquire current heart rate data of the user from the heart rate collector;
  • the facial image determines the correspondence between the facial color data of the user and the heart rate data from the correspondence relationship between the face color data of the plurality of users and the heart rate data stored in advance, and the process is similar to the process of the existing attendance punching, each user
  • the facial features are basically unique. Therefore, when the user uses the attendance machine provided by the present application, the attendance opportunity collects the facial image of the user, and then according to the facial image of the user and the pre-stored face of each user. The image is subjected to feature comparison.
  • the correspondence between the face data of the user and the heart rate data can be extracted. Then, determining whether the acquired current face color data matches the current heart rate data; if the current face color data matches the current heart rate data, by identifying, if the current face color data and the current heart rate data are not If it matches, the identification will not pass.
  • the processor 401 determines that the color temperature value of the current face is 29K, and the current heart rate data acquired by the processor 401 is 98 times/minute, it can be determined from the curve of FIG. 4 according to the color temperature value of 29K.
  • the matching heart rate data corresponding to the color temperature value is 99 times/min, and the heart rate difference between the matching heart rate data and the current heart rate data is determined to be 1 time/minute, and if the preset heart rate threshold is 3 times/minute, the description When the heart rate difference is within the preset heart rate threshold range, it may be determined that the current face color data matches the current heart rate data.
  • the processor 401 determines that the current heart rate data is 99 beats/min, and the processor 401 obtains the current color temperature value of the face is 28.5 K, according to the pre-heart rate data is 99 beats/min, the curve can be determined from the curve of FIG. If the matching color temperature value corresponding to the current heart rate data is 29K, it can be determined that the color difference between the matching color temperature value and the color temperature value of the current face is 0.5K, and the preset color threshold is 1K, indicating that the face color difference is at the preset face threshold. Within the range, it may be determined that the current face data matches the current heart rate data.
  • the solution provided by the embodiment of the present invention effectively avoids malicious use of photos for face recognition, and improves the recognition accuracy of the biometric device.
  • an embodiment of a method for biometric identification provided by an embodiment of the present invention includes:
  • the face image of the user is usually collected by the camera, and the camera is generally only responsible for acquiring the image, and then the current face data of the user can be determined by the image captured by the camera.
  • the process can be understood by referring to the description of the relevant parts in the foregoing, and the details are not repeated here.
  • the biometric recognition method provided by the embodiment of the present invention can be passed when the user's current face data matches the current heart rate data. Identification, thereby effectively avoiding loopholes in biometric identification and improving the recognition accuracy of biometric devices.
  • the method may further include:
  • the establishment of the corresponding relationship is performed in advance. As shown in the parts of FIG. 1 and FIG. 2, the data collection and the establishment of the corresponding relationship may be separately performed for the user who needs to input the correspondence between the face color data and the heart rate data. And then importing the established correspondence of each user into the biometric device, so that in the subsequent biometric process, the corresponding relationship can be directly used. Line identification.
  • the determining, according to the correspondence between the face color data of the user and the heart rate data, whether the acquired current face color data matches the current heart rate data includes:
  • the matching heart rate data may be determined in the correspondence relationship between the face color data and the heart rate data of the user through the current face color data, and then the matching heart rate data and the current are matched.
  • the heart rate data is compared, determining a heart rate difference between the matched heart rate data and the current heart rate data; and when the heart rate difference is within a preset heart rate threshold range, determining the current face data and the current heart rate data match.
  • the determining, according to the correspondence between the face color data of the user and the heart rate data, whether the acquired current face color data matches the current heart rate data includes:
  • the matching face color data when the current face data and the current heart rate data are matched, the matching face color data may be determined in the correspondence relationship between the face color data and the heart rate data of the user through the current heart rate data, and then the matching face color data and the current Comparing the face color data, determining a face color difference between the matching face color data and the current face color data;
  • the solution provided by the multiple embodiments of the present invention monitors the current face color and heart rate of the user in the face detection authentication, and then determines whether the current face color and the current heart rate are consistent with the pre-trained correspondence relationship. It can be determined that the user is a normal user, otherwise the malicious face is authenticated.
  • an embodiment of a biometric device 60 provided by an embodiment of the present invention includes:
  • An obtaining unit 601 configured to acquire a facial image of a user who is performing feature recognition, and current heart rate data of the user;
  • the first determining unit 602 is configured to determine, according to the facial image acquired by the acquiring unit 601, current color data of the user, and a correspondence between the color data of the user and the heart rate data;
