CN106407914B - Method and device for detecting human face and remote teller machine system - Google Patents

Method and device for detecting human face and remote teller machine system Download PDF

Info

Publication number
CN106407914B
CN106407914B CN201610798437.3A CN201610798437A CN106407914B CN 106407914 B CN106407914 B CN 106407914B CN 201610798437 A CN201610798437 A CN 201610798437A CN 106407914 B CN106407914 B CN 106407914B
Authority
CN
China
Prior art keywords
recognized
face
image
information
living body
Prior art date
Legal status (The legal status 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 status listed.)
Active
Application number
CN201610798437.3A
Other languages
Chinese (zh)
Other versions
CN106407914A (en
Inventor
邵猛
印奇
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Beijing Megvii Technology Co Ltd
Beijing Maigewei Technology Co Ltd
Original Assignee
Beijing Megvii Technology Co Ltd
Beijing Maigewei Technology Co Ltd
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 Beijing Megvii Technology Co Ltd, Beijing Maigewei Technology Co Ltd filed Critical Beijing Megvii Technology Co Ltd
Priority to CN201610798437.3A priority Critical patent/CN106407914B/en
Publication of CN106407914A publication Critical patent/CN106407914A/en
Application granted granted Critical
Publication of CN106407914B publication Critical patent/CN106407914B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

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
    • G06V40/168—Feature extraction; Face representation
    • G06V40/171—Local features and components; Facial parts ; Occluding parts, e.g. glasses; Geometrical relationships
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06F—ELECTRIC DIGITAL DATA PROCESSING
    • G06F18/00—Pattern recognition
    • G06F18/20—Analysing
    • G06F18/22—Matching criteria, e.g. proximity measures
    • 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
    • G06V40/165—Detection; Localisation; Normalisation using facial parts and geometric relationships
    • 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
    • G07—CHECKING-DEVICES
    • G07F—COIN-FREED OR LIKE APPARATUS
    • G07F19/00—Complete banking systems; Coded card-freed arrangements adapted for dispensing or receiving monies or the like and posting such transactions to existing accounts, e.g. automatic teller machines
    • G07F19/20—Automatic teller machines [ATMs]

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Oral & Maxillofacial Surgery (AREA)
  • General Physics & Mathematics (AREA)
  • Theoretical Computer Science (AREA)
  • Health & Medical Sciences (AREA)
  • Multimedia (AREA)
  • Human Computer Interaction (AREA)
  • General Health & Medical Sciences (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Data Mining & Analysis (AREA)
  • Evolutionary Computation (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
  • Bioinformatics & Cheminformatics (AREA)
  • General Engineering & Computer Science (AREA)
  • Finance (AREA)
  • Accounting & Taxation (AREA)
  • Life Sciences & Earth Sciences (AREA)
  • Artificial Intelligence (AREA)
  • Evolutionary Biology (AREA)
  • Bioinformatics & Computational Biology (AREA)
  • Geometry (AREA)
  • Collating Specific Patterns (AREA)
  • Business, Economics & Management (AREA)

Abstract

The embodiment of the invention provides a method and a device for detecting a human face and a remote teller machine system. The method comprises the following steps: acquiring an image pair to be recognized, wherein the image pair to be recognized comprises two images to be recognized which are respectively acquired by two cameras aiming at a face to be recognized; obtaining the depth information of the face to be recognized according to the image pair to be recognized; acquiring a light spot pattern formed by a face to be recognized under the irradiation of infrared structural light; acquiring texture information of the face to be recognized according to the light spot pattern; and determining whether the face to be recognized belongs to the living body or not by combining the depth information and the texture information. The method, the device and the remote teller machine system have low matching requirement, high speed and high safety.

