WO2017173639A1 - 一种基于多模式生物识别信息的个人识别装置和方法 - Google Patents

一种基于多模式生物识别信息的个人识别装置和方法 Download PDF

Info

Publication number
WO2017173639A1
WO2017173639A1 PCT/CN2016/078746 CN2016078746W WO2017173639A1 WO 2017173639 A1 WO2017173639 A1 WO 2017173639A1 CN 2016078746 W CN2016078746 W CN 2016078746W WO 2017173639 A1 WO2017173639 A1 WO 2017173639A1
Authority
WO
WIPO (PCT)
Prior art keywords
image
palm
face
image acquisition
facial
Prior art date
Application number
PCT/CN2016/078746
Other languages
English (en)
French (fr)
Inventor
车全宏
李治农
叶善辉
杨李木
Original Assignee
东莞市中控电子技术有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 东莞市中控电子技术有限公司 filed Critical 东莞市中控电子技术有限公司
Priority to PCT/CN2016/078746 priority Critical patent/WO2017173639A1/zh
Publication of WO2017173639A1 publication Critical patent/WO2017173639A1/zh

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
    • G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
    • G06V40/70—Multimodal biometrics, e.g. combining information from different biometric modalities

Definitions

  • the present application relates to the field of biometrics, and in particular to a multi-mode biometric information-based acquisition device and a personal identification device, method and program based thereon.
  • Biometrics and related products have been widely used for user identification and verification/authentication, such as attendance machines, smart locks for security industry, access control, ladder control, access control, access control products, parking products, video surveillance products, This biometric identification method can be introduced to achieve time management, entrance and exit security control, and flow statistics. Biometrics can also be integrated into large-scale software and projects. These products can be applied to any environment that requires access control and security control in banks, enterprises, prisons, homes, schools, etc., and even establish integrated biometric identity. Proof, establish a database for finding lost and abducting children.
  • biometric identification technology fingerprints, faces, finger veins, palm prints, palm veins, irises, etc. are used as single biometrics for identification, and the corresponding technologies are relatively mature.
  • its pass rate and false positive rate, accuracy rate and pass rate have always been mutually constrained and cannot fully meet market demand.
  • the fingerprint and the face are easy to be faked, the reliability of the authentication is hidden.
  • biometric features such as iris, finger vein and palm vein, which are relatively concealed and difficult to imitate, has emerged, but the biometrics of these three recognition methods are relatively difficult to obtain, and the recognition accuracy is relatively limited. Use the more mature recognition method of the face to make up for the safety level.
  • two or more composite authentication methods have been more and more recognized by users, such as fingerprint and facial composite recognition, fingerprint and finger vein composite recognition, but also have different defects: first, due to the different biometric features Different requirements, the market application of its products is very limited, such as fingerprints on the finger wet and dry surface, clean or not, the requirements of facial recognition for ambient light, refers to the requirements of finger collection for the user to use the finger placement, can not meet City The field is simple to use, high recognition accuracy, high pass rate, and good user experience. Secondly, there is a problem that fingerprint and face composite recognition cannot be anti-counterfeit, because fingerprints and faces are easier to forge. Finally, the fingerprint and finger vein composite identification products also have contact collection and comparison problems, and the user experience is not good.
  • One of the technical problems solved by the present application is to provide an apparatus for acquiring biometric information, including:
  • a detecting portion configured to output a result including the face confirmation information when detecting that the face of the person appears within the detection range
  • a first image acquisition part configured to acquire a facial image that appears within the detection range after receiving the facial confirmation information
  • a second image acquisition part configured to acquire a palm image appearing within the detection range
  • the first image acquisition portion and the second image acquisition portion acquire their respective images at different times.
  • the detecting portion includes a color camera and a face confirming unit, wherein the color camera is configured to monitor an image appearing within an imaging range of the camera, and when the image change is detected, start face confirmation The unit performs analysis processing on the current image; and a face confirmation unit configured to analyze the image monitored by the color camera, and output a result including the face confirmation information when the monitored image is a person's face.
  • the first image acquisition portion includes:
  • a first light emitting unit configured to emit infrared rays to a face of a person detected by the detecting portion
  • a first infrared camera for acquiring an infrared map of a face of the person detected by the detecting portion.
  • the second image acquisition portion includes:
  • a second light emitting unit for emitting infrared rays to a palm of a person
  • a second infrared camera for acquiring infrared mapping of a person's palm.
  • the second image acquisition portion further includes:
  • a controller configured to activate the second lighting unit and the second infrared camera when the detecting portion detects that the palm of the person appears within the detection range of the detecting portion, and the first image acquiring portion is not activated.
  • the first and second light emitting units are LED lights for complementing an object photographed by the camera.
  • the sampling distance of the first image acquisition portion is 2 to 10 times the sampling distance of the second image acquisition portion.
  • the sampling distance of the first image capturing portion is 0.3 to 1.5 meters.
  • the intensity of the first lighting unit is 1.5 to 3 times the intensity of the second lighting unit.
  • the palm image includes one or more of a palm palm print image, a palm bone image, a palm shape image, and a palm blood vessel image.
  • the present invention also provides an apparatus for identifying an individual, comprising:
  • a detecting portion configured to output a result including the face confirmation information when detecting that the face of the person appears within the detection range
  • a first image acquisition part configured to acquire a facial image appearing within the detection range
  • a second image acquisition part configured to acquire a palm image appearing within the detection range
  • the first image acquisition portion and the second image acquisition portion acquire their respective images at different times; and an identification portion for identifying the individual based on the face image and/or the palm image.
  • the identifying portion includes:
  • a facial image processing unit configured to generate a facial feature image based on the facial image
  • a palm image processing unit for generating a palm feature image based on the palm image
  • a face-based matching unit configured to compare the facial feature image with a plurality of candidate facial feature images stored in the first database to generate a first matching result
  • a palm-based matching unit for storing the image of the palm feature and storing it in the second number Performing a comparison according to each of the plurality of candidate palm feature images in the library to generate a second matching result
  • An identity determiner for identifying the individual based on the first matching result and/or the second matching result.
  • the present invention also provides a method implemented on a device for acquiring biometric information of an individual, comprising:
  • a palm image belonging to the individual is acquired when the individual's palm appears in the detection area of the device; wherein the facial image and the palm image are acquired at different times.
  • the acquired facial image and palm image are infrared mapping images.
  • the collecting device provided by the invention can simultaneously collect facial and palm biological information, has the characteristics of high pass rate and high precision of facial recognition, and can realize the anti-counterfeiting ability of vein recognition of the palm image. At the same time, since the image acquisition of the face and palm is achieved through non-contact acquisition and comparison, the process of image acquisition is more clean and convenient, and the user experience is good.
  • FIG. 1 is a schematic perspective structural view of an apparatus for acquiring biometric information according to an embodiment of the present invention
  • FIG. 2 is a schematic diagram of an application of an apparatus for acquiring biometric information according to an embodiment of the present invention
  • FIG. 3(a) is a schematic diagram of a first light emitting unit 111 according to an embodiment of the present invention.
  • FIG. 3(b) is a schematic diagram of a second light emitting unit 121 according to an embodiment of the present invention.
  • FIG. 4 is a schematic diagram of an apparatus for identifying an individual in an embodiment of the present invention.
  • FIG. 5 is a schematic structural view of the identification portion 430 of FIG. 4;
  • FIG. 6 is a schematic diagram of an exemplary system for user identification and authorization in one embodiment of the invention.
  • FIG. 7 is a schematic diagram of an exemplary system for user identification and authorization in another embodiment of the present invention.
  • FIG. 8 depicts a general purpose computer architecture upon which the present teachings may be implemented.
  • the present invention describes a multi-mode biometric information based acquisition device and a personal identification device and method based thereon.
  • the individual's multi-modal biometric information may include, but is not limited to, information related to the facial image of the individual and information related to the palm characteristics.
  • Such user-identified applications include secure access, such as buildings, devices, software applications installed on computing devices, and the like. For example, when an individual attempts to enter a building through a door controlled by a security system (eg, mounted on or near a door), the security system can notify the individual to place the finger on the user identification device.
  • the user identification device can determine if the individual has permission to enter the A known and/or authorized identity of a building.
  • FIG. 1 shows an apparatus for acquiring biometric information in an embodiment of the present invention, comprising: a detecting portion 100, a first image acquiring portion, and a second image acquiring portion, wherein the first image acquiring portion includes a light emitting unit 111 and a first infrared camera 112, the second image capturing portion includes a second light emitting unit 121 and a second infrared camera 122, the first image capturing portion and the second image capturing portion acquiring the same at different times The respective images.
  • the detecting portion 100 is for outputting a result including face confirmation information when it is detected that a person's face appears within the detection range.
  • the detecting portion 100 includes a color camera and a face confirming unit (not shown).
  • the color camera is configured to monitor an image appearing within an imaging range of the camera, and when the image change is detected, send the changed image to a face confirmation unit;
  • the face confirmation unit is configured to perform an image monitored by the color camera The analysis process is performed, and when the monitored image is a person's face, the result including the face confirmation information is output.
  • the purpose of the detecting portion 100 is to filter the interference signal, reduce the system power consumption, and ensure that the first image acquiring unit is activated only when the image to be recognized is a person's face.
  • the face confirmation unit, the first image acquisition portion, and the second image acquisition portion are all in a closed state.
  • the image to be recognized is another interference image, such as other obstructions, or when the palm is detected without detecting the face of the person, each of the above portions remains in the off state.