  • the second determining unit 603 is configured to determine, according to the correspondence between the color data of the user and the heart rate data determined by the first determining unit 602, the current facial color data acquired by the acquiring unit 601 and the current heart rate data. Whether it matches;
  • the identifying unit 604 is configured to: if the second determining unit 603 determines that the current facial color data matches the current heart rate data, determine that the user recognition passes, and if the current facial color data does not match the current heart rate data, Then it is determined that the user identification does not pass.
  • the acquiring unit 601 acquires the facial image of the user who is performing the feature recognition, and the current heart rate data of the user; the first determining unit 602 determines the location image according to the facial image acquired by the acquiring unit 601. Determining the current color data of the user, and the correspondence between the color data of the user and the heart rate data, the second determining unit 603 determines the correspondence between the color data of the user and the heart rate data determined by the first determining unit 602.
  • the biometric device provided by the embodiment of the present invention can pass the current facial color data and the current heart rate data. Identification, thereby effectively avoiding loopholes in biometric identification and improving the recognition accuracy of biometric devices.
  • the apparatus 60 further includes a receiving unit 605 and a storage unit 606.
  • the receiving unit 605 is configured to receive a correspondence between the color data of the user and the heart rate data
  • the storage unit 606 is configured to store the correspondence relationship received by the receiving unit 605, where the corresponding relationship is obtained by pre-collecting face color data corresponding to the user at different heart rates.
  • the second determining unit 603 is configured to:
  • the second determining unit 603 is configured to:
  • FIG. 8 is a schematic structural diagram of a device 60 for biometric identification according to an embodiment of the present invention.
  • the biometric device 60 includes a processor 610, a camera 660, a heart rate collector 670 memory 650, and a transceiver 630.
  • the camera 660 can be used to collect a facial image of a user who is performing feature recognition.
  • Heart rate collector 670 can be used to collect current heart rate data for the user.
  • Memory 650 can include read only memory and random access memory and provides operational instructions and data to processor 610. A portion of the memory 650 can also include non-volatile random access memory (NVRAM).
  • NVRAM non-volatile random access memory
  • the memory 650 stores the following elements, executable modules or data structures, or a subset thereof, or their extended set:
  • the biometric device performs the following steps by calling an operation instruction stored in the memory 650 (the operation instruction can be stored in the operating system):
  • the current face color data matches the current heart rate data, it is determined that the user recognition passes, and if the current face color data does not match the current heart rate data, it is determined that the user recognition does not pass.
  • the biometric recognition device provided by the embodiment of the present invention has the current facial color data and the current heart rate of the user. According to the matching situation, the identification will be passed, thereby effectively avoiding the vulnerability of the biometric identification in the application and improving the recognition accuracy of the biometric identification device.
  • the processor 610 controls the operation of the biometric device 60, which may also be referred to as a CPU (Central Processing Unit).
  • Memory 650 can include read only memory and random access memory and provides instructions and data to processor 610. A portion of the memory 650 can also include non-volatile random access memory (NVRAM).
  • the components of the biometric device 60 are coupled together by a bus system 620 in a specific application.
  • the bus system 620 may include a power bus, a control bus, a status signal bus, and the like in addition to the data bus. However, for clarity of description, various buses are labeled as bus system 620 in the figure.
  • Processor 610 may be an integrated circuit chip with signal processing capabilities. In the implementation process, each step of the foregoing method may be completed by an integrated logic circuit of hardware in the processor 610 or an instruction in a form of software.
  • the processor 610 described above may be a general purpose processor, a digital signal processor (DSP), an application specific integrated circuit (ASIC), an off-the-shelf programmable gate array (FPGA) or other programmable logic device, a discrete gate or transistor logic device, or discrete hardware. Component.
  • DSP digital signal processor
  • ASIC application specific integrated circuit
  • FPGA off-the-shelf programmable gate array
  • the methods, steps, and logical block diagrams disclosed in the embodiments of the present invention may be implemented or carried out.
  • the general purpose processor may be a microprocessor or the processor or any conventional processor or the like.
  • the steps of the method disclosed in the embodiments of the present invention may be directly implemented by the hardware decoding processor, or may be performed by a combination of hardware and software modules in the decoding processor.
  • the software module can be located in a conventional storage medium such as random access memory, flash memory, read only memory, programmable read only memory or electrically erasable programmable memory, registers, and the like.
  • the storage medium is located in the memory 650, and the processor 610 reads the information in the memory 650 and performs the steps of the above method in combination with its hardware.
  • the transceiver 630 is configured to receive a correspondence between the color data of the user and the heart rate data;
  • the memory 650 is configured to store the correspondence relationship, where the correspondence relationship is obtained by pre-collecting face color data corresponding to the user at different heart rates.
  • the processor 610 is configured to:
  • the processor 610 is configured to:
  • the above biometric device 60 can be understood by referring to the description in the parts of FIG. 1 to FIG. 5, and no further description is made herein.
  • the program may be stored in a computer readable storage medium, and the storage medium may include: ROM, RAM, disk or CD.