Description

Method and device for detecting human face and remote teller machine system
Technical Field
The present invention relates to the field of face recognition, and more particularly, to a method, an apparatus, and a remote teller machine system for detecting a face.
background
Currently, unattended automatic authentication systems have been widely used, such as remote Video Teller Machines (VTMs) of banks, cell gate systems, and the like. The identity authentication system based on face recognition can solve the problems caused by manual discrimination and the use of media such as IC cards. Before face recognition, it may be first detected whether the acquired face belongs to a living body. At present, the conventional in vivo detection modes mainly comprise two modes: the detection is performed by using a common camera through a coordinated random action and the detection is performed by using a bright pupil effect. Both of these approaches have their own problems. The detection mode based on the common camera requires a user to randomly do a plurality of actions, has high matching difficulty and long time, and is difficult to identify the attacks on masks, videos and paper photos. The detection mode based on the bright pupil effect is easy to attack by various masks combined with devices simulating pupils, and the detection mode also has the safety problem.
Disclosure of Invention
The present invention has been made in view of the above problems. The invention provides a method and a device for detecting a human face and a remote teller machine system.
according to an aspect of the present invention, there is provided a method for detecting a human face. The method comprises the following steps: acquiring an image pair to be recognized, wherein the image pair to be recognized comprises two images to be recognized which are respectively acquired by two cameras aiming at a face to be recognized; obtaining the depth information of the face to be recognized according to the image pair to be recognized; acquiring a light spot pattern formed by the face to be recognized under the irradiation of the infrared structural light; acquiring texture information of the face to be recognized according to the light spot pattern; and determining whether the face to be recognized belongs to a living body or not by combining the depth information and the texture information.
Illustratively, the method further comprises: if the face to be recognized does not belong to the living body is determined for all the image pairs to be recognized collected in a preset time period after the starting moment, determining that the living body detection fails; and determining that the living body detection is passed if it is determined that the face to be recognized belongs to the living body for the specific pair of images to be recognized acquired within the preset period after the start time.
Illustratively, after the determining the pass of the live test, the method further comprises: selecting an image to be recognized with the best face quality from at least part of images to be recognized collected by a specific camera in the two cameras in a time period from the starting time to the collection time of the specific image pair to be recognized; and carrying out face recognition on the face to be recognized by using the selected image to be recognized.
Illustratively, before the recognizing the face of the person to be recognized by using the selected image to be recognized, the method further comprises: acquiring identity card information of an object to which the face to be recognized belongs, wherein the identity card information comprises an identity card face; the face recognition of the face to be recognized by using the selected image to be recognized comprises: and comparing the face to be recognized in the selected image to be recognized with the face of the identity card to determine whether the face to be recognized is consistent with the face of the identity card.
Illustratively, the performing face recognition on the face to be recognized by using the selected image to be recognized includes: comparing the face to be recognized in the selected image to known faces in a first database to determine whether the face to be recognized is one of the known faces in the first database.
illustratively, the selecting the image to be recognized with the best face quality from at least part of the images to be recognized collected by a specific camera of the two cameras in the time period from the starting time to the collection time of the specific image pair to be recognized comprises: scoring each of the at least some of the images to be identified according to one or more of the following parameters: the face brightness, the side light inverse luminosity, the pitch degree, the left and right inclination, the eye opening degree and the mouth opening degree of the face to be recognized in the image to be recognized; and selecting the image to be recognized with the highest score as the image to be recognized with the best face quality.
Illustratively, the determining whether the face to be recognized belongs to a living body by combining the depth information and the texture information includes: and if the texture information conforms to the human skin texture distribution rule and the depth information conforms to the human face depth distribution rule, determining that the human face to be recognized belongs to the living body, otherwise, determining that the human face to be recognized does not belong to the living body.
Illustratively, the method further comprises: and when the image pair to be recognized is obtained, outputting action prompt information to indicate the object to which the face to be recognized belongs to execute the action corresponding to the action prompt information.
Illustratively, before the outputting the action prompt message, the method further comprises: randomly acquiring at least one action prompt message from a second database, wherein the second database comprises a plurality of different action prompt messages; the outputting the action prompt message comprises: and outputting the acquired action prompt information in a text display mode and/or a voice broadcast mode.
According to another aspect of the present invention, there is provided an apparatus for detecting a human face, comprising: the image acquisition module is used for acquiring an image pair to be recognized, wherein the image pair to be recognized comprises two images to be recognized which are respectively acquired by two cameras aiming at a face to be recognized; the depth information acquisition module is used for acquiring the depth information of the face to be recognized according to the image pair to be recognized; the light spot pattern acquisition module is used for acquiring a light spot pattern formed by the face to be recognized under the irradiation of the infrared structural light; the texture information obtaining module is used for obtaining the texture information of the face to be recognized according to the light spot pattern; and the living body detection module is used for determining whether the face to be recognized belongs to a living body or not by combining the depth information and the texture information.
Illustratively, the apparatus further comprises: the failure determination module is used for determining that the face to be recognized does not belong to a living body if all the image pairs to be recognized collected in a preset time period after the starting time are determined to be not the living body; and a pass determination module for determining that the living body detection passes if it is determined that the face to be recognized belongs to the living body for a specific pair of images to be recognized acquired within the preset period after the start time.
Illustratively, the apparatus further comprises: the selection module is used for selecting an image to be recognized with the best face quality from at least part of images to be recognized collected by a specific camera in the two cameras in a time period from the starting time to the collection time of the specific image pair to be recognized; and the face recognition module is used for carrying out face recognition on the face to be recognized by utilizing the selected image to be recognized.
Illustratively, the apparatus further comprises: the identity card information acquisition module is used for acquiring identity card information of an object to which the face to be recognized belongs, wherein the identity card information comprises an identity card face; the face recognition module includes: and the first comparison submodule is used for comparing the face to be recognized in the selected image to be recognized with the face of the identity card so as to determine whether the face to be recognized is consistent with the face of the identity card.
Illustratively, the face recognition module includes: and the second comparison sub-module is used for comparing the face to be recognized in the selected image to be recognized with the known faces in the first database so as to determine whether the face to be recognized is one of the known faces in the first database.
Illustratively, the selection module includes: a scoring submodule for scoring each of the at least some of the images to be identified according to one or more of the following parameters: the face brightness, the side light inverse luminosity, the pitch degree, the left and right inclination, the eye opening degree and the mouth opening degree of the face to be recognized in the image to be recognized; and the selection submodule is used for selecting the image to be recognized with the highest score as the image to be recognized with the best face quality.
illustratively, the liveness detection module includes: the first determining submodule is used for determining that the face to be recognized belongs to a living body if the texture information conforms to a human skin texture distribution rule and the depth information conforms to a face depth distribution rule; and the second determining submodule is used for determining that the face to be recognized does not belong to a living body if the texture information does not accord with the human skin texture distribution rule or the depth information does not accord with the face depth distribution rule.
Illustratively, the apparatus further comprises: and the action prompt module is used for outputting action prompt information when the image acquisition module acquires the image pair to be recognized so as to instruct the object to which the face to be recognized belongs to execute the action corresponding to the action prompt information.
Illustratively, the apparatus further comprises: the prompt information acquisition module is used for randomly acquiring at least one action prompt information from a second database, wherein the second database comprises a plurality of different action prompt information; the action prompt module comprises: and the prompt information output submodule is used for outputting the acquired action prompt information in a text display mode and/or a voice broadcast mode.
According to another aspect of the invention, a remote teller machine system is provided, which comprises two cameras, an infrared structure light emitting device and the device for detecting a human face, wherein the two cameras are used for acquiring two images to be recognized aiming at the human face to be recognized, obtaining an image pair to be recognized, and sending the image pair to be recognized to the image acquisition module; the infrared structure light emitting device is used for emitting infrared structure light to the face to be recognized so as to form the light spot pattern on the face to be recognized.
Exemplarily, the system further comprises a display and/or a voice device, wherein the display is used for displaying the images to be recognized collected by the two cameras in real time, receiving action prompt information from the device for detecting the human face and displaying the action prompt information through characters; the voice equipment is used for receiving the action prompt information from the device for detecting the human face and broadcasting the action prompt information through voice; and the action prompt information is used for indicating the object to which the face to be recognized belongs to execute the action corresponding to the action prompt information.
According to the method, the device and the remote teller machine system for detecting the human face, the cooperation of users is not needed, so that the cooperation requirement is low, the speed is high, in addition, the method is combined with the depth information and the texture information to carry out the living body detection, the attacks such as the mask attack can be effectively prevented, and the safety is high.