  • the color camera is in working state at any time, and the image in the detection range is monitored in real time. When the image in the detection range changes, the changed image is captured, and the image is sent to the face confirmation unit, and the face confirmation unit is activated.
  • the image acquired by the color camera is identified, and when it is determined that the acquired image is a person's face, the face confirmation information is output.
  • the first image acquisition part and the second image acquisition part are sequentially activated according to a preset program.
  • the face confirmation unit may be a device having a logic control function, such as a controller or a micro-single-chip device. How to implement the face-recognition unit is a common technical means in the art, and details are not described herein again.
  • the first image acquisition part is configured to acquire the facial image that appears in the detection range after receiving the facial confirmation information, and includes: a first light emitting unit 111, configured to emit infrared rays to the face of the human detected by the detecting part; An infrared camera 112 for acquiring the detecting portion Infrared mapping of the detected person's face.
  • the first image acquisition portion has a storage function capable of storing the acquired image; and the first light-emitting unit is an LED light for emitting infrared rays to an object photographed by the camera.
  • the first light emitting unit 111 After receiving the facial confirmation information outputted by the detecting portion, the first light emitting unit 111 turns on and emits infrared rays, and the emitted infrared rays are reflected by the human face and captured by the first infrared camera 112, and the first infrared camera 112 receives the infrared camera 112 according to the received
  • the infrared image is obtained, and the face image of the person to be recognized is obtained and stored, and the face image is collected. At this point, the facial image of the person to be identified is successfully collected.
  • the second image acquisition part is configured to acquire the palm image appearing within the detection range after receiving the facial confirmation information
  • the second light emitting unit 121 is configured to emit infrared rays to the palm of the person detected by the detecting part
  • the two infrared camera 122 is configured to acquire an infrared map of the palm of the person detected by the detecting portion.
  • the palm image includes one or more of a palm palm print image, a palm bone image, a palm shape image, and a palm blood vessel image.
  • a palm blood vessel image and a palm bone image having an anti-counterfeiting function are selected as objects to be collected.
  • the second image acquisition portion has a storage function capable of storing the acquired image; and the second illumination unit is an LED lamp for emitting infrared rays to an object photographed by the camera.
  • the second lighting unit 121 turns on and emits infrared rays, and the emitted infrared rays are reflected by the palm of the person and captured by the second infrared camera 122, and the second infrared camera 122 receives the infrared camera 122 according to the received
  • the infrared imaging obtains the image of the palm of the person to be recognized and stores it, and completes the palm image acquisition. At this point, the palm image of the individual to be identified is successfully collected.
  • the second image acquisition portion further includes a controller, configured to start when the detecting portion detects that the palm of the person appears within the detection range of the detecting portion, and the first image capturing portion is not activated.
  • a controller configured to start when the detecting portion detects that the palm of the person appears within the detection range of the detecting portion, and the first image capturing portion is not activated.
  • the purpose of the controller is to enable the second image acquisition portion to be activated only when it is detected that the palm of the person is present and the first image acquisition portion, that is, the face image acquisition portion is not working, thereby ensuring that the acquired image is the The palm image of the individual to be identified, rather than other interfering images, and ensuring that the first and second image acquisition portions independently acquire respective images avoid interference with each other during the acquisition process.
  • the first image acquisition part is configured to acquire a facial image of a person
  • the second image acquisition portion is configured to acquire a palm image of a person.
  • the first image lake area portion and the second image acquisition portion have different values in order to obtain a clear and accurate image due to the difference in the height of the human palm and the face and the distance from the distance collecting device. Collection range. As shown in FIG. 2, in practice, when the person to be identified is located in the image collection area of the collection device, the distance L1 of the face from the collection device is naturally greater than the distance L2 of the palm from the collection device, The height of the face is also naturally greater than the height when the palm is lifted, and the image acquisition range of the face and the palm is very different.
  • the sampling distance of the first image acquiring portion is 0.3 to 1.5 meters, and the first image is acquired.
  • the sampling distance of the portion is 2 to 10 times of the sampling distance of the second image capturing portion; correspondingly, the intensity of the first lighting unit is 1.5 to 3 times the intensity of the second lighting unit.
  • the sampling distance of the first image acquisition portion is 2 to 10 times the sampling distance of the second image acquisition portion.
  • the first light emitting unit 111 is four concentrated infrared lamps, as shown in FIG. 3( a ), the infrared light includes a light source 301 and a lens 302 , and the lens is a light transmitting poly
  • the ester material can concentrate the light of the light source to prevent the irradiation range from increasing with the increase of the distance, so that the infrared light emitted by the light source 301 can effectively illuminate the position of the face to be recognized.
  • the number of the concentrating infrared lamps may also be increased or decreased according to actual needs.
  • the number of the concentrating infrared lamps is an even number, for example, two, six, or eight. Ten and so on.
  • the image capturing range of the first infrared camera 112 is equal to or smaller than the light emitting range of the first light emitting unit 111.
  • the image capturing range of the first infrared camera 112 is equal to the first light emitting unit 111.
  • the range of illumination is equal to the first light emitting unit 111.
  • the second light emitting unit 121 is ten infrared light sources, as shown in FIG. 3(b), the infrared light includes a light source 401, and the light source 401 is distributed in a circle shape, so that The range of illumination effectively covers the position of the palm of the person to be identified.
  • the number of the infrared light sources may also be increased or decreased according to actual needs.
  • the number of the infrared light sources is an even number, for example, eight, twelve, sixteen, etc.
  • the image capturing range of the second infrared camera 122 is equal to or smaller than For example, the imaging range of the second infrared camera 122 is equal to the illumination range of the second illumination unit 121.
  • the present invention further provides a device for identifying an individual, comprising: a detecting portion 400, configured to output a face confirmation message when detecting that a face of a person appears within a detection range.
  • a first image acquisition portion 410 for acquiring a facial image appearing within the detection range
  • a second image acquisition portion 420 for acquiring a palm image appearing within the detection range
  • the image acquisition sections acquire their respective images at different times
  • an identification section 430 for identifying individuals based on the facial images and/or the palm images.
  • the means for identifying an individual further comprises a controller 440, configured to control an operating state of the first and second image acquiring units according to a result of the output of the detecting portion.
  • the identification portion includes: a face image processing unit 512 for generating a facial feature image based on the face image; and a palm image processing unit 522 for generating a palm based on the palm image a feature image; and a face-based matching unit 513 configured to compare the facial feature image with a plurality of candidate facial feature images stored in the first database to generate a first matching result; the palm-based matching unit 523, Aligning the palm feature image with each of a plurality of candidate palm feature images stored in a second database to generate a second match result; and an identity determiner 530 for determining based on the first match The result and/or the second matching result identifies the individual.
  • the detecting portion 400 is configured to output a result including the face confirmation information when it is detected that the face of the person appears within the detection range.
  • the detecting portion 400 includes a color camera and a face confirming unit.
  • the color camera is configured to monitor an image appearing within an imaging range of the camera, and when the image change is detected, send the changed image to a face confirmation unit; the face confirmation unit is configured to perform an image monitored by the color camera
  • the analysis process outputs a result including the face confirmation information when the monitored image is a person's face, and sends the result to the controller 440.
  • the controller 440 After receiving the facial confirmation information sent by the detecting unit, the controller 440 firstly goes to the first The image acquisition unit 410 sends an operation signal, and the first image acquisition unit 410 opens the operation signal, acquires the facial image appearing within the detection range, and sends the acquired image to the identification portion 430 for further processing, and simultaneously Controller 440 signals the completion of the acquisition.
  • the first image capturing portion includes a first light emitting unit 111 and a first infrared camera 112. For details, refer to the description of the collecting device, which is not described herein.
  • the first image acquisition unit 511 transmits it to the face image processing unit 512, and the face image processing unit 512 receives the face image from the first image acquisition unit 511 and processes it.
  • the facial image thus generates a facial feature image.
  • the processing of the face image includes at least extracting a feature including the minutiae point from the face image, and generating the face feature image based on the extracted feature.
  • the facial feature image is transmitted to the face image matching unit 513 via the face image processing unit 512.
  • the face image matching unit 513 compares the received face feature image with the face feature image stored in the biometric database. Since there is no other information about the identity of the user, the ordering of the matches can be determined based on the frequency of accesses associated with each identity. For example, if the first candidate in the biometric database is more frequently accessed than the second candidate in the biometric database, then the first candidate is preferentially verified and the degree of matching with the individual to be identified is obtained. After all the candidates in the biometric database are matched, the candidate when the matching degree meets the determination condition is confirmed as the first candidate collection.
  • the controller 440 After receiving the signal of the acquisition completed by the first image acquisition unit 410, the controller 440 sends a shutdown signal to the first image acquisition unit 410 to stop the operation. At the same time, the controller 440 receives the facial confirmation information sent by the detecting device 400, and sends a working signal to the second image acquiring unit 420. The second image acquiring unit 420 opens after receiving the working signal, and acquires the palm image appearing within the detecting range. And the acquired image is sent to the identification portion 430 for further processing, and a signal for completion of the acquisition is sent to the controller 440.