Landscapes

  • Engineering & Computer Science (AREA)
  • Theoretical Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Computer Security & Cryptography (AREA)
  • General Engineering & Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Health & Medical Sciences (AREA)
  • Multimedia (AREA)
  • Computer Hardware Design (AREA)
  • Software Systems (AREA)
  • General Health & Medical Sciences (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Biomedical Technology (AREA)
  • Dermatology (AREA)
  • Neurology (AREA)
  • Neurosurgery (AREA)
  • Collating Specific Patterns (AREA)
  • Image Analysis (AREA)
  • Image Processing (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

一种生物特征识别的方法，包括：获取正在进行特征识别的用户的脸部图像，以及用户的当前心率数据（501）；根据脸部图像确定用户的当前脸色数据，以及用户的脸色数据与心率数据的对应关系（502）；根据用户的脸色数据与心率数据的对应关系，确定获取的当前脸色数据与当前心率数据是否匹配（503），若当前脸色数据与当前心率数据匹配，则通过识别（504）。该生物特征识别方法，在用户的当前脸色数据与当前心率数据匹配的情况下才会通过识别，从而有效地避免了生物识别在应用中的漏洞。

Description

一种生物特征识别的方法，装置及存储介质
本申请要求于2016年7月20日提交中国专利局、申请号201610574489.2，发明名称为“一种生物特征识别的方法及装置”的中国专利申请的优先权，其全部内容通过引用结合在本申请中。
技术领域
本发明涉及计算机技术领域，具体涉及一种生物特征识别的方法，装置及存储介质。
背景技术
随着生物识别技术的快速发展，现在例如指纹识别和人脸识别等生物识别设备也随之出现，并被广泛应用于门禁以及考勤中。
以人脸识别的考勤设备为例，预先录入考勤者的正脸图像，在考勤时，只要考勤者将脸对准考勤设备，该考勤设备识别出当前所采集的人脸图像与预先存储的该考勤者的人脸图像匹配后，就会提示考勤通过。
通过人脸识别的考勤方式相比与原来的刷卡考勤方式，明显降低了由别人代刷卡的几率，但是还是会有个别人用照片代考勤，考勤设备读取到照片上的特征与预先存储的特征相似度高于预置门限时，也会通过考勤，由此可见，生物特征识别的应用还有很大的改善空间。
发明内容
为了解决现有技术中生物识别在应用中还有漏洞的问题，本发明实施例提供了一种生物特征识别的方法，在用户的当前脸色数据与当前心率数据匹配的情况下才会通过识别，从而有效的避免了生物识别在应用中的漏洞。本发明实施例还提供了相应的装置。
本发明实施例第一方面提供一种生物特征识别的方法，包括：
生物特征识别装置获取正在进行特征识别的用户的脸部图像，以及所述用户的当前心率数据；
生物特征识别装置根据所述脸部图像确定所述用户的当前脸色数据，以及所述用户的脸色数据与心率数据的对应关系；
生物特征识别装置根据所述用户的脸色数据与心率数据的对应关系，确定获取的所述当前脸色数据与所述当前心率数据是否匹配；
若所述当前脸色数据与所述当前心率数据匹配，则生物特征识别装置判定用户识别通过；
若所述当前脸色数据与所述当前心率数据不匹配，则生物特征识别装置判定用户识别不通过。
本发明实施例第二方面提供一种生物特征识别的装置，包括：
获取单元，用于获取正在进行特征识别的用户的脸部图像，以及所述用户的当前心率数据；
第一确定单元，用于根据所述脸部图像确定所述用户的当前脸色数据，以及所述用户的脸色数据与心率数据的对应关系
第二确定单元，用于根据所述第一确定单元确定的所述用户的脸色数据与心率数据的对应关系，确定所述获取单元获取的所述当前脸色数据与所述当前心率数据是否匹配；
识别单元，用于若所述第二确定单元确定出所述当前脸色数据与所述当前心率数据匹配，则判定用户识别通过，若所述当前脸色数据与所述当前心率数据不匹配，则用户识别不通过。
本发明实施例第三方面提供一种生物特征识别的装置，包括：处理器、存储器、摄像头和心率采集器；
所述摄像头用于采集正在进行特征识别的用户的脸部图像；
所述心率采集器用于采集所述用户的当前心率数据；
所述存储器用于存储所述用户的脸色数据与心率数据的对应关系；
所述处理器用于获取所述摄像头采集的所述脸部图像，根据所述脸部图像确定所述用户的当前脸色数据，以及所述用户的脸色数据与心率数据的对应关系，并从所述心率采集器获取所述用户的当前心率数据；根据所述用户的脸色数据与心率数据的对应关系，确定获取的所述当前脸色数据与所述当前心率数据是否匹配；若所述当前脸色数据与所述当前心率数据匹配，则判定用户识别通过，若所述当前脸色数据与所述当前心率数据不匹配，则判定用户识别不通 过。
本申请实施例第四方面提供一种非易失性存储介质，其中存储有计算机可读指令。当所述指令被执行时，使得计算机执行上述的生物特征识别方法。
与现有技术中会发生代刷照片进行识别或者恶意用照片进行识别相比，本发明实施例提供的生物特征识别的方法，在用户的当前脸色数据与当前心率数据匹配的情况下才会通过识别，从而有效的避免了生物识别在应用中的漏洞，提高了生物特征识别装置的识别准确性。
附图说明
为了更清楚地说明本发明实施例中的技术方案，下面将对实施例描述中所需要使用的附图作简单地介绍，显而易见地，下面描述中的附图仅仅是本发明的一些实施例，对于本领域技术人员来讲，在不付出创造性劳动的前提下，还可以根据这些附图获得其他的附图。
图1是本发明实施例中用户在跑步机上跑步的场景下，用户脸色数据与心率数据收集，及其对应关系构建的示意图；
图2是本发明实施例中用户的脸色数据与心率数据对应关系曲线的示意图；
图3是本发明实施例中生物特征识别装置对用户进行识别的示意图；
图4是本发明另一实施例中用户的脸色数据与心率数据对应关系曲线的示意图；
图5是本发明实施例中生物特征识别的方法的示意图；
图6是本发明实施例中生物特征识别的装置的示意图；