Drawings
The above and other objects, features and advantages of the present invention will become more apparent by describing in more detail embodiments of the present invention with reference to the attached drawings. The accompanying drawings are included to provide a further understanding of the embodiments of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings, like reference numbers generally represent like parts or steps.
FIG. 1 shows a schematic block diagram of an example electronic device for implementing a method and apparatus for detecting faces in accordance with embodiments of the invention;
FIG. 2 shows a schematic flow diagram of a method for detecting faces according to one embodiment of the invention;
FIG. 3 shows a schematic block diagram of an apparatus for detecting faces according to one embodiment of the invention; and
Fig. 4 shows a schematic block diagram of a system for detecting a human face according to an embodiment of the invention.
Detailed Description
in order to make the objects, technical solutions and advantages of the present invention more apparent, exemplary embodiments according to the present invention will be described in detail below with reference to the accompanying drawings. It is to be understood that the described embodiments are merely a subset of embodiments of the invention and not all embodiments of the invention, with the understanding that the invention is not limited to the example embodiments described herein. All other embodiments, which can be derived by a person skilled in the art from the embodiments of the invention described herein without inventive step, shall fall within the scope of protection of the invention.
In order to overcome the defects of the conventional in-vivo detection technology (such as the in-vivo detection technology adopted by the existing identity verification system), the embodiment of the invention provides a method for performing in-vivo detection (and subsequent face recognition) based on a binocular camera.
First, an example electronic device 100 for implementing the method and apparatus for detecting a human face according to an embodiment of the present invention is described with reference to fig. 1.
As shown in FIG. 1, electronic device 100 includes one or more processors 102, one or more memory devices 104, an input device 106, an output device 108, and an image capture device 110, which are interconnected via a bus system 112 and/or other form of connection mechanism (not shown). It should be noted that the components and structure of the electronic device 100 shown in fig. 1 are exemplary only, and not limiting, and the electronic device may have other components and structures as desired.
The processor 102 may be a Central Processing Unit (CPU) or other form of processing unit having data processing capabilities and/or instruction execution capabilities, and may control other components in the electronic device 100 to perform desired functions.
The storage 104 may include one or more computer program products that may include various forms of computer-readable storage media, such as volatile memory and/or non-volatile memory. The volatile memory may include, for example, Random Access Memory (RAM), cache memory (cache), and/or the like. The non-volatile memory may include, for example, Read Only Memory (ROM), hard disk, flash memory, etc. On which one or more computer program instructions may be stored that may be executed by processor 102 to implement client-side functionality (implemented by the processor) and/or other desired functionality in embodiments of the invention described below. Various applications and various data, such as various data used and/or generated by the applications, may also be stored in the computer-readable storage medium.
The input device 106 may be a device used by a user to input instructions and may include one or more of a keyboard, a mouse, a microphone, a touch screen, and the like.
The output device 108 may output various information (e.g., images and/or sounds) to an external (e.g., user), and may include one or more of a display, a speaker, etc.
The image acquisition device 110 may acquire a desired image (e.g., an image that requires a biopsy) and store the acquired image in the storage device 104 for use by other components. The image capturing device 110 may be implemented by any suitable device, such as a camera of an access control system. The image capture device 110 is merely an example, and the electronic device 100 may not include the image capture device 110.
Exemplary electronic devices for implementing the method and apparatus for detecting a human face according to embodiments of the present invention may be implemented on devices such as a personal computer or a remote server.
Hereinafter, a method for detecting a human face according to an embodiment of the present invention will be described with reference to fig. 2. Fig. 2 shows a schematic flow diagram of a method 200 for detecting a face according to an embodiment of the invention. As shown in fig. 2, a method 200 for detecting a human face includes the following steps.
in step S210, an image pair to be recognized is obtained, where the image pair to be recognized includes two images to be recognized that are respectively acquired by two cameras for a face to be recognized.
The two cameras constitute a binocular camera which can simulate both eyes of a human being. The two cameras are at different positions, namely, images of the same object are collected from different visual angles, and depth information of the object can be obtained based on the images collected by the two cameras.
The image to be recognized may be from an external camera, which is transmitted to the electronic device 100 for live body detection (and subsequent face recognition). In addition, the image to be recognized may also be acquired by the image acquisition device 110 of the electronic device 100, that is, the two cameras are implemented by the image acquisition device 110. The image capture device 110 may transmit the captured image to the processor 102 for liveness detection (and subsequent face recognition) by the processor 102. The image to be recognized may be an original image or an image obtained by preprocessing the original image.
In step S220, depth information of the face to be recognized is obtained according to the image pair to be recognized.
The depth information of the face to be recognized can be obtained from the images to be recognized which are collected under two different visual angles. Specifically, a three-dimensional contour of the face to be recognized may be determined using the image pair to be recognized based on the principle of parallax, and three-dimensional coordinates of any feature point on the contour (i.e., depth information of the face to be recognized) may be obtained.
in step S230, a light spot pattern formed by the human face to be recognized under the irradiation of the infrared structured light is obtained.
An infrared structure light emitter can be placed between the two cameras, and infrared structure light is emitted to the face to be recognized by the infrared structure light emitter. Under the irradiation of the infrared structural light, a light spot pattern is formed on the face to be recognized. The speckle pattern may be received by either of the two cameras and then transmitted to a back-end processor (e.g., processor 102 shown in fig. 1) for processing. The two cameras, the infrared structure light emitter and the processor at the rear end can form a binocular stereoscopic vision system.
In step S240, texture information of the face to be recognized is obtained according to the spot pattern.
Different material structures can form different light spot patterns under the structured light. The processor can obtain the texture information of the human face, namely the material property of the surface of the human face according to the received light spot pattern. And if the texture information of the face to be recognized is found not to conform to the human skin texture distribution rule, determining that the face to be recognized is not a living body, and judging the face to be recognized as a mask attack and the like.
In step S250, it is determined whether the face to be recognized belongs to a living body in combination with the depth information and the texture information.
since the attacker can use the mask made of the artificial human skin material to carry out the attack, even if the texture information of the face to be recognized accords with the human skin texture distribution rule, the face to be recognized cannot be determined to belong to the living body, and therefore whether the face to be recognized belongs to the living body can be further judged by combining the depth information. It should be understood that a real face is usually fluctuated, for example, the coordinate depths of the eyes and the nose are different and have a large difference, while a mask made of a material imitating the human skin is fluctuated a little and has a small difference between the coordinate depths of the eyes and the nose. Therefore, whether the face to be recognized belongs to the living body can be further judged by combining the depth information.
It should be understood that two cameras may capture one image pair to be identified, or may capture a plurality of image pairs to be identified, that is, for each camera, it may capture both still images and video. In the case where the camera captures a video, the image to be recognized belongs to one frame in the video, and the above-described steps S210 to S250 may be performed for each pair of images to be recognized to determine whether the face to be recognized belongs to a living body.
It should be understood that the execution order of the steps shown in fig. 2 is only an example and not a limitation of the present invention, and the present invention may have other reasonable execution orders. For example, any one of steps S230 and S240 may be performed before, after, or simultaneously with step S210, or before, after, or simultaneously with step S220.
The method for detecting the human face does not need user cooperation, so that the cooperation requirement is low, the speed is high, in addition, the method combines depth information and texture information to carry out living body detection, attacks such as mask attack and the like can be effectively prevented, and the safety is higher.
Illustratively, the method for detecting a human face according to embodiments of the present invention may be implemented in a device, apparatus or system having a memory and a processor.
The method for detecting the human face according to the embodiment of the invention can be deployed at an image acquisition end, for example, the method can be deployed at an image acquisition end of a bank VTM or an access control system. Alternatively, the method for detecting a human face according to the embodiment of the present invention may also be deployed at a server side (or a cloud side). For example, an image to be recognized may be collected at a client, and the client transmits the collected image to be recognized to a server (or a cloud), and the server (or the cloud) performs living body detection (and subsequent face recognition).
According to an embodiment of the invention, the method 200 may further comprise: if the face to be recognized does not belong to the living body is determined for all the image pairs to be recognized collected in the preset time period after the starting moment, determining that the living body detection fails; and determining that the living body detection is passed if it is determined that the face to be recognized belongs to the living body for the specific pair of images to be recognized acquired within a preset period after the start time.
The preset time period may be any suitable time period, which may be set as needed, and the present invention is not limited thereto. For example, the preset period may be 10 seconds, 20 seconds, 30 seconds, 1 minute, or the like.
In this embodiment, what two cameras gathered can be videos, and the image to be recognized is one frame in the video. It is assumed that after the detection starts, two cameras can acquire 200 images to be recognized within a preset time period, that is, each camera acquires 200 images to be recognized respectively. For example, it may be determined whether the face to be recognized belongs to a living body while acquiring the pair of images to be recognized. If the face to be recognized is determined to belong to a living body when the 150 th image pair to be recognized is acquired, the living body detection can be determined to pass, and the subsequent face recognition can be entered. The 150 th image pair to be recognized is the specific image pair to be recognized. If the face to be recognized still cannot be determined to belong to the living body after 200 pairs of images to be recognized are acquired, the failure of the living body detection can be determined, in this case, the whole process of detecting the face can be finished, namely, the subsequent face recognition process is not performed, and the failure result can be output.
