[go: up one dir, main page]

CN103034846A - Face indentification device for live person - Google Patents

Face indentification device for live person Download PDF

Info

Publication number
CN103034846A
CN103034846A CN2012105361882A CN201210536188A CN103034846A CN 103034846 A CN103034846 A CN 103034846A CN 2012105361882 A CN2012105361882 A CN 2012105361882A CN 201210536188 A CN201210536188 A CN 201210536188A CN 103034846 A CN103034846 A CN 103034846A
Authority
CN
China
Prior art keywords
face
indentification
light source
differentiated
striped
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.)
Pending
Application number
CN2012105361882A
Other languages
Chinese (zh)
Inventor
高宏
王庆
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.)
UNIS CO Ltd
Original Assignee
UNIS 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 UNIS CO Ltd filed Critical UNIS CO Ltd
Priority to CN2012105361882A priority Critical patent/CN103034846A/en
Publication of CN103034846A publication Critical patent/CN103034846A/en
Pending legal-status Critical Current

Links

Images

Landscapes

  • Collating Specific Patterns (AREA)

Abstract

The invention relates to a face indentification device for a live person and belongs to technical field of the face indentification. The face indentification device for the live person comprises a light source, a barrier panel, a vidicon, and a computer. The computer is respectively connected with the vidicon and a light source. Light beams sent by the light source are kept out by the barrier panel. The light beams can be turned into parallel equal separation stright line fringe patterns and can be reflected on surface of the indentified subject. The vidicion can convert an image of the identified subject to a digital image and output the digital image to the computer. The face indentification device for the live person can identify the faces of the live persons, static graphic photos, and dynamic screen images by utilizing stright line fringe patterns which are sent out. Accuracy rate of the identification is very high. Compared with prior art, the face indentification device for the live person can identify the face without a person identified changing face expression to coordinate the identification. The defect which the existing technology can only identify the static photos and cannot identify the dynamic screen images is resolved. The face indentification device for the live person enhances security and convenience of a face indentification system. The face indentification device for the live person has the advantages of being simple in structure, reliable in operation, rapid in indentification, and easy to carry out.