图7是本发明另一实施例中生物特征识别的装置的示意图；
图8是本发明又一实施例中生物特征识别的装置的示意图。
具体实施方式
本发明实施例提供一种生物特征识别的方法，在用户的当前脸色数据与当前心率数据匹配的情况下才会通过识别，从而有效的避免了生物识别在应用中的漏洞，提高了生物特征识别装置的识别准确性。本发明实施例还提供了相应的装置。以下分别进行详细说明。
下面将结合本发明实施例中的附图，对本发明实施例中的技术方案进行清楚、完整地描述，显然，所描述的实施例仅仅是本发明一部分实施例，而不是 全部的实施例。基于本发明中的实施例，本领域技术人员在没有作出创造性劳动前提下所获得的所有其他实施例，都属于本发明保护的范围。
目前人脸识别有一个比较大的瓶颈就是如何确认识别的是自然人，而不是照片。针对这个问题，本发明实施例提出一种生物特征识别的方法，依据人体心率变化的同时脸色也会随之变化的原理，构建出一些固定群体用户的脸色数据与心率数据的对应关系，每个用户的脸色数据与心率数据的对应关系中都会包含该用户在不同心率时所对应的脸色数据。然后，将该对应关系存储到生物特征识别的装置中，该生物特征识别的装置可以是考勤机等设备。
为了更好的理解为用户的脸色数据与心率数据的对应关系的使用，下面结合图1先介绍本发明实施例中用户的脸色数据与心率数据的对应关系的建立过程。
可以通过用户在跑步机上跑步的场景来收集该用户在跑步过程中的心率变化，以及对应的脸色变化。
以生物特征识别的装置是考勤机为例，如果该考勤机负责为公司中的30个人考勤，那么该考勤机中需要先录入这30个人的脸色数据与心率数据的对应关系，那么针对每个人员都需要先建立自己的脸色数据与心率数据的对应关系。
如图1所示，以跑步机10上的用户是上述30个人员中的一个为例，该用户的手腕上带有心率采集器20，跑步机10上安装有摄像头30，摄像头30用于在用户跑步过程中采集该用户的脸部图像，心率采集器20用于在用户跑步过程中采集该用户的心率数据。心率采集器20可以是智能手环。可以通过脉搏来测量心率。
摄像头30收集到该用户的脸部图像，以及心率采集器20采集到心率数据后，可以将该用户的脸部图像和心率数据传输到一个数据收集设备40中，该数据收集设备40可以是一个单独的设备，也可以是本发明实施例中的生物特征识别的装置。摄像头30可以通过有线与数据收集设备40通信连接，心率采集器20可以通过无线与数据收集设备40通信连接。
数据收集设备40获取到的脸部图像有很多个，心率数据也有很多个，可以通过时间将两者进行匹配。数据收集设备40需要先从脸部图像中确定脸色数据，本发明实施例中，脸色数据可以用色温或三原色来量化，三原色为：红(R)、绿(G)和蓝(B)。当然，不限于用色温或者三原色来量化，也可以用例如：亮度等其他物理参数来量化。
色温(color temperature)是表示光源光色的尺度，单位为开尔文(K)。光源的色温是通过对比它的色彩和理论的热黑体辐射体来确定的。热黑体辐射体与光源的色彩相匹配时的开尔文温度就是那个光源的色温，色温直接和普朗克黑体辐射定律相联系。
例如：一些常用光源的色温为:标准烛光为1930K，钨丝灯为2760-2900K；荧光灯为3000K，闪光灯为3800K，中午阳光为5600K，电子闪光灯为6000K等。人脸色的色温可以为十几K到几十K。
RGB一种颜色标准，是通过对红(R)、绿(G)、蓝(B)三个颜色通道的变化以及它们相互之间的叠加来得到各式各样的颜色。因此这红色绿色蓝色又称为三原色光，用英文表示就是R(red)、G(green)、B(blue)。
在电脑中，RGB的所谓"多少"就是指亮度的大小，并使用整数来表示。通常情况下，RGB各有256级亮度，用数字表示为从0、1、2...直到255。因此，可以为每个脸部图像确定出该脸部图像对应的R、G、B各自数值。
从脸部图像确定脸色数据的方案可以包括RGB的处理方法以及色温的处理方法。
因为不同心率下，脸色的变化主要体现在由淡变红，或者由红转淡，所以RGB的处理方法是将脸部图像上每个像素点的红色(R)值提取出来，然后求平均值，将该R的平均值作为当前脸部图像的脸色数据。
色温的处理方法是先确定脸部图像上每个像素点的R、G、B的均值，然后依据色温估计算法，将脸部图像的R、G、B的均值代入色温估计算法，求出当前脸部图像的色温。
心率的单位为次/分，因此，在数据收集设备40获取到连续三分钟的脸部图像和这三分钟的心率数据后，就可以进行对应关系的构建。本发明的示例中是以每个人员测试三分钟为例进行说明的，所以本处的数据用了三分钟的数据，但不应将三分钟理解为是对测试时间的限定。
为了便于说明，本发明实施例中只分析每隔20秒的心率数据和脸部图像。本发明实施例中按照运动的连续性，每隔20秒分析一次用户的脸部图像，从这次的脸部图像中获取用户的脸色数据，如R、G、B数值或者色温数值，下面将以色温为例进行说明。
表1：心率数据与脸色数据的对应关系
脸部图像(每隔20秒) 心率数据(次/分) 色温数值(K)
第一张脸部图像 72 13
第二张脸部图像 78 16
第三张脸部图像 85 20
第四张脸部图像 92 25
第五张脸部图像 99 29
第六张脸部图像 105 36
第七张脸部图像 110 42
第八张脸部图像 115 49
第九张脸部图像 121 56
以上表1只是以一些趋势性的数据为例进行说明，每个用户的对应关系中的数据以实际测量值为准。而且，表1也是为了便于说明，只是列出了每隔20秒的数据，实际上这些数据可以是连续的，通过心率数据和脸色数据(量化后如色温)的关系对，建立一个自然人的心率和脸色之间的关系，这种数据关系可以为一个高阶的曲线y＝axn+bxn-1+...+t，其中x可以是心率，y可以是脸色，也可以是x是脸色，y是心率，a，b及t为常数，n为大于等于2的整数。
每个用户都会有一个脸色数据与心率数据的对应关系，该对应关系可以通过用户的脸部图像进行索引，该索引的过程类似于现有考勤打卡的过程，每个用户的脸部特征都基本是唯一的，所以，在用户使用本申请提供的考勤机时，考勤机会采集该用户的脸部图像，然后根据该用户的脸部图像与预先存储的各个用户的脸部图像进行特征比对，当该用户的脸部图像与预先存储的用户脸部图像匹配时，就可以提取到该用户的脸色数据与心率数据的对应关系。也可以通过用户的脸部图像确定该用户的编号后，通过该用户的编号来索引该用户的脸色数据与心率数据的对应关系，该过程包括预先录入该用户时为该用户设置一个编号，通过上述特征比对确定正在考勤的用户的编号，然后根据该编号索引该用户的脸色数据与心率数据的对应关系。
如果用图2表示心率和脸色之间的对应关系，那么通过一个心率值在图2所示的曲线上就可以找到一个对应的脸色值，当然，通过一个脸色值在图2所示的曲线上也都可以找到一个对应的心率值。