the preset time period is set, so that the detection time of the living body detection can be conveniently controlled according to needs.
According to an embodiment of the present invention, after determining that the in vivo test has passed, the method 200 may further include: selecting an image to be recognized with the best face quality from at least part of images to be recognized collected by a specific camera in the two cameras in a time period from the starting time to the collection time of the specific image pair to be recognized; and carrying out face recognition on the face to be recognized by using the selected image to be recognized.
the particular camera may be any one of two cameras, which is not a limitation of the present invention.
following the above example, assuming that after the detection starts, two cameras can acquire 200 pairs of images to be recognized within a preset time period, if it is determined that the face to be recognized belongs to a living body when the 150 th pair of images to be recognized is acquired, an image to be recognized with the best face quality can be selected from at least a part of the first 150 images to be recognized acquired by a certain camera. And selecting the image to be recognized with the best quality to facilitate subsequent face recognition. The better the face quality is, the clearer the detected face to be recognized is, the closer the face to be recognized is to the real face, and therefore the higher the accuracy of face recognition is.
Face recognition may include face verification, i.e., one-to-one face image comparison, or face recognition, i.e., one-to-many face image comparison, as will be described below in connection with specific embodiments.
According to an embodiment, before performing face recognition on a face to be recognized by using the selected image to be recognized, the method 200 may further include: acquiring identity card information of an object to which a face to be recognized belongs, wherein the identity card information comprises an identity card face; performing face recognition on the face to be recognized by using the selected image to be recognized may include: and comparing the face to be recognized in the selected image to be recognized with the face of the identity card to determine whether the face to be recognized is consistent with the face of the identity card.
the embodiment can be applied to the scenes such as identity verification in the self-service business handling of a bank VTM (Video Teller Machine, remote Teller Machine or remote Video Teller Machine). For example, in a bank VTM self-service business office, a user may present his or her own identification card and scan the identification card with a scanner in the VTM to obtain the user's identification card information. The identity card information may include a face of the identity card, and of course, may also include information such as an identity card number. After obtaining the identification card information, the identification card information may be processed by a processor local to the VTM or may be transmitted to a remote server (or cloud) for processing. Then, the local processor or the server (or the cloud) can compare the acquired face of the identity card with the face to be recognized, and determine whether the face to be recognized and the face on the identity card represent the same person. The face to be recognized participating in the comparison is detected and recognized from the selected image to be recognized having the best face quality.
In the face recognition process, since the living body detection is performed in advance, a certain user can be prevented from performing authentication by using a photo and an identification card of another person.
According to another embodiment, the face recognition of the face to be recognized using the selected image to be recognized may include: and comparing the face to be recognized in the selected image to be recognized with the known faces in the first database to determine whether the face to be recognized is one of the known faces in the first database.
The embodiment can be applied to scenes such as entrance guard control and the like. For example, in an access control system application, a database storing face data of persons authorized to enter (e.g., residents of a cell) in an area in which the access control system is responsible, that is, a first database, may be read. When someone needs to enter the area, the face to be recognized and all known faces in the first database can be compared one by one to determine whether the object to which the face to be recognized belongs is qualified to enter. This is similar to the management of a conventional access control system, and is not described herein.
According to the embodiment of the present invention, selecting an image to be recognized with the best face quality from at least some images to be recognized collected by a specific camera of the two cameras in a time period from a start time to a collection time of the specific image pair to be recognized may include: scoring each of at least some of the images to be identified according to one or more of the following parameters: the face brightness, the side light inverse luminosity, the pitch degree, the left and right inclination, the eye opening degree and the mouth opening degree of the face to be recognized in the image to be recognized; and selecting the image to be recognized with the highest score as the image to be recognized with the best face quality.
The parameters of face brightness, side light inverse luminosity, pitch, left and right inclination, eye opening degree and mouth opening degree can be used as indexes for evaluating the face quality. Of course, the above indexes are only examples and are not limiting to the present invention, and the present invention may adopt other suitable indexes to evaluate the face quality. The image to be recognized, in which the brightness of the face to be recognized is high, the side light inverse luminosity is low, the face is over against the camera (i.e. the pitch and the left-right inclination are low), and the eyes are opened and the mouth is closed, belongs to the image with high face quality. In a word, whether the face quality is high or low can be judged according to the posture, the illumination condition and the like of the face to be recognized in each image to be recognized, and a score is given to each image to be recognized for evaluating the face quality of the image to be recognized. Then, the image to be recognized with the highest score can be selected from the at least part of the images to be recognized as the image to be recognized with the best face quality, and the image to be recognized is used for subsequent face recognition.
According to the embodiment of the present invention, step S250 may include: and if the texture information conforms to the human skin texture distribution rule and the depth information conforms to the human face depth distribution rule, determining that the human face to be recognized belongs to the living body, otherwise, determining that the human face to be recognized does not belong to the living body.
In some examples of the invention, the method 200 may further include: when step S210 is executed, the action prompt information is output to instruct the object to which the face to be recognized belongs to execute the action corresponding to the action prompt information. For example, the motion prompt information may include prompt information about motions such as mouth opening, mouth closing, eye opening, nodding, head shaking, smiling, and the like, for example, when the motion prompt information is prompt information about nodding, that is, instructing an object to which a face to be recognized belongs to perform nodding motion.
Further, according to an exemplary embodiment of the present invention, before outputting the action prompt message, the method 200 may further include: randomly acquiring at least one action prompt message from a second database, wherein the second database comprises a plurality of different action prompt messages; the outputting the action prompt message comprises: and outputting the acquired action prompt information in a text display mode and/or a voice broadcast mode.
Specifically, the action prompt information may be stored in a second database (a plurality of different action prompt information may be stored), one or more action prompt information may be randomly selected from the second database, and the object to which the face to be recognized belongs may be prompted to execute the corresponding action in a random or specific order. And the acquired action prompt information can be provided for the object to which the face to be recognized belongs in a text display mode and/or a voice broadcast mode. In other examples, when the object to which the face to be recognized belongs accurately completes the corresponding action or fails to accurately complete the corresponding action according to the action prompt information, the object to which the face to be recognized belongs may be notified through text display, icon display (e.g., a tick icon), and/or voice.
As described above, both the texture information and the depth information can reflect to a certain extent whether the face to be recognized is a human face or a mask, a video, a photograph, etc., and the combination of the two can more accurately determine whether the face to be recognized belongs to a living body. The human skin texture distribution rule and the human face depth distribution rule as the basis for judgment can be set based on theory or experience.
According to another aspect of the present invention, there is provided an apparatus for detecting a human face. Fig. 3 shows a schematic block diagram of an apparatus 300 for detecting a human face according to an embodiment of the present invention.
As shown in fig. 3, the apparatus 300 for detecting a human face according to an embodiment of the present invention includes an image acquisition module 310, a depth information acquisition module 320, a spot pattern acquisition module 330, a texture information acquisition module 340, and a live body detection module 350.
The image obtaining module 310 is configured to obtain an image pair to be recognized, where the image pair to be recognized includes two images to be recognized, which are respectively acquired by two cameras for a face to be recognized. The image acquisition module 310 may be implemented by the processor 102 in the electronic device shown in fig. 1 executing program instructions stored in the storage 104.
The depth information obtaining module 320 is configured to obtain depth information of the face to be recognized according to the image pair to be recognized. The depth information obtaining module 320 may be implemented by the processor 102 in the electronic device shown in fig. 1 executing program instructions stored in the storage 104.
The light spot pattern obtaining module 330 is configured to obtain a light spot pattern formed by the face to be recognized under the irradiation of the infrared structured light. Speckle pattern acquisition module 330 may be implemented by processor 102 in the electronic device shown in fig. 1 executing program instructions stored in storage 104.
The texture information obtaining module 340 is configured to obtain texture information of the face to be recognized according to the light spot pattern. The texture information obtaining module 340 may be implemented by the processor 102 in the electronic device shown in fig. 1 executing program instructions stored in the storage 104.
The living body detection module 350 is configured to determine whether the face to be recognized belongs to a living body by combining the depth information and the texture information. The liveness detection module 350 may be implemented by the processor 102 in the electronic device shown in FIG. 1 executing program instructions stored in the memory device 104.
According to an embodiment of the present invention, the apparatus 300 further comprises: the failure determination module is used for determining that the face to be recognized does not belong to a living body if all the image pairs to be recognized collected in a preset time period after the starting time are determined to be not the living body; and a pass determination module for determining that the living body detection passes if it is determined that the face to be recognized belongs to the living body for a specific pair of images to be recognized acquired within the preset period after the start time.