  • the first image capturing portion 410 includes: a first lighting unit and a first infrared camera. For details, refer to the description of the collecting device in the above, and details are not described herein again.
  • the second image acquisition unit 521 acquires the palm image of the individual to be recognized, it transmits it to the palm image processing unit 522, and the palm image processing unit 522 receives the palm image from the second image acquisition unit 521 and processes it.
  • the processing of the palm image includes at least extracting features including minutiae points from the palm image, and generating a palm feature image based on the extracted features.
  • the palm image may be one or more of a palm palm print image, a palm bone image, a palm shape image, and a palm blood vessel image.
  • a palm blood vessel image having an anti-counterfeiting function is selected as an object of collection.
  • the palm image processing unit 522 receives the palm blood vessel image from the second image acquisition unit 521 and processes the palm blood vessel image to generate a characteristic palm blood vessel image.
  • a region in which a blood vessel in a palm blood vessel image appears in the image is partitioned.
  • the geometric features of the palm vein image can be normalized to have a regularized shape, size, and orientation of the image.
  • the gray level of the palm blood vessel image can also be normalized.
  • the blood veins in the regularized palm blood vessel image can be identified.
  • noise can be removed from the palm blood vessel image and the palm blood vessel image can be stored.
  • the palm feature image is transmitted to the palm image matching unit 523 via the palm image processing unit 522.
  • the palm image matching unit 523 compares the received palm feature image with the palm feature image stored in the biometric database. Since there is no other information about the identity of the user, the ordering of the matches can be determined based on the frequency of accesses associated with each identity. For example, if the first candidate in the biometric database is more frequently accessed than the second candidate in the biometric database, then the first candidate is preferentially verified and the degree of matching with the individual to be identified is obtained. After all the candidates in the biometric database are matched, the candidate when the matching degree meets the determination condition is confirmed as the second candidate collection.
  • the identity determiner 530 determines the identity of the person to be identified based on the first and second candidate collections. Specifically, it can be judged by a logical combination of two collections, such as logical AND, logical OR, and the like. It can also be judged according to other fusion algorithms, and will not be described here.
  • the collecting device provided by the invention can simultaneously collect facial and palm biological information, has the characteristics of high pass rate and high precision of facial recognition, and can realize the anti-counterfeiting ability of vein recognition of the palm image. At the same time, since the image acquisition of the face and palm is achieved through non-contact acquisition and comparison, the process of image acquisition is more clean and convenient, and the user experience is good.
  • FIG. 6 is a user identification according to an embodiment of the present invention. And a high level depiction of the authorized exemplary system 600.
  • exemplary system 600 includes a server 630, an identification device 640, one or more authorization controllers 610, a user 650, and a network 620.
  • Network 620 can be a single network or a combination of different networks.
  • network 620 can be a local area network (LAN), a wide area network (WAN), a public network, a private network, a proprietary network, a public switched telephone network (PSTN), the Internet, a wireless network, a virtual network, or any combination thereof.
  • Network 620 may also include various network access points, such as wired or wireless access points, such as base stations or Internet switching points 620-1, ... 620-2, by which authorization controller 610 may be connected to network 620 to obtain via network 620.
  • Authorization information such as wired or wireless access points, such as base stations or Internet switching points 620-1, ... 620-2, by which authorization controller 610 may be connected to network 620 to obtain via network 620.
  • the authorization controller 610 can have different types, such as an authorization controller connected to the door 610-1, the car 610-2, the laptop 610-3, or the mobile device 610-4.
  • User 650 may wish to enter a building, enter a vehicle, or access data in a laptop or mobile device through a door. In each case, the user 650 must obtain an access authorization from the corresponding authorization controller 610.
  • the access authorization may be obtained by a user identification process performed at the identification device 640 that is directly or as shown via the network 620 to the authorization controller 610.
  • the identification device 640 can include portions of the product described in accordance with FIG.
  • the identity recognition device 640 can acquire biometric information about the fingerprint and the finger vessel from the same finger of the user 650. Based on the acquired biometric information, the identity recognition device 640 identifies the user 650 either by itself or by means of the server 630.
  • the identity recognition device 640 identifies the user 650 by communicating with the server 630 via the network 620. This can be applied where the user wishes to enter a building associated with a company with hundreds or thousands of employees and many office buildings. In this case, the user or employee data used to identify and authorize access can be relatively large and frequently changed. Therefore, it is not practical to provide such huge amounts of data to the location of each office building. As such, the user/employee data required for identification and authorization can be stored in the general purpose server 630 and accessible to many of the identification devices 640 associated with different office addresses.
  • the identity recognition device 640 can transmit the image to the server 630 via the network 620.
  • Server 630 can take fingerprint images and finger blood The tube image is compared to the image in the database implemented at server 630. Server 630 can then send the results of the image comparison back to identity device 640 for user identification or directly to authorization controller 610 for user authorization.
  • the exemplary system in this embodiment includes an authorization controller 710, an identification device 770, and a user 750.
  • user 750 wishes to enter the building through a door controlled by authorization controller 710.
  • the identity device 740 in this example is located near the door and can communicate directly with the authorization controller 710 without the need for a network.
  • the identity recognition device 740 can have an inherent ability to identify the user 750. This can be applied in situations where a user wishes to enter a particular building (eg, a private home) associated with a small crowd. In this case, the user or employee data used to identify and authorize access may be relatively small and static, and the user identification process may not require many sources.
  • a database with user information can be implemented locally or provided at the identification device 740. For example, after the identification device 740 is from the facial image and the palm image of the user 750, the identification device 740 can compare the facial image and the palm image with the image in the local database to obtain a matching result for the user identification. Based on the comparison results, the identification device 740 can determine if the user 750 has authorization and send authorization information to the authorization controller 710 for authorizing access or denying access.
  • FIG. 8 depicts a functional block diagram depiction of a general purpose computer architecture on which the present teachings may be implemented and having a computer hardware platform including user interface elements.
  • the computer can be a general purpose computer or a special purpose computer.
  • This computer 800 can be used to implement any of the components of the user identification architecture described herein.
  • various components of the systems depicted in Figures 6 and 7 can all be implemented on one or more computers, such as computer 800, via their hardware, software programs, firmware, or a combination thereof.
  • the computer functions for user identification can be implemented in a distributed manner on a plurality of similar platforms, thereby distributing the process load.
  • Computer 800 for example, includes a COM port 802 that is coupled to and connected to a network that is connected thereto to facilitate data communication.
  • Computer 800 also includes a CPU 804 in the form of one or more processors for executing program instructions.
  • An exemplary computer platform includes internal communication A letter bus 806, having different forms of program storage devices and data storage devices, such as a disk 808, a read only memory (ROM) 810, or a random access memory (RAM) 812 for various types of processing and/or communication to be processed by the computer Data files, as well as possible program instructions to be executed by CPU 804.
  • the computer 800 also includes an I/O component 814 that supports input/output streams between the computer and other components such as the user interface element 816.
  • Computer 800 can also receive programs and data via network communications.
  • a procedural aspect of the technology may be considered a "product” or “manufactured piece” typically in the form of executable code and/or associated data that is carried or implemented on a machine readable medium type.
  • a tangible permanent “storage” type of media includes any or all of the memory or other memory for a computer, processor or similar or its associated modules, such as various semiconductor memories, tape drives, disk drives or the like, which may be in any Provide storage for software programs.
  • All or part of the software may communicate from time to time over a network such as the Internet or various other telecommunications networks. Such communication may, for example, enable software to be loaded from one computer or processor into another.
  • a network such as the Internet or various other telecommunications networks.
  • other types of media that can carry software elements include optical, electrical, and electromagnetic waves, such as those used by wired and optical landline networks, and through physical interfaces between domain devices across various air links. Physical elements that carry such waves, such as limited or wireless links, optical links, or the like, can also be considered as a medium carrying software.
  • the term "computer- or machine-readable” refers to any medium that participates in providing instructions to a processor for execution.
  • a machine-readable medium can take many forms, including but not limited to, a tangible storage medium, a carrier wave medium, or a physical transmission medium.
  • Non-volatile storage media include, for example, optical disks or magnetic disks, such as any storage device in any computer or the like, which can be used to implement a system or any component thereof, as illustrated.
  • Volatile storage media include dynamic storage, such as main memory of such computer platforms.
  • Tangible transmission media include coaxial cables, copper wire and fiber optics, including the circuitry that forms the bus within the computer system.
  • the carrier transmission medium can take the form of an electronic or electromagnetic signal, or acoustic or optical waves, such as those generated in radio frequency (RF) and infrared (IR) data communications.
  • RF radio frequency
  • IR infrared
  • the general form of computer readable media thus includes, for example, floppy disks, soft Disk, hard disk, disk, any other magnetic media, CD-ROM, DVD or DVD-ROM, any other optical media, punched card tape, any other physical storage medium with hole pattern, RAM, PROM and EPROM, FLASH - EPROM, any other memory chip or cartridge, carrier carrying data or instructions, cable or link carrying such carrier, or any other medium from which the computer can read program code and/or data.
  • Many of these forms of computer readable media may be involved in carrying one or more sequences of one or more instructions to a processor for execution.