以上对应关系建立好后，将该用户的脸色数据与心率数据的对应关系存储 到本发明实施例中的生物特征识别的装置中。
如图3所示，本发明实施例提供的生物特征识别的装置40包括处理器401、存储器402、摄像头403和心率采集器404。当有用户正在使用该生物特征识别的装置40时，该用户的脸正对摄像头403，摄像头403采集正在进行特征识别的用户的当前脸部图像，用户将心率采集器404戴在手腕上，通过脉搏采集心率，心率采集器404用于采集所述用户的当前心率数据，存储器402中存储有该用户的脸色数据与心率数据的对应关系。该对应关系可以参阅图1和图2部分的相应描述进行理解。
处理器401用于获取所述摄像头采集的所述脸部图像，从所述当前脸部图像中确定所述当前脸色数据，并从所述心率采集器获取所述用户的当前心率数据；根据用户的脸部图像，从预先存储的多个用户的脸色数据与心率数据的对应关系中确定出该用户的脸色数据与心率数据的对应关系，该过程类似于现有考勤打卡的过程，每个用户的脸部特征都基本是唯一的，所以，在用户使用本申请提供的考勤机时，考勤机会采集该用户的脸部图像，然后根据该用户的脸部图像与预先存储的各个用户的脸部图像进行特征比对，当比对上该用户的脸部图像时，就可以提取到该用户的脸色数据与心率数据的对应关系。然后，确定获取的所述当前脸色数据与所述当前心率数据是否匹配；若所述当前脸色数据与所述当前心率数据匹配，则通过识别，若所述当前脸色数据与所述当前心率数据不匹配，则识别不通过。
如图4所示，若处理器401确定当前的脸色的色温数值为29K，并且处理器401获取到的当前心率数据为98次/分，根据色温数值为29K从图4的曲线中可以确定出与色温数值对应的匹配心率数据为99次/分，则可以确定匹配心率数据与所述当前心率数据的心率差值为1次/分，若预设心率阈值为3次/分，说明所述心率差值在预设心率阈值范围内时，则可以确定所述当前脸色数据与所述当前心率数据匹配。
若处理器401确定当前心率数据为99次/分，并且处理器401获取到当前的脸色的色温数值为28.5K，根据前心率数据为99次/分，从图4的曲线中可以确定出与当前心率数据对应的匹配色温数值为29K，则可以确定匹配色温数值与当前的脸色的色温数值的脸色差值为0.5K，预设脸色阈值为1K，说明所述脸色差值在预设脸色阈值范围内，则可以确定当前脸色数据与所述当前心率数据匹配。
从以上描述可以看出，本发明实施例所提供的方案，有效的避免了恶意使用照片进行人脸识别，提高了生物特征识别装置的识别准确性。
以上是对用户的脸色数据与心率数据的对应关系的建立以及本发明实施例中使用本发明实施例的生物特征识别的装置的示例性场景的描述。下面结合图5介绍本发明实施例中生物特征识别的方法。
如图5所示，本发明实施例提供的生物特征识别的方法的一实施例包括：
501、获取正在进行特征识别的用户的脸部图像，以及所述用户的当前心率数据。
502、根据所述脸部图像确定所述用户的当前脸色数据，以及所述用户的脸色数据与心率数据的对应关系。
本发明实施例中，用户的脸部图像通常是通过摄像头采集的，摄像头一般只负责采集图像，然后，可以通过摄像头采集的图像确定用户的当前脸色数据。该过程可以参阅前述相关部分的描述进行理解，本处不再重复赘述。
503、根据所述用户的脸色数据与心率数据的对应关系，确定获取的所述当前脸色数据与所述当前心率数据是否匹配。
504、若所述当前脸色数据与所述当前心率数据匹配，则判定用户识别通过,若所述当前脸色数据与所述当前心率数据不匹配，则判定用户识别不通过。
与现有技术中会发生代刷照片进行识别或者恶意用照片进行识别相比，本发明实施例提供的生物特征识别的方法，在用户的当前脸色数据与当前心率数据匹配的情况下才会通过识别，从而有效的避免了生物识别在应用中的漏洞，提高了生物特征识别装置的识别准确性。
可选地，所述获取正在进行特征识别的用户的脸部图像，所述方法还可以包括：
接收所述用户的脸色数据与心率数据的对应关系；
存储所述对应关系，所述对应关系为预先采集所述用户在不同心率时所对应的脸色数据得到的。
本发明实施例中，对应关系的建立是预先完成的，如图1和图2部分的描述，可以先为需要录入脸色数据与心率数据的对应关系的用户分别进行数据采集，以及对应关系的建立，然后将建立好的各用户的对应关系导入到生物特征识别的装置，这样在后续生物特征识别的过程中，就可以直接使用该对应关系，就 行识别。
可选地，所述根据所述用户的脸色数据与心率数据的对应关系，确定获取的所述当前脸色数据与所述当前心率数据是否匹配，包括：
根据所述当前脸色数据，从所述对应关系中查找与所述当前脸色数据对应的匹配心率数据；
确定所述匹配心率数据与所述当前心率数据的心率差值；
当所述心率差值在预设心率阈值范围内时，确定所述当前脸色数据与所述当前心率数据匹配。
本发明实施例中，在匹配当前脸色数据与当前心率数据时，可以通过当前脸色数据，在该用户的脸色数据与心率数据的对应关系中确定出匹配心率数据，然后，将匹配心率数据与当前心率数据进行比对，确定所述匹配心率数据与所述当前心率数据的心率差值；当所述心率差值在预设心率阈值范围内时，确定所述当前脸色数据与所述当前心率数据匹配。
可选地，所述根据所述用户的脸色数据与心率数据的对应关系，确定获取的所述当前脸色数据与所述当前心率数据是否匹配，包括：
根据所述当前心率数据，从所述对应关系中查找与所述当前心率数据对应的匹配脸色数据；
确定所述匹配脸色数据与所述当前脸色数据的脸色差值；
当所述脸色差值在预设脸色阈值范围内时，确定所述当前脸色数据与所述当前心率数据匹配。
本发明实施例中，在匹配当前脸色数据与当前心率数据时，可以通过当前心率数据，在该用户的脸色数据与心率数据的对应关系中确定出匹配脸色数据，然后，将匹配脸色数据与当前脸色数据进行比对，确定所述匹配脸色数据与所述当前脸色数据的脸色差值；
当所述脸色差值在预设脸色阈值范围内时，确定所述当前脸色数据与所述当前心率数据匹配。
以上，本发明多个实施例提供的方案，在人脸检测鉴权中，同时监测用户当前的脸色和心率，然后确定当前脸色和当前心率是否与预先训练出的对应关系吻合，如果吻合，则可以确定为该用户就为正常用户，否则为恶意的人脸鉴权。
参阅图6，本发明实施例提供的生物特征识别的装置60的一实施例包括：
获取单元601，用于获取正在进行特征识别的用户的脸部图像，以及所述用户的当前心率数据；
第一确定单元602，用于根据所述获取单元601获取的所述脸部图像确定所述用户的当前脸色数据，以及所述用户的脸色数据与心率数据的对应关系；
第二确定单元603，用于根据所述第一确定单元602确定的所述用户的脸色数据与心率数据的对应关系，确定所述获取单元601获取的所述当前脸色数据与所述当前心率数据是否匹配；