according to an embodiment of the present invention, the apparatus 300 further comprises: the selection module is used for selecting an image to be recognized with the best face quality from at least part of images to be recognized collected by a specific camera in the two cameras in a time period from the starting time to the collection time of the specific image pair to be recognized; and the face recognition module is used for carrying out face recognition on the face to be recognized by utilizing the selected image to be recognized.
according to an embodiment of the present invention, the apparatus 300 further comprises: the identity card information acquisition module is used for acquiring identity card information of an object to which the face to be recognized belongs, wherein the identity card information comprises an identity card face; the face recognition module includes: and the first comparison submodule is used for comparing the face to be recognized in the selected image to be recognized with the face of the identity card so as to determine whether the face to be recognized is consistent with the face of the identity card.
According to an embodiment of the present invention, the face recognition module includes: and the second comparison sub-module is used for comparing the face to be recognized in the selected image to be recognized with the known faces in the first database so as to determine whether the face to be recognized is one of the known faces in the first database.
According to an embodiment of the invention, the selection module comprises: a scoring submodule for scoring each of the at least some of the images to be identified according to one or more of the following parameters: the face brightness, the side light inverse luminosity, the pitch degree, the left and right inclination, the eye opening degree and the mouth opening degree of the face to be recognized in the image to be recognized; and the selection submodule is used for selecting the image to be recognized with the highest score as the image to be recognized with the best face quality.
According to an embodiment of the present invention, the liveness detection module 350 includes: the first determining submodule is used for determining that the face to be recognized belongs to a living body if the texture information conforms to a human skin texture distribution rule and the depth information conforms to a face depth distribution rule; and the second determining submodule is used for determining that the face to be recognized does not belong to a living body if the texture information does not accord with the human skin texture distribution rule or the depth information does not accord with the face depth distribution rule.
according to an embodiment of the present invention, the apparatus 300 further comprises: and an action prompt module (not shown in the figure) for outputting action prompt information when the image acquisition module acquires the pair of images to be recognized so as to instruct the object to which the face to be recognized belongs to execute an action corresponding to the action prompt information.
According to the embodiment of the present invention, the device further includes a prompt information obtaining module (not shown in the figure), and the action prompt module (not shown in the figure) includes a prompt information output sub-module (not shown in the figure). The prompt information acquisition module is used for randomly acquiring at least one action prompt message from a second database, the second database comprises a plurality of different action prompt messages, and the prompt information output submodule is used for outputting the acquired action prompt messages in a text display mode and/or a voice broadcast mode.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
fig. 4 shows a schematic block diagram of a system 400 for detecting a human face according to an embodiment of the invention. The system 400 for detecting a human face includes an image acquisition device 410, a storage device 420, and a processor 430.
The image capturing device 410 is used for capturing an image to be recognized. The image acquisition device 410 is optional and the system 400 for detecting a human face may not include the image acquisition device 410.
the storage 420 stores program codes for implementing respective steps in the method for detecting a human face according to an embodiment of the present invention.
The processor 430 is configured to run the program codes stored in the storage device 420 to perform the corresponding steps of the method for detecting a human face according to the embodiment of the present invention, and is configured to implement the image acquisition module 310, the depth information acquisition module 320, the speckle pattern acquisition module 330, the texture information acquisition module 340 and the living body detection module 350 in the apparatus for detecting a human face according to the embodiment of the present invention.
In one embodiment, the program code, when executed by the processor 430, causes the system for detecting faces 400 to perform the steps of: acquiring an image pair to be recognized, wherein the image pair to be recognized comprises two images to be recognized which are respectively acquired by two cameras aiming at a face to be recognized; obtaining the depth information of the face to be recognized according to the image pair to be recognized; acquiring a light spot pattern formed by the face to be recognized under the irradiation of the infrared structural light; acquiring texture information of the face to be recognized according to the light spot pattern; and determining whether the face to be recognized belongs to a living body or not by combining the depth information and the texture information.
In one embodiment, the program code, when executed by the processor 430, causes the system for detecting a human face 400 to further perform: if the face to be recognized does not belong to the living body is determined for all the image pairs to be recognized collected in a preset time period after the starting moment, determining that the living body detection fails; and determining that the living body detection is passed if it is determined that the face to be recognized belongs to the living body for the specific pair of images to be recognized acquired within the preset period after the start time.
In one embodiment, after the step of determining the passage of a live detection performed by the system for detecting a human face 400 when the program code is executed by the processor 430, the program code further causes the system for detecting a human face 400 to perform, when the program code is executed by the processor 430: selecting an image to be recognized with the best face quality from at least part of images to be recognized collected by a specific camera in the two cameras in a time period from the starting time to the collection time of the specific image pair to be recognized; and carrying out face recognition on the face to be recognized by using the selected image to be recognized.
In one embodiment, before the step of performing face recognition on the face to be recognized by using the selected image to be recognized by the system for detecting a face 400 executed by the processor 430, the program code when executed by the processor 430 causes the system for detecting a face 400 to further perform: acquiring identity card information of an object to which the face to be recognized belongs, wherein the identity card information comprises an identity card face; the program code, when executed by the processor 430, causes the system for detecting a human face 400 to perform the steps of performing face recognition on the human face to be recognized using the selected image to be recognized, including: and comparing the face to be recognized in the selected image to be recognized with the face of the identity card to determine whether the face to be recognized is consistent with the face of the identity card.
in one embodiment, the program code, when executed by the processor 430, causes the system for detecting a human face 400 to perform the step of performing face recognition on the human face to be recognized by using the selected image to be recognized, including: comparing the face to be recognized in the selected image to known faces in a first database to determine whether the face to be recognized is one of the known faces in the first database.
in one embodiment, the program code, when executed by the processor 430, causes the system for detecting a human face 400 to perform the step of selecting an image to be recognized with the best quality of a human face from at least some images to be recognized acquired by a specific camera of the two cameras in a time period from the start time to the acquisition time of the specific image pair to be recognized, including: scoring each of the at least some of the images to be identified according to one or more of the following parameters: the face brightness, the side light inverse luminosity, the pitch degree, the left and right inclination, the eye opening degree and the mouth opening degree of the face to be recognized in the image to be recognized; and selecting the image to be recognized with the highest score as the image to be recognized with the best face quality.
In one embodiment, the program code, when executed by the processor 430, causes the system for detecting a face 400 to perform the step of determining whether the face to be recognized belongs to a living body in combination with the depth information and the texture information, including: and if the texture information conforms to the human skin texture distribution rule and the depth information conforms to the human face depth distribution rule, determining that the human face to be recognized belongs to the living body, otherwise, determining that the human face to be recognized does not belong to the living body.
in one embodiment, when executed by the processor 430, the program code causes the system 400 for detecting a human face to output action prompt information when the step of acquiring the pair of images to be recognized is executed, so as to instruct an object to which the human face to be recognized belongs to execute an action corresponding to the action prompt information.
In one embodiment, before the step of outputting the action prompt information performed by the system for detecting a human face 400 when the program code is executed by the processor 430, the system for detecting a human face 400 further performs: randomly acquiring at least one action prompt message from a second database, wherein the second database comprises a plurality of different action prompt messages; the program code when executed by the processor 430 causes the system for detecting a human face 400 to perform the step of outputting an action prompt message comprising: and outputting the acquired action prompt information in a text display mode and/or a voice broadcast mode.
Furthermore, according to an embodiment of the present invention, there is also provided a storage medium on which program instructions are stored, which when executed by a computer or a processor are used for executing the corresponding steps of the method for detecting a human face according to the embodiment of the present invention, and for implementing the corresponding modules in the apparatus for detecting a human face according to the embodiment of the present invention. The storage medium may include, for example, a memory card of a smart phone, a storage component of a tablet computer, a hard disk of a personal computer, a Read Only Memory (ROM), an Erasable Programmable Read Only Memory (EPROM), a portable compact disc read only memory (CD-ROM), a USB memory, or any combination of the above storage media.
in one embodiment, the computer program instructions, when executed by a computer or a processor, may cause the computer or the processor to implement the functional modules of the apparatus for detecting a human face according to the embodiment of the present invention and/or may perform the method for detecting a human face according to the embodiment of the present invention.
in one embodiment, the computer program instructions, when executed by a computer, cause the computer to perform the steps of: acquiring an image pair to be recognized, wherein the image pair to be recognized comprises two images to be recognized which are respectively acquired by two cameras aiming at a face to be recognized; obtaining the depth information of the face to be recognized according to the image pair to be recognized; acquiring a light spot pattern formed by the face to be recognized under the irradiation of the infrared structural light; acquiring texture information of the face to be recognized according to the light spot pattern; and determining whether the face to be recognized belongs to a living body or not by combining the depth information and the texture information.