Description

A kind of living body faces identification device
Technical field
The present invention relates to a kind of living body faces identification device, particularly a kind of living body faces identification device for face identification system belongs to the face recognition technology field.
Background technology
Face recognition technology is differentiated people's identity by analyzing relatively people's face biological information.Compare with other biological characteristic authentication technique, recognition of face is a kind of more direct, more convenient, more friendly, easier non-infringement gender identity recognition technology that is accepted.Along with the widespread use of recognition of face identity authentication system, illegal use validated user photo has appearred with the security incident by authentication.
For identification true man and photo, some face identification systems have increased the living body faces identification function, determining to be identified object by identified person's countenance variation (nictation or smile) is the live body true man, there is following defective in this living body faces discrimination method: need identified person face to do a large amount of expression interoperations, man-machine interaction mode is unfriendly, the user is produced be weary of sense, and algorithm is complicated, reduce the speed of recognition of face; And, if utilize panel computer or notebook computer, when playing the video image of validated user, still can by authentication, cause security incident.
Summary of the invention
The objective of the invention is to propose a kind of living body faces identification device, in identifying, the identified person does not need to do expression shape change and cooperates identification, can identify the screen equipment of playing validated user dynamic human face image simultaneously.
The living body faces identification device that the present invention proposes comprises:
Light source is used for providing stable luminous energy, to being differentiated that object throws light on;
The fence panel is used for blocking the illuminating bundle that light source sends, illuminating bundle is become project behind the parallel equidistant linear fringe shape illuminating bundle differentiated body surface, fence panel place light source with by between the discriminating object;
Video camera be used for to be taken the surface with the equidistant image of being differentiated object of striped, and is digital picture with the image transitions of taking, and digital picture is exported to computing machine;
Computing machine, the unlatching of control light source, the digital picture of acquisition camera output is judged the equidistant striped in the digital picture, if equidistantly striped is parallel equidistant linear fringe, then judges and is differentiated that object is non-living body people face; If equidistantly striped is crooked equidistantly striped, then judges and differentiated that object is living body faces.
The living body faces identification device that the present invention proposes, utilize the height change of true man face surface configuration, be modulated to the curved stripes that changes with people's face three-D profile with projecting identified person's linear fringe on the face, whether project identified person's linear fringe on the face by judgement occurs bending and deformation, and whether the striated pattern outside the facial contour suddenly disappears, differentiate living body faces and plane photo and flat screen, the accuracy rate of discriminating is very high.Compared with prior art, do not need the identified person to do expression shape change and cooperate identification, and solved the defective that prior art can only be differentiated still photo, can not differentiate the screen dynamic image, improved greatly security and the convenience of face identification system.Simultaneously, adopt apparatus of the present invention, simple in structure, reliable operation, distinguishing speed is very fast, and easy to implement.
Description of drawings
Fig. 1 is the structured flowchart of the face detection device that proposes of the present invention.
Fig. 2 is the fence panel structure chart.
Fig. 3 is that the living body faces that face identification system collects is differentiated image, and wherein (a) is the image when projecting the linear fringe figure on the photo, (b) is the image when projecting the linear fringe figure on the living body faces.
Among Fig. 1, the 1st, light source, the 2nd, fence panel, the 3rd, video camera, the 4th, computing machine.
Embodiment
The living body faces identification device that the present invention proposes, its structured flowchart comprises as shown in Figure 1:
Light source 1 is used for providing stable luminous energy, to being differentiated that object throws light on, is differentiated that object may be identified person's face, also may be photo, panel computer screen or notebook computer screen etc.;
Fence panel 2, its structure are used for blocking the illuminating bundle that light source sends as shown in Figure 2, illuminating bundle is become project behind the parallel equidistant linear fringe shape illuminating bundle differentiated body surface, fence panel place light source with by between the discriminating object;
Video camera 3 be used for to be taken the surface with the equidistant image of being differentiated object of striped, and is digital picture with the image transitions of taking, and digital picture is exported to computing machine;
Computing machine 4, the unlatching of control light source, the digital picture of acquisition camera output is judged the equidistant striped in the digital picture, if equidistantly striped is parallel equidistant linear fringe, then judges and is differentiated that object is non-living body people face; If equidistantly striped is crooked equidistantly striped, then judges and differentiated that object is living body faces.
Among the embodiment of living body faces identification device of the present invention, light source 1 adopts Ou Silang 3W large power white light LED (Light Emitting Diode) light emitting diode, it is opaque plastics sheet (the gap width 0.2mm of 0.3mm that fence panel 2 adopts thickness, slit spacing 0.4mm), video camera 3 adopts the CCD digital camera, and computing machine 1 adopts general purpose PC.
The principle of work of living body faces identification device of the present invention is:
It is luminous that computing machine 4 is at first controlled light source 1, the illuminating bundle that light source 1 sends is blocked by fence panel 2, project by on discriminating object (identified person's face, photo, panel computer screen or the notebook computer screen) surface after making illuminating bundle become parallel equidistant linear fringe figure, video camera 3 will be differentiated, and the optical imagery of object is converted to digital picture, and digital picture is exported to computing machine 4.
Be the plane if be identified body surface, such as photo, panel computer screen and notebook computer screen, project the striped that is identified on the object and remain parallel lines, and on the background beyond the facial contour, still can see the parallel lines striped, shown in Fig. 3 (a), then computing machine 1 judges that being identified object is not living body faces.
Be living body faces if be identified object, because everywhere height is different on people's face surface, make and project the lip-deep linear fringe of identified person's face and occur bending and deformation, and the light that projects beyond the facial contour is absorbed by surrounding environment, can't be reflected back video camera 3, shown in Fig. 3 (b), the striated pattern bar that projects beyond the facial contour is suddenly disappeared, then computing machine 4 judges that being identified object is the live body true man.Then computing machine 4 cuts out light source 1, Resurvey video camera 3 output be identified facial image, extract identified person's face organ's feature and the relative position between them, again the people's face in itself and the face database is compared, thereby draws recognition result.
The parallel lines striated pattern that living body faces identification device of the present invention utilization is throwed is away differentiated living body faces and static plane photo and flat screen dynamic image, the accuracy rate of differentiating is very high, compared with prior art, do not need the identified person to do expression shape change and cooperate identification, and solved the defective that prior art can only be differentiated still photo, can not differentiate the screen dynamic image, improved greatly security and the convenience of face identification system.Simultaneously, adopt technical scheme of the present invention, system architecture is simple and reliable, and distinguishing speed is very fast, and easy to implement.