Landscapes

  • Engineering & Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Collating Specific Patterns (AREA)

Abstract

一种用于获取生物识别信息的装置，包括：探测部分(100)，用于当探测到人的面部出现在探测范围内时，输出包含面部确认信息的结果；第一图像获取部分(111, 112)，用于接收到该面部确认信息后，获取探测范围内出现的面部图像；第二图像获取部分(121, 122)，用于获取探测范围内出现的手掌图像；其中，该第一图像获取部分(111, 112)和第二图像获取部分(121, 122)在不同的时间获取其各自的图像。该装置能够同时采集面部和手掌生物信息，不但具有面部识别具有的高通过率以及高精确度的特点，同时能够实现手掌图像的静脉识别防伪能力。同时，由于面部、手掌图像采集均是通过非接触实现采集与比对，图像获取的过程更加清洁方便，用户体验好。

Description

一种基于多模式生物识别信息的个人识别装置和方法 技术领域
本申请涉及生物识别领域，特别地，涉及一种基于多模式生物识别信息的采集装置以及基于该装置的个人识别装置、方法和程序。
背景技术
生物识别技术及相关产品已经广泛地用于用户识别和验证/鉴权，例如考勤机，安防行业的智能锁、门禁机、梯控，出入口控制的通道产品、停车场产品、视频监控产品，都可以引入这种生物特征身份识别方式，达到时间管理、出入口安全控制、人流统计等目的。生物识别技术还可以集成应用于大型软件、项目，具体这些产品可以应用于银行、企事业单位、监狱、家庭、学校等等任何需要出入口控制、安全控制的环境，甚至可以建立集成生物特征的身份证，建立数据库，用于寻找走失、拐卖儿童。
传统的生物识别技术中，指纹、面部、指静脉、掌纹、掌静脉、虹膜等作为单一生物特征用于身份识别，相应技术已经较为成熟。但是其通过率与误判率、准确率与通过率一直相互制约，不能完全满足市场需求。此外，由于指纹、面部易于仿制造假，使身份验证的可靠性存在隐患。例如，使用人造的指纹膜、指纹硅胶膜以假冒真通过验证、或者直接使用照片做面部识别等。因此，虹膜、指静脉、掌静脉这些生物特征比较隐蔽、难以仿制的生物识别特征的应用应运而生，但是这3种识别方式的生物特征也相对难以获取，且识别准确率也相对有限，需要用面部这种比较成熟的识别方式予以弥补，提高安全级别。
目前，两个及以上的复合认证方式已经越来越得到用户的认可，如指纹与面部复合识别、指纹与指静脉复合识别，但也都存在不同缺陷：首先，因其不同生物识别特征的取像要求不同，导致其产品的市场应用非常有限，如指纹对手指指纹表面干湿、干净与否的要求，面部识别对环境光的要求，指静脉采集对用户使用时手指放置的要求，不能满足市 场上使用简单、识别准确率高、通过率高、用户体验好的要求。其次，指纹与面部复合识别存在不能防伪的问题，因为指纹、面部都较容易伪造。最后，指纹与指静脉复合识别产品，还具有接触式采集与比对的问题，用户体验不好。
因此，亟需提出一种新的基于多模式生物识别信息的采集装置以及基于该装置的个人识别装置与方法来解决上述问题。
发明内容
本申请解决的技术问题之一是提供一种用于获取生物识别信息的装置，包括：
探测部分，用于当探测到人的面部出现在探测范围内时，输出包含面部确认信息的结果；
第一图像获取部分，用于接收到所述面部确认信息后，获取探测范围内出现的面部图像；
第二图像获取部分，用于获取探测范围内出现的手掌图像；其中，
所述第一图像获取部分和第二图像获取部分在不同的时间获取其各自的图像。
根据本发明的其中一个方面，所述探测部分包括彩色摄像头和面部确认单元，其中，所述彩色摄像头用于对摄像头的摄像范围内出现的图像进行监测，当监测到图像变化时，启动面部确认单元对当前图像进行分析处理；以及面部确认单元，用于对彩色摄像头监测到的图像进行分析处理，并在监测到的图像为人的面部时，输出包含面部确认信息的结果。
根据本发明的其中一个方面，所述第一图像获取部分包括：
第一发光单元，用于向所述探测部分探测到的人的面部发射红外线；
第一红外摄像头，用于获取所述探测部分探测到的人的面部的红外测绘图。
根据本发明的其中一个方面，所述第二图像获取部分包括：
第二发光单元，用于向人的手掌发射红外线；
第二红外摄像头，用于获取人的手掌的红外测绘图。
根据本发明的其中一个方面，所述第二图像获取部分还包括：
控制器，用于当所述探测部分探测到人的手掌出现在探测部分的探测范围内，且第一图像获取部分没有启动时，启动第二发光单元以及第二红外摄像头。
根据本发明的其中一个方面，所述第一、第二发光单元为LED灯，用于对摄像头拍摄的对象进行补光。
根据本发明的其中一个方面，所述第一图像获取部分的取样距离为所述第二图像获取部分的取样距离的2～10倍。
根据本发明的其中一个方面，所述第一图像获取部分的取样距离为0.3～1.5米。
根据本发明的其中一个方面，所述第一发光单元的强度为第二发光单元强度的1.5～3倍。
根据本发明的其中一个方面，所述手掌图像包括手掌掌纹图像、手掌骨骼图像、手掌形状图像以及手掌血管图像中的一种或几种。
相应的，本发明还提供了一种用于识别个人的装置，包括：
探测部分，用于当探测到人的面部出现在探测范围内时，输出包含面部确认信息的结果；
第一图像获取部分，用于获取探测范围内出现的面部图像；
第二图像获取部分，用于获取探测范围内出现的手掌图像；其中，
所述第一图像获取部分和第二图像获取部分在不同的时间获取其各自的图像；以及识别部分，用于基于面部图像和/或手掌图像识别个人。
根据本发明的其中一个方面，其中，所述识别部分包括：
面部图像处理单元，用于基于面部图像生成面部特征图像；
手掌图像处理单元，用于基于手掌图像生成手掌特征图像；以及
基于面部的匹配单元，用于对所述面部特征图像和存储在第一数据库中的多个候选面部特征图像进行比对从而生成第一匹配结果；
基于手掌的匹配单元，用于对所述手掌特征图像和存储在第二数 据库中的多个候选手掌特征图像中的每一个进行比对从而生成第二匹配结果；以及
身份确定器，用于基于所述第一匹配结果和/或第二匹配结果识别该个人。
相应的，本发明还提供了一种实施在用于获取个人的生物识别信息的装置上的方法，包括：
当个人的面部出现在设备的探测区域内时对所述面部的存在进行感测；
获取感测到的所述人的面部图像；以及
当个人的手掌出现在设备的探测区域内时获取属于该个人的手掌图像；其中，所述面部图像和手掌图像在不同的时间获取。
根据本发明的其中一个方面，获取的所述面部图像和手掌图像为红外测绘图像。
本发明提供的采集装置能够同时采集面部和手掌生物信息，不但具有面部识别具有的高通过率以及高精确度的特点，同时能够实现手掌图像的静脉识别防伪能力。同时，由于面部、手掌图像采集均是通过非接触实现采集与比对，图像获取的过程更加清洁方便，用户体验好。
本领域普通技术人员将了解，虽然下面的详细说明将参考图示实施例、附图进行，但本申请并不仅限于这些实施例。而是，本申请的范围是广泛的，且意在仅通过后附的权利要求限定本申请的范围。
附图说明
通过阅读参照以下附图所作的对非限制性实施例所作的详细描述，本申请的其它特征、目的和优点将会变得更明显：