In one embodiment, the computer program instructions, when executed by a computer, cause the computer to further perform: if the face to be recognized does not belong to the living body is determined for all the image pairs to be recognized collected in a preset time period after the starting moment, determining that the living body detection fails; and determining that the living body detection is passed if it is determined that the face to be recognized belongs to the living body for the specific pair of images to be recognized acquired within the preset period after the start time.
In one embodiment, after the computer program instructions, when executed by a computer, cause the computer to perform the step of determining a pass of a live test, the computer program instructions, when executed by a computer, cause the computer to further perform: selecting an image to be recognized with the best face quality from at least part of images to be recognized collected by a specific camera in the two cameras in a time period from the starting time to the collection time of the specific image pair to be recognized; and carrying out face recognition on the face to be recognized by using the selected image to be recognized.
In one embodiment, before the computer program instructions, when executed by a computer, cause the computer to perform the step of face recognition of the face to be recognized using the selected image to be recognized, the computer program instructions, when executed by a computer, cause the computer to further perform: acquiring identity card information of an object to which the face to be recognized belongs, wherein the identity card information comprises an identity card face; the computer program instructions, when executed by a computer, cause the computer to perform the step of face recognition of the face to be recognized using the selected image to be recognized, including: and comparing the face to be recognized in the selected image to be recognized with the face of the identity card to determine whether the face to be recognized is consistent with the face of the identity card.
In one embodiment, the computer program instructions, when executed by a computer, cause the computer to perform the step of face recognition of the face to be recognized using the selected image to be recognized, including: comparing the face to be recognized in the selected image to known faces in a first database to determine whether the face to be recognized is one of the known faces in the first database.
In one embodiment, the computer program instructions, when executed by a computer, cause the computer to perform the step of selecting an image to be recognized with the best face quality from among at least some of the images to be recognized captured by a particular camera of the two cameras during a period from the start time to the capture time of the particular image pair to be recognized, comprising: scoring each of the at least some of the images to be identified according to one or more of the following parameters: the face brightness, the side light inverse luminosity, the pitch degree, the left and right inclination, the eye opening degree and the mouth opening degree of the face to be recognized in the image to be recognized; and selecting the image to be recognized with the highest score as the image to be recognized with the best face quality.
In one embodiment, the computer program instructions, when executed by a computer, cause the computer to perform the step of determining whether the face to be recognized belongs to a living body in combination with the depth information and the texture information, including: and if the texture information conforms to the human skin texture distribution rule and the depth information conforms to the human face depth distribution rule, determining that the human face to be recognized belongs to the living body, otherwise, determining that the human face to be recognized does not belong to the living body.
In one embodiment, the computer program instructions, when executed by a computer, cause the computer to further perform: and when the image pair to be recognized is obtained, outputting action prompt information to indicate the object to which the face to be recognized belongs to execute the action corresponding to the action prompt information.
in one embodiment, prior to the step of outputting action prompt information performed by the computer, the computer program instructions, when executed by the computer, cause the computer to further perform: randomly acquiring at least one action prompt message from a second database, wherein the second database comprises a plurality of different action prompt messages; the computer program instructions, when executed by a computer, cause the computer to perform the step of outputting action prompt information comprising: and outputting the acquired action prompt information in a text display mode and/or a voice broadcast mode.
According to the method and the device for detecting the human face, the cooperation of users is not needed, so that the cooperation requirement is low, the speed is high, in addition, the method is combined with the depth information and the texture information to carry out the living body detection, the attacks such as the mask attack can be effectively prevented, and the safety is high.
Based on the method and the device for detecting the human face in the embodiment, the invention also provides a remote teller machine system which comprises two cameras, an infrared structure light emitting device and the device for detecting the human face in the embodiment. The two cameras are used for collecting two images to be recognized aiming at the face to be recognized to obtain an image pair to be recognized and sending the image pair to be recognized to the image acquisition module; the infrared structure light emitting device is used for emitting infrared structure light to the face to be recognized so as to form a light spot pattern on the face to be recognized.
In the embodiment of the invention, the system further comprises a display and/or a voice device, wherein the display is used for displaying the images to be recognized collected by the two cameras in real time, receiving action prompt information from the device for detecting the human face and displaying the action prompt information through characters; the voice equipment is used for receiving the action prompt information from the device for detecting the human face and broadcasting the action prompt information through voice; and the action prompt information is used for indicating the object to which the face to be recognized belongs to execute the action corresponding to the action prompt information.
Although the illustrative embodiments have been described herein with reference to the accompanying drawings, it is to be understood that the foregoing illustrative embodiments are merely exemplary and are not intended to limit the scope of the invention thereto. Various changes and modifications may be effected therein by one of ordinary skill in the pertinent art without departing from the scope or spirit of the present invention. All such changes and modifications are intended to be included within the scope of the present invention as set forth in the appended claims.
Those of ordinary skill in the art will appreciate that the various illustrative elements and algorithm steps described in connection with the embodiments disclosed herein may be implemented as electronic hardware or combinations of computer software and electronic hardware. Whether such functionality is implemented as hardware or software depends upon the particular application and design constraints imposed on the implementation. Skilled artisans may implement the described functionality in varying ways for each particular application, but such implementation decisions should not be interpreted as causing a departure from the scope of the present invention.
in the several embodiments provided in the present application, it should be understood that the disclosed apparatus and method may be implemented in other ways. For example, the above-described device embodiments are merely illustrative, and for example, the division of the units is only one logical functional division, and other divisions may be realized in practice, for example, a plurality of units or components may be combined or integrated into another device, or some features may be omitted, or not executed.
In the description provided herein, numerous specific details are set forth. It is understood, however, that embodiments of the invention may be practiced without these specific details. In some instances, well-known methods, structures and techniques have not been shown in detail in order not to obscure an understanding of this description.
Similarly, it should be appreciated that in the description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the invention and aiding in the understanding of one or more of the various inventive aspects. However, the method of the present invention should not be construed to reflect the intent: that the invention as claimed requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
It will be understood by those skilled in the art that all of the features disclosed in this specification (including any accompanying claims, abstract and drawings), and all of the processes or elements of any method or apparatus so disclosed, may be combined in any combination, except combinations where such features are mutually exclusive. Each feature disclosed in this specification (including any accompanying claims, abstract and drawings) may be replaced by alternative features serving the same, equivalent or similar purpose, unless expressly stated otherwise.
Furthermore, those skilled in the art will appreciate that while some embodiments described herein include some features included in other embodiments, rather than other features, combinations of features of different embodiments are meant to be within the scope of the invention and form different embodiments. For example, in the claims, any of the claimed embodiments may be used in any combination.
The various component embodiments of the invention may be implemented in hardware, or in software modules running on one or more processors, or in a combination thereof. It will be appreciated by those skilled in the art that a microprocessor or Digital Signal Processor (DSP) may be used in practice to implement some or all of the functions of some of the modules in an apparatus for detecting a human face according to embodiments of the present invention. The present invention may also be embodied as apparatus programs (e.g., computer programs and computer program products) for performing a portion or all of the methods described herein. Such programs implementing the present invention may be stored on computer-readable media or may be in the form of one or more signals. Such a signal may be downloaded from an internet website or provided on a carrier signal or in any other form.
It should be noted that the above-mentioned embodiments illustrate rather than limit the invention, and that those skilled in the art will be able to design alternative embodiments without departing from the scope of the appended claims. In the claims, any reference signs placed between parentheses shall not be construed as limiting the claim. The word "comprising" does not exclude the presence of elements or steps not listed in a claim. The word "a" or "an" preceding an element does not exclude the presence of a plurality of such elements. The invention may be implemented by means of hardware comprising several distinct elements, and by means of a suitably programmed computer. In the unit claims enumerating several means, several of these means may be embodied by one and the same item of hardware. The usage of the words first, second and third, etcetera do not indicate any ordering. These words may be interpreted as names.
The above description is only for the specific embodiment of the present invention or the description thereof, and the protection scope of the present invention is not limited thereto, and any person skilled in the art can easily conceive of the changes or substitutions within the technical scope of the present invention, and the changes or substitutions should be covered within the protection scope of the present invention. The protection scope of the present invention shall be subject to the protection scope of the claims.