识别单元604，用于若所述第二确定单元603确定出所述当前脸色数据与所述当前心率数据匹配，则判定用户识别通过，若所述当前脸色数据与所述当前心率数据不匹配，则判定用户识别不通过。
本发明实施例中，获取单元601获取正在进行特征识别的用户的脸部图像，以及所述用户的当前心率数据；第一确定单元602根据所述获取单元601获取的所述脸部图像确定所述用户的当前脸色数据，以及所述用户的脸色数据与心率数据的对应关系，第二确定单元603根据所述第一确定单元602确定的所述用户的脸色数据与心率数据的对应关系，确定所述获取单元获取的所述当前脸色数据与所述当前心率数据是否匹配；识别单元604若所述第二确定单元603确定出所述当前脸色数据与所述当前心率数据匹配，则判定用户识别通过，若所述当前脸色数据与所述当前心率数据不匹配，则判定用户识别不通过。与现有技术中会发生代刷照片进行识别或者恶意用照片进行识别相比，本发明实施例提供的生物特征识别的装置，在用户的当前脸色数据与当前心率数据匹配的情况下才会通过识别，从而有效的避免了生物识别在应用中的漏洞，提高了生物特征识别装置的识别准确性。
可选地，参阅图7，本发明实施例提供的生物特征识别的装置60的另一实施例中，所述装置60还包括接收单元605和存储单元606，
所述接收单元605，用于接收所述用户的脸色数据与心率数据的对应关系；
所述存储单元606，用于存储所述接收单元605接收的所述对应关系，所述对应关系为预先采集所述用户在不同心率时所对应的脸色数据得到的。
可选地，所述第二确定单元603用于：
根据所述当前脸色数据，从所述对应关系中查找与所述当前脸色数据对应 的匹配心率数据；
确定所述匹配心率数据与所述当前心率数据的心率差值；
当所述心率差值在预设心率阈值范围内时，确定所述当前脸色数据与所述当前心率数据匹配。
可选地，所述第二确定单元603用于：
根据所述当前心率数据，从所述对应关系中查找与所述当前心率数据对应的匹配脸色数据；
确定所述匹配脸色数据与所述当前脸色数据的脸色差值；
当所述脸色差值在预设脸色阈值范围内时，确定所述当前脸色数据与所述当前心率数据匹配。
图8是本发明实施例提供的生物特征识别的装置60的结构示意图。所述生物特征识别的装置60所述生物特征识别的装置包括处理器610、摄像头660、心率采集器670存储器650和收发器630，摄像头660可用于采集正在进行特征识别的用户的脸部图像，心率采集器670可用于采集所述用户的当前心率数据。存储器650可以包括只读存储器和随机存取存储器，并向处理器610提供操作指令和数据。存储器650的一部分还可以包括非易失性随机存取存储器(NVRAM)。
在一些实施方式中，存储器650存储了如下的元素，可执行模块或者数据结构，或者他们的子集，或者他们的扩展集:
在本发明实施例中，生物特征识别装置通过调用存储器650存储的操作指令(该操作指令可存储在操作系统中)，执行如下步骤：
获取正在进行特征识别的用户的脸部图像，以及所述用户的当前心率数据；
根据所述脸部图像确定所述用户的当前脸色数据，以及所述用户的脸色数据与心率数据的对应关系；
根据所述用户的脸色数据与心率数据的对应关系，确定获取的所述当前脸色数据与所述当前心率数据是否匹配；
若所述当前脸色数据与所述当前心率数据匹配，则判定用户识别通过,若所述当前脸色数据与所述当前心率数据不匹配，则判定用户识别不通过。
与现有技术中会发生代刷照片进行识别或者恶意用照片进行识别相比，本发明实施例提供的生物特征识别的装置，在用户的当前脸色数据与当前心率数 据匹配的情况下才会通过识别，从而有效的避免了生物识别在应用中的漏洞，提高了生物特征识别装置的识别准确性。
处理器610控制生物特征识别的装置60的操作，处理器610还可以称为CPU(Central Processing Unit，中央处理单元)。存储器650可以包括只读存储器和随机存取存储器，并向处理器610提供指令和数据。存储器650的一部分还可以包括非易失性随机存取存储器(NVRAM)。具体的应用中生物特征识别的装置60的各个组件通过总线系统620耦合在一起，其中总线系统620除包括数据总线之外，还可以包括电源总线、控制总线和状态信号总线等。但是为了清楚说明起见，在图中将各种总线都标为总线系统620。
上述本发明实施例揭示的方法可以应用于处理器610中，或者由处理器610实现。处理器610可能是一种集成电路芯片，具有信号的处理能力。在实现过程中，上述方法的各步骤可以通过处理器610中的硬件的集成逻辑电路或者软件形式的指令完成。上述的处理器610可以是通用处理器、数字信号处理器(DSP)、专用集成电路(ASIC)、现成可编程门阵列(FPGA)或者其他可编程逻辑器件、分立门或者晶体管逻辑器件、分立硬件组件。可以实现或者执行本发明实施例中的公开的各方法、步骤及逻辑框图。通用处理器可以是微处理器或者该处理器也可以是任何常规的处理器等。结合本发明实施例所公开的方法的步骤可以直接体现为硬件译码处理器执行完成，或者用译码处理器中的硬件及软件模块组合执行完成。软件模块可以位于随机存储器，闪存、只读存储器，可编程只读存储器或者电可擦写可编程存储器、寄存器等本领域成熟的存储介质中。该存储介质位于存储器650，处理器610读取存储器650中的信息，结合其硬件完成上述方法的步骤。
可选地，收发器630用于接收所述用户的脸色数据与心率数据的对应关系；
存储器650用于存储所述对应关系，所述对应关系为预先采集所述用户在不同心率时所对应的脸色数据得到的。
可选地，处理器610用于：
根据所述当前脸色数据，从所述对应关系中查找与所述当前脸色数据对应的匹配心率数据；
确定所述匹配心率数据与所述当前心率数据的心率差值；
当所述心率差值在预设心率阈值范围内时，确定所述当前脸色数据与所述 当前心率数据匹配。
可选地，处理器610用于：
根据所述当前心率数据，从所述对应关系中查找与所述当前心率数据对应的匹配脸色数据；
确定所述匹配脸色数据与所述当前脸色数据的脸色差值；
当所述脸色差值在预设脸色阈值范围内时，确定所述当前脸色数据与所述当前心率数据匹配。
以上的生物特征识别的装置60可以参阅图1至图5部分的描述进行理解，本处不做过多赘述。
本领域普通技术人员可以理解上述实施例的各种方法中的全部或部分步骤是可以通过程序来指令相关的硬件来完成，该程序可以存储于一计算机可读存储介质中，存储介质可以包括：ROM、RAM、磁盘或光盘等。
以上对本发明实施例所提供的生物特征识别的方法以及装置进行了详细介绍，本文中应用了具体个例对本发明的原理及实施方式进行了阐述，以上实施例的说明只是用于帮助理解本发明的方法及其核心思想；同时，对于本领域的一般技术人员，依据本发明的思想，在具体实施方式及应用范围上均会有改变之处，综上所述，本说明书内容不应理解为对本发明的限制。