图1为本发明一个实施例中的获取生物识别信息的装置的立体结构示意图；
图2为本发明一个实施例中的获取生物识别信息的装置的一个应用示意图；
图3(a)为本发明一个实施例中的第一发光单元111的一个示意图；
图3(b)为本发明一个实施例中的第二发光单元121的一个示意图；
图4为本发明一个实施例中的用于识别个人的装置的示意图；
图5为图4中识别部分430的结构示意图；
图6为本发明一个实施例中的用于用户识别和授权的示例性系统的示意图；
图7为本发明另一个实施例中的用于用户识别和授权的示例性系统的示意图；
图8描绘了其上可以实施本教导的通用计算机架构。
附图中相同或相似的附图标记代表相同或相似的部件。
具体实施方式
为使本发明的目的、技术方案和优点更加清楚，下面将结合附图对本发明的实施例作详细描述。
下面详细描述本发明的实施例，所述实施例的示例在附图中示出，其中自始至终相同或类似的标号表示相同或类似的元件或具有相同或类似功能的元件。下面通过参考附图描述的实施例是示例性的，仅用于解释本发明，而不能解释为对本发明的限制。
在下面详细的描述中，作为示例列举出了多个特定的细节从而提供对于相关实施例的全面理解。然而，对于本领域的技术人员来说，可以不限于这些细节或者连同附加特征来实现本发明。在其他的例子中，在相对高的层面上无有细节地对公知的方法、进程、系统、组件和/或电路进行描述，从而避免对本发明造成不必要的模糊化。
本发明描述了基于多模式生物识别信息的采集装置以及基于该装置的个人识别装置与方法。个人的多模式生物识别信息可以包括但不限于与个人的面部图像相关的信息以及与手掌特征相关的信息。这种用户识别的应用包括安全进入，例如建筑物、设备、安装在计算设备上的软件应用等。例如，当个人试图通过由安全系统(例如安装在门上或者门的附近)控制的门进入建筑物时，安全系统可以通知个人将指头放置在用户识别设备上。用户识别设备可以确定该个人是否具有被允许进入该 建筑物的已知并且/或授权的身份。
图1示出了本发明一个实施例中的用于获取生物识别信息的装置，包括：探测部分100、第一图像获取部分以及第二图像获取部分，其中，所述第一图像获取部分包括第一发光单元111和第一红外摄像头112，所述第二图像获取部分包括第二发光单元121和第二红外摄像头122，所述第一图像获取部分和第二图像获取部分在不同的时间获取其各自的图像。
探测部分100用于当探测到人的面部出现在探测范围内时，输出包含面部确认信息的结果。具体的，探测部分100包括彩色摄像头和面部确认单元(图中未示出)。所述彩色摄像头用于对摄像头的摄像范围内出现的图像进行监测，当监测到图像变化时，将变化的图像发送给面部确认单元；所述面部确认单元用于对彩色摄像头监测到的图像进行分析处理，并在监测到的图像为人的面部时，输出包含面部确认信息的结果。
探测部分100的目的是过滤干扰信号，降低系统功耗，确保只有当待识别的图像为人的面部时才启动第一图像获取单元。在实际使用中，所述面部确认单元、第一图像获取部分以及第二图像获取部分均处于关闭状态。当待识别图像为其他干扰图像，如其他遮挡物，或者，在没有探测到人的面部的情况下检测到手掌时，上述各部分均保持关闭状态。彩色摄像头则随时处于工作状态，对探测范围内的图像进行实时监控，当探测范围内的图像发生变化时，捕捉变化后的图像，并将该图像发送给面部确认单元，此时面部确认单元启动，对彩色摄像头获取的图像进行识别，当判断出获取的图像是人的面部后，输出面部确认信息。第一图像获取部分以及第二图像获取部分接收到该确认信息后，按照预设程序先后启动。所述面部确认单元可以是控制器、微型单片机等具有逻辑控制功能的器件，如何实现面部确认单元是本领域的常用技术手段，在此不再赘述。
第一图像获取部分用于接收到所述面部确认信息后，获取探测范围内出现的面部图像，包括：第一发光单元111，用于向所述探测部分探测到的人的面部发射红外线；第一红外摄像头112，用于获取所述探测部 分探测到的人的面部的红外测绘图。优选的，所述第一图像获取部分具有存储功能，能够存储获取的图像；以及，所述第一发光单元为LED灯，用于对摄像头拍摄的对象发射红外线。接收到探测部分输出的面部确认信息后，所述第一发光单元111开启并发射红外线，发出的红外线经人的面部反射后被第一红外摄像头112捕捉，所述第一红外摄像头112根据接收到的红外线成像，得到待识别的人的面部图像并存储，完成面部图像采集。至此，待识别个人的面部图像采集成功。
第二图像获取部分用于接收到所述面部确认信息后，获取探测范围内出现的手掌图像，包括：第二发光单元121，用于向所述探测部分探测到的人的手掌发射红外线；第二红外摄像头122，用于获取所述探测部分探测到的人的手掌的红外测绘图。其中，所述手掌图像包括手掌掌纹图像、手掌骨骼图像、手掌形状图像以及手掌血管图像中的一种或几种。优选的，在本实施例中，选取具有防伪功能的手掌血管图像和手掌骨骼图像作为采集的对象。优选的，所述第二图像获取部分具有存储功能，能够存储获取的图像；以及，所述第二发光单元为LED灯，用于对摄像头拍摄的对象发射红外线。接收到探测部分输出的手掌确认信息后，所述第二发光单元121开启并发射红外线，发出的红外线经人的手掌反射后被第二红外摄像头122捕捉，所述第二红外摄像头122根据接收到的红外线成像，得到待识别的人的手掌图像并存储，完成手掌图像采集。至此，待识别个人的手掌图像采集成功。
在其他实施例中，所述第二图像获取部分还包括控制器，用于当所述探测部分探测到人的手掌出现在探测部分的探测范围内，且第一图像获取部分没有启动时，启动第二发光单元以及第二红外摄像头。所述控制器的目的在于，使所述第二图像获取部分仅在探测到人的手掌存在且第一图像获取部分，即面部图像获取部分未工作时启动，从而确保其获取的图像为所述待识别个人的手掌图像，而不是其他干扰图像，以及确保所述第一和第二图像获取部分独立采集各自的图像，避免采集的过程中相互干扰。
在本实施例中，所述第一图像获取部分用于获取人的面部图像， 所述第二图像获取部分用于获取人的手掌图像。在实际采集过程中，由于人的手掌和面部的采集高度以及距离采集装置的距离存在差异，为了能够获得清晰准确的图像，所述第一图像湖区部分和所述第二图像获取部分具有不同的采集范围。如图2所示，在实际中，当待识别个人位于所述采集装置的图像采集区域内时，其面部距离所述采集设备的距离L1自然的大于手掌距离所述采集设备的距离L2，其面部的高度也自然的大于手掌距举起时的高度，面部和手掌的图像获取范围差别很大，因此，需要通过第一图像获取部分和第二图像获取部分分别获取面部和手掌的图像。由于人的面部距离所述采集设备的距离L1为手掌距离所述采集设备的距离L2的2～5倍，所述第一图像获取部分的取样距离为0.3～1.5米，所述第一图像获取部分的取样距离为所述第二图像获取部分的取样距离的2～10倍；相应的，所述第一发光单元的强度为第二发光单元强度的1.5～3倍。所述第一图像获取部分的取样距离为所述第二图像获取部分的取样距离的2～10倍。