Claims (18)

1. A method for detecting a human face, comprising:
Acquiring an image pair to be recognized, wherein the image pair to be recognized comprises two images to be recognized which are respectively acquired by two cameras aiming at a face to be recognized;
Obtaining the depth information of the face to be recognized according to the image pair to be recognized;
Acquiring a light spot pattern formed by the face to be recognized under the irradiation of the infrared structural light;
Acquiring texture information of the face to be recognized according to the light spot pattern; and
Determining whether the face to be recognized belongs to a living body or not by combining the depth information and the texture information;
Wherein the determining whether the face to be recognized belongs to a living body by combining the depth information and the texture information comprises:
And if the texture information conforms to the human skin texture distribution rule and the depth information conforms to the human face depth distribution rule, determining that the human face to be recognized belongs to the living body, otherwise, determining that the human face to be recognized does not belong to the living body.
2. The method of claim 1, wherein the method further comprises:
if the face to be recognized does not belong to the living body is determined for all the image pairs to be recognized collected in a preset time period after the starting moment, determining that the living body detection fails; and
And if the face to be recognized is determined to belong to a living body for the specific image pair to be recognized acquired in the preset time period after the starting moment, determining that the living body detection is passed.
3. the method of claim 2, wherein after the determining that the liveness detection has passed, the method further comprises:
Selecting an image to be recognized with the best face quality from at least part of images to be recognized collected by a specific camera in the two cameras in a time period from the starting time to the collection time of the specific image pair to be recognized; and
And carrying out face recognition on the face to be recognized by using the selected image to be recognized.
4. The method of claim 3, wherein prior to said face recognizing the face to be recognized using the selected image to be recognized, the method further comprises: acquiring identity card information of an object to which the face to be recognized belongs, wherein the identity card information comprises an identity card face;
The face recognition of the face to be recognized by using the selected image to be recognized comprises: and comparing the face to be recognized in the selected image to be recognized with the face of the identity card to determine whether the face to be recognized is consistent with the face of the identity card.
5. The method of claim 3, wherein the recognizing the face of the person to be recognized using the selected image to be recognized comprises:
Comparing the face to be recognized in the selected image to known faces in a first database to determine whether the face to be recognized is one of the known faces in the first database.
6. the method of claim 3, wherein the selecting the image to be recognized with the best face quality from at least part of the images to be recognized acquired by a specific camera of the two cameras in the period from the starting time to the acquisition time of the specific image pair to be recognized comprises:
Scoring each of the at least some of the images to be identified according to one or more of the following parameters: the face brightness, the side light inverse luminosity, the pitch degree, the left and right inclination, the eye opening degree and the mouth opening degree of the face to be recognized in the image to be recognized; and
And selecting the image to be recognized with the highest score as the image to be recognized with the best face quality.
7. The method of claim 1, wherein the method further comprises: and when the image pair to be recognized is obtained, outputting action prompt information to indicate the object to which the face to be recognized belongs to execute the action corresponding to the action prompt information.
8. The method of claim 7, wherein prior to the outputting action prompt information, the method further comprises:
Randomly acquiring at least one action prompt message from a second database, wherein the second database comprises a plurality of different action prompt messages;
The outputting the action prompt message comprises:
and outputting the acquired action prompt information in a text display mode and/or a voice broadcast mode.
9. An apparatus for detecting a human face, comprising:
the image acquisition module is used for acquiring an image pair to be recognized, wherein the image pair to be recognized comprises two images to be recognized which are respectively acquired by two cameras aiming at a face to be recognized;
The depth information acquisition module is used for acquiring the depth information of the face to be recognized according to the image pair to be recognized;
The light spot pattern acquisition module is used for acquiring a light spot pattern formed by the face to be recognized under the irradiation of the infrared structural light;
The texture information obtaining module is used for obtaining the texture information of the face to be recognized according to the light spot pattern; and
The living body detection module is used for determining whether the face to be recognized belongs to a living body or not by combining the depth information and the texture information;
wherein the in-vivo detection module includes:
The first determining submodule is used for determining that the face to be recognized belongs to a living body if the texture information conforms to a human skin texture distribution rule and the depth information conforms to a face depth distribution rule; and
and the second determining submodule is used for determining that the face to be recognized does not belong to a living body if the texture information does not accord with the human skin texture distribution rule or the depth information does not accord with the face depth distribution rule.
10. The apparatus of claim 9, wherein the apparatus further comprises:
The failure determination module is used for determining that the face to be recognized does not belong to a living body if all the image pairs to be recognized collected in a preset time period after the starting time are determined to be not the living body; and
a pass determination module for determining that the live body detection passes if it is determined that the face to be recognized belongs to a live body for a specific pair of images to be recognized acquired within the preset period after the start time.
11. The apparatus of claim 10, wherein the apparatus further comprises:
the selection module is used for selecting an image to be recognized with the best face quality from at least part of images to be recognized collected by a specific camera in the two cameras in a time period from the starting time to the collection time of the specific image pair to be recognized; and
And the face recognition module is used for carrying out face recognition on the face to be recognized by utilizing the selected image to be recognized.
12. The apparatus of claim 11, wherein the apparatus further comprises: the identity card information acquisition module is used for acquiring identity card information of an object to which the face to be recognized belongs, wherein the identity card information comprises an identity card face;
The face recognition module includes: and the first comparison submodule is used for comparing the face to be recognized in the selected image to be recognized with the face of the identity card so as to determine whether the face to be recognized is consistent with the face of the identity card.
13. The apparatus of claim 11, wherein the face recognition module comprises: and the second comparison sub-module is used for comparing the face to be recognized in the selected image to be recognized with the known faces in the first database so as to determine whether the face to be recognized is one of the known faces in the first database.
14. The apparatus of claim 11, wherein the selection module comprises:
a scoring submodule for scoring each of the at least some of the images to be identified according to one or more of the following parameters: the face brightness, the side light inverse luminosity, the pitch degree, the left and right inclination, the eye opening degree and the mouth opening degree of the face to be recognized in the image to be recognized; and
And the selection submodule is used for selecting the image to be recognized with the highest score as the image to be recognized with the best face quality.
15. The apparatus of claim 9, wherein the apparatus further comprises: and the action prompt module is used for outputting action prompt information when the image acquisition module acquires the image pair to be recognized so as to instruct the object to which the face to be recognized belongs to execute the action corresponding to the action prompt information.
16. The apparatus of claim 15, wherein,
The device further comprises: the prompt information acquisition module is used for randomly acquiring at least one action prompt information from a second database, wherein the second database comprises a plurality of different action prompt information;
the action prompt module comprises: and the prompt information output submodule is used for outputting the acquired action prompt information in a text display mode and/or a voice broadcast mode.
17. A remote teller machine system, wherein the system comprises two cameras, infrared structured light emitting means and means for detecting a human face according to any of claims 9 to 16,
The two cameras are used for collecting two images to be recognized aiming at the face to be recognized, obtaining an image pair to be recognized and sending the image pair to be recognized to the image acquisition module;
the infrared structure light emitting device is used for emitting infrared structure light to the face to be recognized so as to form the light spot pattern on the face to be recognized.
18. The system of claim 17, wherein the system further comprises a display and/or a voice device,
The display is used for displaying images to be recognized collected by the two cameras in real time, receiving action prompt information from the device for detecting the human face and displaying the action prompt information through characters;
The voice equipment is used for receiving the action prompt information from the device for detecting the human face and broadcasting the action prompt information through voice;
And the action prompt information is used for indicating the object to which the face to be recognized belongs to execute the action corresponding to the action prompt information.
CN201610798437.3A 2016-08-31 2016-08-31 Method and device for detecting human face and remote teller machine system Active CN106407914B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201610798437.3A CN106407914B (en) 2016-08-31 2016-08-31 Method and device for detecting human face and remote teller machine system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201610798437.3A CN106407914B (en) 2016-08-31 2016-08-31 Method and device for detecting human face and remote teller machine system