Claims (11)

  1. 一种生物特征识别的方法，其特征在于，包括：
    生物特征识别装置获取正在进行特征识别的用户的脸部图像，以及所述用户的当前心率数据；
    生物特征识别装置根据所述脸部图像确定所述用户的当前脸色数据，以及所述用户的脸色数据与心率数据的对应关系；
    生物特征识别装置根据所述用户的脸色数据与心率数据的对应关系，确定获取的所述当前脸色数据与所述当前心率数据是否匹配；
    若所述当前脸色数据与所述当前心率数据匹配，则生物特征识别装置判定用户识别通过；以及
    若所述当前脸色数据与所述当前心率数据不匹配，则生物特征识别装置判定用户识别不通过。
  2. 根据权利要求1所述的方法，其特征在于，所述生物特征识别装置获取正在进行特征识别的用户的脸部图像之前，所述方法还包括：
    生物特征识别装置接收所述用户的脸色数据与心率数据的对应关系；以及
    生物特征识别装置存储所述对应关系，所述对应关系为生物特征识别装置预先采集所述用户在不同心率时所对应的脸色数据得到的。
  3. 根据权利要求1或2所述的方法，其特征在于，所述生物特征识别装置根据所述用户的脸色数据与心率数据的对应关系，确定获取的所述当前脸色数据与所述当前心率数据是否匹配，包括：
    生物特征识别装置根据所述当前脸色数据，从所述对应关系中查找与所述当前脸色数据对应的匹配心率数据；
    生物特征识别装置确定所述匹配心率数据与所述当前心率数据的心率差值；以及
    当所述心率差值在预设心率阈值范围内时，生物特征识别装置确定所述当前脸色数据与所述当前心率数据匹配。
  4. 根据权利要求1或2所述的方法，其特征在于，所述根生物特征识别装置据所述用户的脸色数据与心率数据的对应关系，确定获取的所述当前脸色数据 与所述当前心率数据是否匹配，包括：
    生物特征识别装置根据所述当前心率数据，从所述对应关系中查找与所述当前心率数据对应的匹配脸色数据；
    生物特征识别装置确定所述匹配脸色数据与所述当前脸色数据的脸色差值；以及
    当所述脸色差值在预设脸色阈值范围内时，生物特征识别装置确定所述当前脸色数据与所述当前心率数据匹配。
  5. 一种生物特征识别的装置，其特征在于，包括：
    获取单元，用于获取正在进行特征识别的用户的脸部图像，以及所述用户的当前心率数据；
    第一确定单元，用于根据所述获取单元获取的所述脸部图像确定所述用户的当前脸色数据，以及所述用户的脸色数据与心率数据的对应关系
    第二确定单元，用于根据所述第一确定单元确定的所述用户的脸色数据与心率数据的对应关系，确定所述获取单元获取的所述当前脸色数据与所述当前心率数据是否匹配；以及
    识别单元，用于若所述第二确定单元确定出所述当前脸色数据与所述当前心率数据匹配，则判定用户识别通过，若所述当前脸色数据与所述当前心率数据不匹配，则判定用户识别不通过。
  6. 根据权利要求5所述的装置，其特征在于，所述装置还包括接收单元和存储单元，
    所述接收单元，用于接收所述用户的脸色数据与心率数据的对应关系；
    所述存储单元，用于存储所述接收单元接收的所述对应关系，所述对应关系为预先采集所述用户在不同心率时所对应的脸色数据得到的。
  7. 根据权利要求5或6所述的装置，其特征在于，
    所述第二确定单元用于：
    根据所述当前脸色数据，从所述对应关系中查找与所述当前脸色数据对应的匹配心率数据；
    确定所述匹配心率数据与所述当前心率数据的心率差值；
    当所述心率差值在预设心率阈值范围内时，确定所述当前脸色数据与所述当前心率数据匹配。
  8. 根据权利要求5或6所述的装置，其特征在于，
    所述第二确定单元用于：
    根据所述当前心率数据，从所述对应关系中查找与所述当前心率数据对应的匹配脸色数据；
    确定所述匹配脸色数据与所述当前脸色数据的脸色差值；
    当所述脸色差值在预设脸色阈值范围内时，确定所述当前脸色数据与所述当前心率数据匹配。
  9. 一种生物特征识别的装置，其特征在于，包括：处理器、存储器、摄像头和心率采集器；
    所述摄像头用于采集正在进行特征识别的用户的脸部图像；
    所述心率采集器用于采集所述用户的当前心率数据；
    所述存储器用于存储所述用户的脸色数据与心率数据的对应关系；
    所述处理器用于获取所述摄像头采集的所述脸部图像，根据所述脸部图像确定所述用户的当前脸色数据，以及所述用户的脸色数据与心率数据的对应关系，并从所述心率采集器获取所述用户的当前心率数据；根据所述用户的脸色数据与心率数据的对应关系，确定获取的所述当前脸色数据与所述当前心率数据是否匹配；若所述当前脸色数据与所述当前心率数据匹配，则判定用户识别通过，若所述当前脸色数据与所述当前心率数据不匹配，则判定用户识别不通过。
  10. 根据权利要求9所述的装置，其特征在于，所述装置还包括收发器，
    所述收发器用于接收所述用户的脸色数据与心率数据的对应关系；
    所述对应关系为预先采集所述用户在不同心率时所对应的脸色数据得到的。
  11. 一种非易失性存储介质，用于存储一个或多个计算机程序，其中，所述计算机程序包括一个或多个处理器可运行的指令，所述指令被计算机执行时，使得所述计算机执行以下操作：
    获取正在进行特征识别的用户的脸部图像，以及所述用户的当前心率数据；
    根据所述脸部图像确定所述用户的当前脸色数据，以及所述用户的脸色数据与心率数据的对应关系；
    根据所述用户的脸色数据与心率数据的对应关系，确定获取的所述当前脸色数据与所述当前心率数据是否匹配；
    若所述当前脸色数据与所述当前心率数据匹配，则判定用户识别通过；以及
    若所述当前脸色数据与所述当前心率数据不匹配，则判定用户识别不通过。
PCT/CN2017/093588 2016-07-20 2017-07-20 一种生物特征识别的方法，装置及存储介质 WO2018014851A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
EP17830485.3A EP3489850B1 (en) 2016-07-20 2017-07-20 Biological characteristic recognition method and device, and storage medium
US16/201,701 US10824848B2 (en) 2016-07-20 2018-11-27 Biological feature recognition method and apparatus, and storage medium