在本发明的一个实施例中，所述第一发光单元111为四个聚光红外灯，如图3(a)所示，该红外灯包括光源301和透镜302，所述透镜为透光聚酯材料，能够汇聚光源的光线，避免其照射范围随着距离的增加而增加，使光源301发出的红外线能够有效的照射到待识别面部所在的位置。在其他实施例中，所述聚光红外灯的数量也可以根据实际需要增加或减少，优选的，所述聚光红外灯的数目为偶数，例如，可以为两个、六个、八个、十个等。相应的，所述第一红外摄像头112的取像范围等于或小于所述第一发光单元111的发光范围，优选的，所述第一红外摄像头112的取像范围等于所述第一发光单元111的发光范围。
在本发明的一个实施例中，所述第二发光单元121为十个红外灯光源，如图3(b)所示，该红外灯包括光源401，所述光源401呈圆圈状分布，使其发光范围有效地覆盖了待识别个人的手掌覆盖的位置。在其他实施例中，所述红外灯光源的数量也可以根据实际需要增加或减少，优选的，所述红外灯光源的数目为偶数，例如，可以为八个、十二个、十六个等。相应的，所述第二红外摄像头122的取像范围等于或小于所 述第二发光单元121的发光范围，优选的，所述第二红外摄像头122的取像范围等于所述第二发光单元121的发光范围。
相应的，如图4所示，本发明还提供了一种用于识别个人的装置，包括：探测部分400，用于当探测到人的面部出现在探测范围内时，输出包含面部确认信息的结果；第一图像获取部分410，用于获取探测范围内出现的面部图像；第二图像获取部分420，用于获取探测范围内出现的手掌图像；其中，所述第一图像获取部分和第二图像获取部分在不同的时间获取其各自的图像；以及识别部分430，用于基于面部图像和/或手掌图像识别个人。优选的，所述用于识别个人的装置还包括控制器440，用于根据探测部分输出的结果控制第一、第二图像获取单元的工作状态。
在本发明的一个实施例中，如图5所示，所述识别部分包括：面部图像处理单元512，用于基于面部图像生成面部特征图像；手掌图像处理单元522，用于基于手掌图像生成手掌特征图像；以及基于面部的匹配单元513，用于对所述面部特征图像和存储在第一数据库中的多个候选面部特征图像进行比对从而生成第一匹配结果；基于手掌的匹配单元523，用于对所述手掌特征图像和存储在第二数据库中的多个候选手掌特征图像中的每一个进行比对从而生成第二匹配结果；以及身份确定器530，用于基于所述第一匹配结果和/或第二匹配结果识别该个人。
具体的，参考图4和图5对所述用于识别个人的装置识别和识别个人的方法进行详细叙述。
当个人的面部出现在设备的探测区域内时，首先，由探测装置400对所述面部的存在进行感测。所述探测部分400用于当探测到人的面部出现在探测范围内时，输出包含面部确认信息的结果。具体的，探测部分400包括彩色摄像头和面部确认单元。所述彩色摄像头用于对摄像头的摄像范围内出现的图像进行监测，当监测到图像变化时，将变化的图像发送给面部确认单元；所述面部确认单元用于对彩色摄像头监测到的图像进行分析处理，在监测到的图像为人的面部时，输出包含面部确认信息的结果，并将该结果发给控制器440。
控制器440收到探测单元发出的面部确认信息后，首先将向第一 图像获取单元410发出工作信号，所述第一图像获取单元410接收到工作信号后打开，获取探测范围内出现的面部图像，并将获取到的图像发送给识别部分430进行下一步处理，同时向控制器440发出采集完成的信号。所述第一图像获取部分包括：第一发光单元111和第一红外摄像头112，具体的参见上文中关于采集装置的描述，在此不再赘述。
如图5所示，第一图像获取单元511获取到待识别个人的面部图像后，将其发送给面部图像处理单元512，面部图像处理单元512从第一图像获取单元511接收到面部图像并且处理面部图像从而生成面部特征图像。对于面部图像的处理至少包括从面部图像中提取包括细节点的特征，并且基于所提取的特征生成面部特征图像。
所述面部特征图像经由面部图像处理单元512发送给面部图像匹配单元513。面部图像匹配单元513将接收到的面部特征图像与存储在生物识别数据库中的面部特征图像进行比对。由于没有其他关于用户身份的信息，比对的排序可以基于与每个身份相关联的访问的频率而确定。例如，如果在生物识别数据库中的第一候选较之在生物识别数据库中的第二候选的访问频率更加频繁，则优先对第一候选进行验证，并得到与待识别个人的匹配度。对生物识别数据库中的所有候选匹配完之后，将匹配度符合判定条件时的候选确认为第一候选合集。
控制器440收到第一图像获取单元410发出的所述采集完成的信号后，向其发出关闭信号，使所述第一图像获取单元410停止工作。同时，控制器440接收探测装置400发出的面部确认信息，并向第二图像获取单元420发出工作信号，所述第二图像获取单元420接收到工作信号后打开，获取探测范围内出现的手掌图像，并将获取到的图像发送给识别部分430进行下一步处理，同时向控制器440发出采集完成的信号。所述第一图像获取部分410包括：第一发光单元和第一红外摄像头，具体的参见上文中关于采集装置的描述，在此不再赘述。
如图5所示，第二图像获取单元521获取到待识别个人的手掌图像后，将其发送给手掌图像处理单元522，手掌图像处理单元522从第二图像获取单元521接收到手掌图像并且处理手掌图像从而生成手掌特征 图像。对于手掌图像的处理至少包括从手掌图像中提取包括细节点的特征，并且基于所提取的特征生成手掌特征图像。其中，所述手掌图像可以是手掌掌纹图像、手掌骨骼图像、手掌形状图像以及手掌血管图像中的一种或几种。优选的，在本实施例中，选取具有防伪功能的手掌血管图像作为采集的对象。具体的，手掌图像处理单元522从第二图像获取单元521接收手掌血管图像并且处理手掌血管图像从而生成特征手掌血管图像。将手掌血管图像中的血管在该处出现在图像中的区域进行分区。进一步，手掌血管图像的几何特征可以被规整化从而具有规整化的形状、尺寸以及图像的方向。手掌血管图像的灰度水平同样可以被规整化。在规整化的手掌血管图像中的血液脉络可以被识别。此外，可以从手掌血管图像中去除噪声并且将手掌血管图像进行存储。
所述手掌特征图像经由手掌图像处理单元522发送给手掌图像匹配单元523。手掌图像匹配单元523将接收到的手掌特征图像与存储在生物识别数据库中的手掌特征图像进行比对。由于没有其他关于用户身份的信息，比对的排序可以基于与每个身份相关联的访问的频率而确定。例如，如果在生物识别数据库中的第一候选较之在生物识别数据库中的第二候选的访问频率更加频繁，则优先对第一候选进行验证，并得到与待识别个人的匹配度。对生物识别数据库中的所有候选匹配完之后，将匹配度符合判定条件时的候选确认为第二候选合集。
最后，由身份确定器530根据第一和第二候选合集确定待识别个人的身份。具体的，可以由两个合集的逻辑组合进行判断，如逻辑与、逻辑或等。也可根据其他的融合算法进行判断，在此不再赘述。
本发明提供的采集装置能够同时采集面部和手掌生物信息，不但具有面部识别具有的高通过率以及高精确度的特点，同时能够实现手掌图像的静脉识别防伪能力。同时，由于面部、手掌图像采集均是通过非接触实现采集与比对，图像获取的过程更加清洁方便，用户体验好。
需要说明的是，本发明中的生物信息采集装置以及基于该装置的个人识别装置与方法可以用于用户的识别与授权，参见图6，图6为根据本发明的实施例的用于用户识别和授权的示例性系统600的高层面描绘。 在图6中，示例性系统600包括服务器630、身份识别设备640、一个或多个授权控制器610、用户650以及网络620。网络620可以是单一网络或者不同网络的组合。例如，网络620可以是局域网(LAN)、广域网(WAN)、公共网络、私有网络、专有网络、公共电话交换网络(PSTN)、因特网、无线网络、虚拟网络或其任何组合。网络620还可能包括各种网络访问点，例如，诸如基站或者因特网交换点620-1，…620-2的有线或者无线访问点，通过其授权控制器610可以连接到网络620从而经由网络620获得授权信息。