Publications (2)

Publication Number Publication Date
CN106407914A CN106407914A (en) 2017-02-15
CN106407914B true CN106407914B (en) 2019-12-10

Family

ID=58000726

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201610798437.3A Active CN106407914B (en) 2016-08-31 2016-08-31 Method and device for detecting human face and remote teller machine system

Country Status (1)

Country Link
CN (1) CN106407914B (en)

Families Citing this family (38)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10796178B2 (en) 2016-12-15 2020-10-06 Beijing Kuangshi Technology Co., Ltd. Method and device for face liveness detection
CN108629259A (en) * 2017-03-17 2018-10-09 北京旷视科技有限公司 Identity identifying method and device and storage medium
CN112651348B (en) * 2017-03-17 2024-04-05 北京旷视科技有限公司 Identity authentication method and device and storage medium
CN108694357A (en) * 2017-04-10 2018-10-23 北京旷视科技有限公司 Method, apparatus and computer storage media for In vivo detection
CN108734057A (en) * 2017-04-18 2018-11-02 北京旷视科技有限公司 The method, apparatus and computer storage media of In vivo detection
CN108875452A (en) * 2017-05-11 2018-11-23 北京旷视科技有限公司 Face identification method, device, system and computer-readable medium
CN107392137B (en) * 2017-07-18 2020-09-08 艾普柯微电子（上海）有限公司 Face recognition method and device
CN107590430A (en) * 2017-07-26 2018-01-16 百度在线网络技术（北京）有限公司 Biopsy method, device, equipment and storage medium
CN107392874B (en) * 2017-07-31 2021-04-09 Oppo广东移动通信有限公司 Beauty treatment method and device and mobile equipment
CN108875331B (en) * 2017-08-01 2022-08-19 北京旷视科技有限公司 Face unlocking method, device and system and storage medium
CN107609515B (en) * 2017-09-13 2021-04-02 麒麟软件有限公司 Double-verification face comparison system and method based on Feiteng platform
CN107832712A (en) * 2017-11-13 2018-03-23 深圳前海微众银行股份有限公司 Biopsy method, device and computer-readable recording medium
CN107944378A (en) * 2017-11-20 2018-04-20 广东金赋科技股份有限公司 The personal identification method and self-help serving system of a kind of Self-Service
CN108875508B (en) * 2017-11-23 2021-06-29 北京旷视科技有限公司 Living body detection algorithm updating method, device, client, server and system
CN108171113A (en) * 2017-12-01 2018-06-15 国政通科技股份有限公司 A kind of identity authentication method and system
CN108509868B (en) * 2018-03-12 2020-08-04 杭州软库科技有限公司 Face recognition system and method based on light field camera
CN108335394A (en) * 2018-03-16 2018-07-27 东莞市华睿电子科技有限公司 A kind of long-range control method of intelligent door lock
CN108596061A (en) * 2018-04-12 2018-09-28 Oppo广东移动通信有限公司 Face identification method, device and mobile terminal, storage medium
WO2019196683A1 (en) 2018-04-12 2019-10-17 Oppo广东移动通信有限公司 Method and device for image processing, computer-readable storage medium, and electronic device
US11410458B2 (en) 2018-04-12 2022-08-09 Guangdong Oppo Mobile Telecommunications Corp., Ltd. Face identification method and apparatus, mobile terminal and storage medium
CN108875546A (en) * 2018-04-13 2018-11-23 北京旷视科技有限公司 Face auth method, system and storage medium
CN108764052B (en) * 2018-04-28 2020-09-11 Oppo广东移动通信有限公司 Image processing method, image processing device, computer-readable storage medium and electronic equipment
CN108776786A (en) * 2018-06-04 2018-11-09 北京京东金融科技控股有限公司 Method and apparatus for generating user's truth identification model
CN109147116A (en) * 2018-07-25 2019-01-04 深圳市飞瑞斯科技有限公司 The method that smart lock and control smart lock are opened
CN111046703B (en) * 2018-10-12 2023-04-18 杭州海康威视数字技术股份有限公司 Face anti-counterfeiting detection method and device and multi-view camera
CN109635539B (en) * 2018-10-30 2022-10-14 荣耀终端有限公司 Face recognition method and electronic equipment
CN111444744A (en) * 2018-12-29 2020-07-24 北京市商汤科技开发有限公司 Living body detection method, living body detection device, and storage medium
CN111382639A (en) * 2018-12-30 2020-07-07 深圳市光鉴科技有限公司 Living body face detection method and device
CN110222486A (en) * 2019-05-18 2019-09-10 王�锋 User ID authentication method, device, equipment and computer readable storage medium
CN110321793A (en) * 2019-05-23 2019-10-11 平安科技（深圳）有限公司 Check enchashment method, apparatus, equipment and computer readable storage medium
CN110443237B (en) * 2019-08-06 2023-06-30 北京旷视科技有限公司 Certificate identification method, device, electronic equipment and computer readable storage medium
CN110720105A (en) * 2019-09-11 2020-01-21 深圳市汇顶科技股份有限公司 Face anti-counterfeiting detection method, device, chip, electronic equipment and computer readable medium
CN110705451A (en) * 2019-09-27 2020-01-17 支付宝(杭州)信息技术有限公司 Face recognition method, face recognition device, terminal and server
CN111311792A (en) * 2020-02-12 2020-06-19 德施曼机电（中国）有限公司 Intelligent lock verification system and method
CN111611843A (en) * 2020-03-30 2020-09-01 北京爱接力科技发展有限公司 Face detection preprocessing method, device, equipment and storage medium
CN113066237B (en) * 2021-03-26 2022-12-23 中国工商银行股份有限公司 Face living body detection and identification method for automatic teller machine and automatic teller machine
WO2023156319A1 (en) * 2022-02-15 2023-08-24 Trinamix Gmbh Image manipulation for material information determination
WO2023156315A1 (en) * 2022-02-15 2023-08-24 Trinamix Gmbh Face authentication including material data extracted from image

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102622588A (en) * 2012-03-08 2012-08-01 无锡数字奥森科技有限公司 Dual-certification face anti-counterfeit method and device
CN104598878A (en) * 2015-01-07 2015-05-06 深圳市唯特视科技有限公司 Multi-modal face recognition device and method based on multi-layer fusion of gray level and depth information
CN104834901A (en) * 2015-04-17 2015-08-12 北京海鑫科金高科技股份有限公司 Binocular stereo vision-based human face detection method, device and system
CN105022994A (en) * 2015-06-30 2015-11-04 国网山东省电力公司日照供电公司 Identity authentication method of network safety access of power system
CN105138996A (en) * 2015-09-01 2015-12-09 北京上古视觉科技有限公司 Iris identification system with living body detecting function
CN204944450U (en) * 2015-09-18 2016-01-06 上海图漾信息科技有限公司 Depth data measuring system
CN105513221A (en) * 2015-12-30 2016-04-20 四川川大智胜软件股份有限公司 ATM (Automatic Teller Machine) cheat-proof device and system based on three-dimensional human face identification
CN105825186A (en) * 2016-03-16 2016-08-03 四川川大智胜软件股份有限公司 Identity authentication method for identity card and card holder based on 3D face data

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102622588A (en) * 2012-03-08 2012-08-01 无锡数字奥森科技有限公司 Dual-certification face anti-counterfeit method and device
CN104598878A (en) * 2015-01-07 2015-05-06 深圳市唯特视科技有限公司 Multi-modal face recognition device and method based on multi-layer fusion of gray level and depth information
CN104834901A (en) * 2015-04-17 2015-08-12 北京海鑫科金高科技股份有限公司 Binocular stereo vision-based human face detection method, device and system
CN105022994A (en) * 2015-06-30 2015-11-04 国网山东省电力公司日照供电公司 Identity authentication method of network safety access of power system
CN105138996A (en) * 2015-09-01 2015-12-09 北京上古视觉科技有限公司 Iris identification system with living body detecting function
CN204944450U (en) * 2015-09-18 2016-01-06 上海图漾信息科技有限公司 Depth data measuring system
CN105513221A (en) * 2015-12-30 2016-04-20 四川川大智胜软件股份有限公司 ATM (Automatic Teller Machine) cheat-proof device and system based on three-dimensional human face identification
CN105825186A (en) * 2016-03-16 2016-08-03 四川川大智胜软件股份有限公司 Identity authentication method for identity card and card holder based on 3D face data

Also Published As

Publication number Publication date
CN106407914A (en) 2017-02-15

Similar Documents

Publication Publication Date Title
CN106407914B (en) Method and device for detecting human face and remote teller machine system
CN106599772B (en) Living body verification method and device and identity authentication method and device
CN107609383B (en) 3D face identity authentication method and device
KR102036978B1 (en) Liveness detection method and device, and identity authentication method and device
CN106778525B (en) Identity authentication method and device
CN107748869B (en) 3D face identity authentication method and device
CN108573203B (en) Identity authentication method and device and storage medium
CN107633165B (en) 3D face identity authentication method and device
US10339402B2 (en) Method and apparatus for liveness detection
CN109740491B (en) Human eye sight recognition method, device, system and storage medium
CN108875452A (en) Face identification method, device, system and computer-readable medium
CN104834901B (en) A kind of method for detecting human face, apparatus and system based on binocular stereo vision
CN108573202A (en) Identity identifying method, device and system and terminal, server and storage medium
WO2016197298A1 (en) Living body detection method, living body detection system and computer program product
US11663853B2 (en) Iris authentication device, iris authentication method, and recording medium
US9501719B1 (en) System and method for verification of three-dimensional (3D) object
CN108875468B (en) Living body detection method, living body detection system, and storage medium
US11961329B2 (en) Iris authentication device, iris authentication method and recording medium
JP2017010210A (en) Face detection apparatus, face detection system, and face detection method
RU2005100267A (en) METHOD AND SYSTEM OF AUTOMATIC VERIFICATION OF THE PRESENCE OF A LIVING FACE OF A HUMAN IN BIOMETRIC SECURITY SYSTEMS
CN114299569A (en) Safe face authentication method based on eyeball motion
CN113496166A (en) Face living body data acquisition method and device
CN115331315A (en) Living body detection method and living body detection device

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
CB02 Change of applicant information

Address after: 100190 Beijing, Haidian District Academy of Sciences, South Road, No. 2, block A, No. 313

Applicant after: MEGVII INC.

Applicant after: Beijing maigewei Technology Co., Ltd.

Address before: 100190 Beijing, Haidian District Academy of Sciences, South Road, No. 2, block A, No. 313

Applicant before: MEGVII INC.

Applicant before: Beijing aperture Science and Technology Ltd.

CB02 Change of applicant information
GR01 Patent grant
GR01 Patent grant