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201610574489.2 2016-07-20
CN201610574489.2A CN107644189B (zh) 2016-07-20 2016-07-20 一种生物特征识别的方法及装置

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US16/201,701 Continuation US10824848B2 (en) 2016-07-20 2018-11-27 Biological feature recognition method and apparatus, and storage medium

Publications (1)

Publication Number Publication Date
WO2018014851A1 true WO2018014851A1 (zh) 2018-01-25

Family

ID=60991946

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2017/093588 WO2018014851A1 (zh) 2016-07-20 2017-07-20 一种生物特征识别的方法，装置及存储介质

Country Status (4)

Country Link
US (1) US10824848B2 (zh)
EP (1) EP3489850B1 (zh)
CN (1) CN107644189B (zh)
WO (1) WO2018014851A1 (zh)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110555918A (zh) * 2018-06-01 2019-12-10 杭州海康威视数字技术股份有限公司 考勤管理的方法和考勤管理设备

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110012256A (zh) * 2018-10-08 2019-07-12 杭州中威电子股份有限公司 一种融合视频通信与体征分析的系统

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101635743A (zh) * 2009-04-02 2010-01-27 浙江亚斯特科技有限公司 使用生物特征认证结果确认移动终端持有者身份的系统和方法
US8984622B1 (en) * 2012-01-17 2015-03-17 Amazon Technologies, Inc. User authentication through video analysis
CN104699931A (zh) * 2013-12-09 2015-06-10 广州华久信息科技有限公司 一种基于人脸的神经网络血压预测方法及手机
CN104809371A (zh) * 2014-01-24 2015-07-29 北京奇虎科技有限公司 判断头戴式智能设备的鉴权信息有效性的装置和方法
CN105188522A (zh) * 2013-03-08 2015-12-23 富士胶片株式会社 脉搏波传播速度的测定方法、测定系统及摄像装置
CN205179369U (zh) * 2014-11-26 2016-04-20 三星电子株式会社 用于与智能设备配对的可穿戴设备

Family Cites Families (13)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10150025B2 (en) * 2012-02-10 2018-12-11 Envisionbody, Llc Process to aid in motivation of personal fitness, health monitoring and validation of user
CN103177494A (zh) * 2013-03-26 2013-06-26 姬志刚 非正常状态下的开门者不能开启的门禁系统
CN103226857A (zh) * 2013-03-26 2013-07-31 姬志刚 一种采用多重验证获得完整开启密码的门禁一体机
CN104102868A (zh) * 2014-07-31 2014-10-15 中山市品汇创新专利技术开发有限公司 一种基于人脸识别技术的多模态Usb Key认证的方法
US9582879B2 (en) * 2014-10-20 2017-02-28 Microsoft Technology Licensing, Llc Facial skin mask generation for heart rate detection
US10134274B2 (en) * 2014-11-24 2018-11-20 Echostar Ukraine L.L.C. Remote control with enhanced modularity
US9715621B2 (en) * 2014-12-22 2017-07-25 Mcafee, Inc. Systems and methods for real-time user verification in online education
US10154818B2 (en) * 2014-12-24 2018-12-18 Samsung Electronics Co., Ltd. Biometric authentication method and apparatus
US10108264B2 (en) * 2015-03-02 2018-10-23 Emotiv, Inc. System and method for embedded cognitive state metric system
WO2016170810A1 (ja) * 2015-04-23 2016-10-27 ソニー株式会社 情報処理装置、制御方法、およびプログラム
US9676395B2 (en) * 2015-10-30 2017-06-13 Ford Global Technologies, Llc Incapacitated driving detection and prevention
CN106716297B (zh) * 2015-12-31 2019-11-05 华为技术有限公司 一种指纹识别的方法、装置及触摸屏终端
CN105520724A (zh) * 2016-02-26 2016-04-27 严定远 一种测量人体心跳速率和呼吸频率的方法

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101635743A (zh) * 2009-04-02 2010-01-27 浙江亚斯特科技有限公司 使用生物特征认证结果确认移动终端持有者身份的系统和方法
US8984622B1 (en) * 2012-01-17 2015-03-17 Amazon Technologies, Inc. User authentication through video analysis
CN105188522A (zh) * 2013-03-08 2015-12-23 富士胶片株式会社 脉搏波传播速度的测定方法、测定系统及摄像装置
CN104699931A (zh) * 2013-12-09 2015-06-10 广州华久信息科技有限公司 一种基于人脸的神经网络血压预测方法及手机
CN104809371A (zh) * 2014-01-24 2015-07-29 北京奇虎科技有限公司 判断头戴式智能设备的鉴权信息有效性的装置和方法
CN205179369U (zh) * 2014-11-26 2016-04-20 三星电子株式会社 用于与智能设备配对的可穿戴设备

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3489850A4 *

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110555918A (zh) * 2018-06-01 2019-12-10 杭州海康威视数字技术股份有限公司 考勤管理的方法和考勤管理设备

Also Published As

Publication number Publication date
US10824848B2 (en) 2020-11-03
CN107644189A (zh) 2018-01-30
US20190147223A1 (en) 2019-05-16
EP3489850B1 (en) 2021-04-14
EP3489850A4 (en) 2020-02-26
CN107644189B (zh) 2021-02-02
EP3489850A1 (en) 2019-05-29

Similar Documents

Publication Publication Date Title
US8724856B1 (en) Method, system and computer program for comparing images
WO2019134536A1 (zh) 基于神经网络模型的人脸活体检测
CN106295672B (zh) 一种人脸识别方法及装置
US10127428B2 (en) Fingerprint identification method and fingerprint identification device
US11281892B2 (en) Technologies for efficient identity recognition based on skin features
KR101276345B1 (ko) 다중 생체 인식 장치 및 방법
TWI640929B (zh) 指紋辨識方法以及指紋辨識裝置
US20150157243A1 (en) Health state determining method and apparatus using facial image
US20100215223A1 (en) Vein Pattern Management System, Vein Pattern Registration Apparatus, Vein Pattern Authentication Apparatus, Vein Pattern Registration Method, Vein Pattern Authentication Method, Program, and Vein Data Configuration
CN106056083B (zh) 一种信息处理方法及终端
US9449217B1 (en) Image authentication
US10956553B2 (en) Method of unlocking an electronic device, unlocking device and system and storage medium
US10853624B2 (en) Apparatus and method
US20140148709A1 (en) System and method for integrating heart rate measurement and identity recognition
US20210204123A1 (en) Iris recognition workflow
WO2018014851A1 (zh) 一种生物特征识别的方法，装置及存储介质
TW202105329A (zh) 人臉校驗方法、裝置、伺服器及可讀儲存媒介
IL264041A (en) Device for identity verification
US9390481B2 (en) Enhancing content appearance
KR100973832B1 (ko) 영상 선택 방법, 장치 및 그 방법을 실행하는 프로그램이기록된 기록매체
JP2018101289A (ja) 生体認証装置、生体認証システム、生体認証プログラム、及び生体認証方法
Rasti et al. Statistical approach based iris recognition using local binary pattern
TWI547882B (zh) 生物特徵辨識系統、辨識方法、儲存媒體及生物特徵辨識處理晶片
CN116152936B (zh) 一种带交互式活体检测的人脸身份认证系统及其方法
KR101228946B1 (ko) 신뢰구간을 이용하여 인식 결과를 예측하는 인증 방법 및 인증 시스템

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: 17830485

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2017830485

Country of ref document: EP

Effective date: 20190220