授权控制器610可以具有不同的类型，例如连接到门610-1、车610-2、膝上计算机610-3或者移动设备610-4的授权控制器。用户650可能希望通过门进入建筑物、进入车辆或者访问在便携电脑或者移动设备中的数据。在每种情况下，用户650必须从相对应的授权控制器610获得访问授权。访问授权可以通过在直接或者如所示出地经由网络620连接到授权控制器610的身份识别设备640处执行的用户识别过程来获得。
身份识别设备640可以包括根据图1描述的产品的部分。身份识别设备640可以从用户650的相同手指获取关于指纹和指头血管的生物识别信息。基于所获取的生物识别信息，身份识别设备640或者通过其自身或者借助于服务器630对用户650进行识别。
在一个实施例中，身份识别设备640通过经由网络620与服务器630进行通信来识别用户650。这可以应用在其中用户希望进入与具有上百或上千雇员以及许多办公室建筑的公司相关联的建筑物的情况下。在这种情况下，用来识别并且授权访问的用户或者雇员数据可以相对地大并且频繁地改变。因此，将如此巨大的数据提供到每个办公室建筑物的位置是不太实际的。如此，进行身份识别和授权所需要的用户/雇员数据可以存储在通用服务器630中并且对于许多与不同办公地址相关联的身份识别设备640来说是可以访问的。例如，在身份识别设备640从用户650捕获并且生成指纹图像和指头血管图像后，身份识别设备640可以经由网络620发送图像到服务器630。服务器630可以将指纹图像和指头血 管图像与在服务器630处实施的数据库中的图像进行比对。服务器630接着可以将图像比对的结果发送返回到身份识别设备640用于用户识别或者直接发送到授权控制器610用于用户授权。
图7为根据本发明的实施例的用于用户识别和授权的另一个示例性系统的高层面描绘。在这个实施例中的示例性系统包括授权控制器710、身份识别设备770以及用户750。在这个例子中，用户750希望通过由授权控制器710控制的门进入建筑物。在这个例子中的身份识别设备740位于靠近门处并且可以无需网络直接与授权控制器710进行通信。
在这个实施例中，身份识别设备740可以具有固有的识别用户750的能力。这可以应用在其中用户希望进入与小人群相关联的特定建筑物(例如，私有住宅)的情况中。在这种情况下，用于识别和授权访问的用户或者雇员数据可能相对小且为静态，并且用户识别过程可能不需要很多来源。这样，具有用户信息的数据库可以本地地实施或提供在身份识别设备740处。例如，在身份识别设备740从用户750的面部图像和手掌图像后，身份识别设备740可以将面部图像和手掌图像与在本地数据库中的图像进行比对从而获得用于用户识别的匹配结果。基于比对结果，身份识别设备740可以确定用户750是否具有授权，并且将授权信息发送到授权控制器710用于授权访问或者拒绝访问。
图8描绘了其上可以实施本教导的通用计算机架构并且具有包括用户接口元素的计算机硬件平台的功能性框图描述。计算机可以是通用目的的计算机或者专用目的计算机。这个计算机800可以用于实施这里所描述的用户识别架构的任何组件。例如图6和图7所描绘的系统的不同组件全部可以经由其硬件、软件程序、固件或其组合而实施在例如计算机800的一个或多个计算机上。虽然为了方便仅仅示出了一个这种计算机，但是关于用户识别的计算机功能可以以分布的方式实施在多个相似的平台上，从而分布过程负载。
计算机800，例如包括连接到并且连接自连接到此从而有助于数据通信的网络的COM端口802。计算机800还包括CPU804，其形式为用于执行程序指令的一个或多个处理器。示例性的计算机平台包括内部通 信总线806、具有不同形式的程序贮存设备和数据贮存设备，例如碟808、只读存储器(ROM)810、或者随机存储存储器(RAM)812，用于将被计算机处理并且/或者通信的各种数据文件，以及将被CPU804执行的可能的程序指令。计算机800还包括I/O组件814，支持在计算机和其中诸如用户接口元素816的其他组件之间的输入/输出流。计算机800还可以经由网络通信接收程序和数据。
因此，如上面所勾勒出的用户识别方法的各个方面可以在程序中实施。技术的程序方面可以被认为是典型地形式为被承载或者实施在机器可读介质类型上的可执行代码和/或相关联数据的“产品”或“制造件”。有形的永久“贮存”类型介质包括任何或者所有的存储器或其他用于计算机、处理器或类似的存储器或其相关联模块，诸如各种半导体存储器、带驱动、盘驱动或类似，其可以在任何时候提供用于软件程序的贮存。
软件的所有或者部分可以不时地通过诸如因特网或各种其他电信网络的网络进行通信。这种通信例如可以实现软件从一个计算机或处理器加载进入另一个中。由此，可以承载软件元素的其他类型的介质包括光学、电气、以及电磁波，例如通过有线和光学陆地线网络以及通过各种空中链路而跨域本地设备之间的物理接口所使用的。承载这种波的物理元素，例如有限或无线链路、光学链路或者类似同样可以被视为承载软件的介质。正如在这里所使用的，除非限制于有形的“贮存”介质，例如计算机或机器“可读”的术语指的是任何参与了提供指令到处理器用于执行的介质。
因此，机器可读介质可以采用许多形式，包括但不限于有形贮存介质、载波介质或物理传输介质。非易失性贮存介质例如包括诸如在任何计算机或类似中的任何贮存设备的光盘或磁盘，其可以用于实施系统或其任何组件，如图所示出。易失性贮存介质包括动态存储器，例如这种计算机平台的主存储器。有形传输介质包括同轴线缆、铜线和光纤，包括形成计算机系统内的总线的线路。载波传输介质可以采用电子或电磁信号的形式，或者声波或光波，例如这些在射频(RF)和红外(IR)数据通信中生成的。计算机可读介质的通用形式因此包括例如软盘、柔 性盘、硬盘、磁盘、任何其他磁性介质、CD-ROM、DVD或DVD-ROM、任何其他光学介质、打孔卡片纸带、任何其他具有孔图案的物理贮存介质、RAM、PROM和EPROM、FLASH-EPROM、任何其他存储器芯片或卡盘、传送数据或指令的载波、传送这种载波的线缆或链路、或者计算机可以从其读取程序代码和/或数据的任何其他介质。许多这些形式的计算机可读介质可以涉及运载一个或多个指令的一个或多个序列到处理器用于执行。
对于本领域技术人员而言，显然本申请不限于上述示范性实施例的细节，而且在不背离本申请的精神或基本特征的情况下，能够以其他的具体形式实现本申请。因此，无论从哪一点来看，均应将实施例看作是示范性的，而且是非限制性的，本申请的范围由所附权利要求而不是上述说明限定，因此旨在将落在权利要求的等同要件的含义和范围内的所有变化涵括在本申请内。不应将权利要求中的任何附图标记视为限制所涉及的权利要求。此外，显然“包括”一词不排除其他单元或步骤，单数不排除复数。系统权利要求中陈述的多个单元或装置也可以由一个单元或装置通过软件或者硬件来实现。第一，第二等词语用来表示名称，而并不表示任何特定的顺序。

Claims (14)

  1. 一种用于获取生物识别信息的装置，包括：
    探测部分，用于当探测到人的面部出现在探测范围内时，输出包含面部确认信息的结果；
    第一图像获取部分，用于接收到所述面部确认信息后，获取探测范围内出现的面部图像；
    第二图像获取部分，用于获取探测范围内出现的手掌图像；其中，
    所述第一图像获取部分和第二图像获取部分在不同的时间获取其各自的图像。
  2. 根据权利要求1的装置，其特征在于，所述探测部分包括彩色摄像头和面部确认单元，其中，
    所述彩色摄像头用于对摄像头的摄像范围内出现的图像进行监测，当监测到图像变化时，启动面部确认单元对当前图像进行分析处理；
    面部确认单元，用于对彩色摄像头监测到的图像进行分析处理，并在监测到的图像为人的面部时，输出包含面部确认信息的结果。
  3. 根据权利要求1的装置，其特征在于，所述第一图像获取部分包括：
    第一发光单元，用于向所述探测部分探测到的人的面部发射红外线；
    第一红外摄像头，用于获取所述探测部分探测到的人的面部的红外测绘图。
  4. 根据权利要求1的装置，其特征在于，所述第二图像获取部分包括：
    第二发光单元，用于向人的手掌发射红外线；
    第二红外摄像头，用于获取人的手掌的红外测绘图。
  5. 根据权利要求1的装置，其特征在于，所述第二图像获取部分还包括：
    控制器，用于当所述探测部分探测到人的手掌出现在探测部分的探测范围内，且第一图像获取部分没有启动时，启动第二发光单元以及第二红外摄像头。
  6. 根据权利要求3或4所述的装置，其特征在于，所述第一、第二发光单元为LED灯，用于对摄像头拍摄的对象进行补光。
  7. 根据权利要求1所述的装置，其特征在于，所述第一图像获取部分的取样距离为所述第二图像获取部分的取样距离的2～10倍。
  8. 根据权利要求7所述的装置，其特征在于，所述第一图像获取部分的取样距离为0.3～1.5米。
  9. 根据权利要求6所述的装置，其特征在于，所述第一发光单元的强度为第二发光单元强度的1.5～3倍。
  10. 根据权利要求1所述的装置，其特征在于，所述手掌图像包括手掌掌纹图像、手掌骨骼图像、手掌形状图像以及手掌血管图像中的一种或几种。
  11. 一种用于识别个人的装置，包括：
    探测部分，用于当探测到人的面部出现在探测范围内时，输出包含面部确认信息的结果；
    第一图像获取部分，用于获取探测范围内出现的面部图像；
    第二图像获取部分，用于获取探测范围内出现的手掌图像；其中，
    所述第一图像获取部分和第二图像获取部分在不同的时间获取其各自的图像；以及
    识别部分，用于基于面部图像和/或手掌图像识别个人。
  12. 根据权利要求11的装置，其中所述识别部分包括：
    面部图像处理单元，用于基于面部图像生成面部特征图像；
    手掌图像处理单元，用于基于手掌图像生成手掌特征图像；以及
    基于面部的匹配单元，用于对所述面部特征图像和存储在第一数据库中的多个候选面部特征图像进行比对从而生成第一匹配结果；
    基于手掌的匹配单元，用于对所述手掌特征图像和存储在第二数据库中的多个候选手掌特征图像中的每一个进行比对从而生成第二匹配结果；以及
    身份确定器，用于基于所述第一匹配结果和/或第二匹配结果识别该个人。
  13. 一种在具有至少一个处理器和存储器的机器上实现的获取生物识别信息的方法，包括：
    当个人的面部出现在设备的探测区域内时对所述面部的存在进行感测；
    获取感测到的所述人的面部图像；以及
    当人的手掌出现在设备的探测区域内时获取属于该个人的手掌图像；其中，
    所述面部图像和手掌图像在不同的时间获取。
  14. 根据权利要求13的方法，其特征在于，获取的所述面部图像和手掌图像为红外测绘图像。
PCT/CN2016/078746 2016-04-08 2016-04-08 一种基于多模式生物识别信息的个人识别装置和方法 WO2017173639A1 (zh)

Priority Applications (1)

Application Number Priority Date Filing Date Title
PCT/CN2016/078746 WO2017173639A1 (zh) 2016-04-08 2016-04-08 一种基于多模式生物识别信息的个人识别装置和方法

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
PCT/CN2016/078746 WO2017173639A1 (zh) 2016-04-08 2016-04-08 一种基于多模式生物识别信息的个人识别装置和方法

Publications (1)

Publication Number Publication Date
WO2017173639A1 true WO2017173639A1 (zh) 2017-10-12

Family

ID=60000196

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2016/078746 WO2017173639A1 (zh) 2016-04-08 2016-04-08 一种基于多模式生物识别信息的个人识别装置和方法

Country Status (1)

Country Link
WO (1) WO2017173639A1 (zh)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111137605A (zh) * 2018-11-06 2020-05-12 珠海格力电器股份有限公司 一种垃圾桶
CN112666835A (zh) * 2019-10-15 2021-04-16 新狮展(上海)展示服务有限公司 一种用于展厅远程控制的中央控制系统
US11341794B2 (en) 2020-03-28 2022-05-24 Zkteco Usa Unattended touchless health-check screening systems incorporating biometrics and thermographic technologies

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1612715A1 (en) * 2004-06-28 2006-01-04 Fujitsu Limited Image capturing apparatus for palm authentication
CN102332093A (zh) * 2011-09-19 2012-01-25 汉王科技股份有限公司 一种掌纹和人脸融合识别的身份认证方法及装置
CN202266112U (zh) * 2011-09-19 2012-06-06 汉王科技股份有限公司 一种具有人脸和掌纹识别功能的保险柜
CN202431068U (zh) * 2011-09-19 2012-09-12 汉王科技股份有限公司 一种基于人脸和掌纹识别的智能门锁
CN103646203A (zh) * 2013-12-20 2014-03-19 中晟国计科技有限公司 一种具有人体生物特征识别的计算机安全系统

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP1612715A1 (en) * 2004-06-28 2006-01-04 Fujitsu Limited Image capturing apparatus for palm authentication
CN102332093A (zh) * 2011-09-19 2012-01-25 汉王科技股份有限公司 一种掌纹和人脸融合识别的身份认证方法及装置
CN202266112U (zh) * 2011-09-19 2012-06-06 汉王科技股份有限公司 一种具有人脸和掌纹识别功能的保险柜
CN202431068U (zh) * 2011-09-19 2012-09-12 汉王科技股份有限公司 一种基于人脸和掌纹识别的智能门锁
CN103646203A (zh) * 2013-12-20 2014-03-19 中晟国计科技有限公司 一种具有人体生物特征识别的计算机安全系统

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN111137605A (zh) * 2018-11-06 2020-05-12 珠海格力电器股份有限公司 一种垃圾桶
CN112666835A (zh) * 2019-10-15 2021-04-16 新狮展(上海)展示服务有限公司 一种用于展厅远程控制的中央控制系统
US11341794B2 (en) 2020-03-28 2022-05-24 Zkteco Usa Unattended touchless health-check screening systems incorporating biometrics and thermographic technologies

Similar Documents

Publication Publication Date Title
CN105956520B (zh) 一种基于多模式生物识别信息的个人识别装置和方法
US7616784B2 (en) Method and apparatus for contactless hand recognition
CN107438854B (zh) 使用移动设备捕获的图像执行基于指纹的用户认证的系统和方法
CN107209848B (zh) 用于基于多模式生物识别信息的个人识别的系统和方法
KR101720957B1 (ko) 지문과 지정맥을 동시에 인증하는 다면 입체 촬영장치
JP2020061171A (ja) カメラ付きデバイスに関連する生体認証のためのシステム及び方法
TWI664552B (zh) 與配備有相機之裝置連接之用於生物特徵量測鑑認之系統及方法
CN108604289B (zh) 用于身份验证的有机体检测系统和方法
WO2005057472A1 (fr) Procede de reconnaissance des visages et systeme d'acquisition d'images
CN107004113B (zh) 用于获取多模式生物识别信息的系统和方法
KR101626837B1 (ko) 손가락 마디 및 지정맥 기반의 융합형 생체 인증 방법 및 그 장치
CN112232155B (zh) 非接触指纹识别的方法、装置、终端及存储介质
CN112232163B (zh) 指纹采集方法及装置、指纹比对方法及装置、设备
CN112232159B (zh) 指纹识别的方法、装置、终端及存储介质
WO2017173639A1 (zh) 一种基于多模式生物识别信息的个人识别装置和方法
CN112232157B (zh) 指纹区域检测方法、装置、设备、存储介质
CN112232152B (zh) 非接触式指纹识别方法、装置、终端和存储介质
Patil et al. Iris recognition using fuzzy system
KR101792012B1 (ko) 지문과 지정맥의 알고리즘을 동시에 연동시키는 입출력 통합모듈
Schreiner Biometrics: Prospects for going the distance
Hartová et al. Influence of face lighting on the reliability of biometric facial readers
Reddy et al. Intelligent Door Lock System with Face Recognition
CN212569821U (zh) 非接触式指纹采集装置
Hemalatha et al. A study of liveness detection in face biometric systems
Falohun et al. Remote Access Control System using Iris Signature

Legal Events

Date Code Title Description
NENP Non-entry into the national phase

Ref country code: DE

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

Ref document number: 16897573

Country of ref document: EP

Kind code of ref document: A1

122 Ep: pct application non-entry in european phase

Ref document number: 16897573

Country of ref document: EP

Kind code of ref document: A1