Claims (1)

1. living body faces identification device is characterized in that this living body faces identification device comprises:
Light source is used for providing stable luminous energy, to being differentiated that object throws light on;
The fence panel is used for blocking the illuminating bundle that light source sends, illuminating bundle is become project behind the parallel equidistant linear fringe shape illuminating bundle differentiated body surface, fence panel place light source with by between the discriminating object;
Video camera be used for to be taken the surface with the equidistant image of being differentiated object of striped, and is digital picture with the image transitions of taking, and digital picture is exported to computing machine;
Computing machine, the unlatching of control light source, the digital picture of acquisition camera output is judged the equidistant striped in the digital picture, if equidistantly striped is parallel equidistant linear fringe, then judges and is differentiated that object is non-living body people face; If equidistantly striped is crooked equidistantly striped, then judges and differentiated that object is living body faces.
CN2012105361882A 2012-12-12 2012-12-12 Face indentification device for live person Pending CN103034846A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN2012105361882A CN103034846A (en) 2012-12-12 2012-12-12 Face indentification device for live person

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN2012105361882A CN103034846A (en) 2012-12-12 2012-12-12 Face indentification device for live person

Publications (1)

Publication Number Publication Date
CN103034846A true CN103034846A (en) 2013-04-10

Family

ID=48021725

Family Applications (1)

Application Number Title Priority Date Filing Date
CN2012105361882A Pending CN103034846A (en) 2012-12-12 2012-12-12 Face indentification device for live person

Country Status (1)

Country Link
CN (1) CN103034846A (en)

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108171205A (en) * 2018-01-17 2018-06-15 百度在线网络技术(北京)有限公司 For identifying the method and apparatus of face
CN108304801A (en) * 2018-01-30 2018-07-20 亿慧云智能科技(深圳)股份有限公司 A kind of face identification method of anti-fraud, storage medium and face identification device
CN109299677A (en) * 2018-09-07 2019-02-01 西安知微传感技术有限公司 A kind of recognition of face living body judgment method and system
CN112115925A (en) * 2020-11-18 2020-12-22 鹏城实验室 Face recognition method and device and computer readable storage medium
CN112784714A (en) * 2021-01-11 2021-05-11 江苏大学 Real-time detection system and method for reading attention of user group based on library shared space
CN112949364A (en) * 2019-12-10 2021-06-11 纬创资通股份有限公司 Living face identification system and method

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE19712844A1 (en) * 1997-03-26 1998-10-08 Siemens Ag Method for three-dimensional identification of objects
CN1748227A (en) * 2003-02-13 2006-03-15 日本电气株式会社 Masquerading detection device and masquerading detection method
CN202956771U (en) * 2012-12-12 2013-05-29 紫光股份有限公司 Living body face identification device

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE19712844A1 (en) * 1997-03-26 1998-10-08 Siemens Ag Method for three-dimensional identification of objects
CN1748227A (en) * 2003-02-13 2006-03-15 日本电气株式会社 Masquerading detection device and masquerading detection method
CN202956771U (en) * 2012-12-12 2013-05-29 紫光股份有限公司 Living body face identification device

Cited By (10)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN108171205A (en) * 2018-01-17 2018-06-15 百度在线网络技术(北京)有限公司 For identifying the method and apparatus of face
CN108304801A (en) * 2018-01-30 2018-07-20 亿慧云智能科技(深圳)股份有限公司 A kind of face identification method of anti-fraud, storage medium and face identification device
CN108304801B (en) * 2018-01-30 2021-10-08 亿慧云智能科技(深圳)股份有限公司 An anti-spoofing face recognition method, storage medium and face recognition device
CN109299677A (en) * 2018-09-07 2019-02-01 西安知微传感技术有限公司 A kind of recognition of face living body judgment method and system
CN112949364A (en) * 2019-12-10 2021-06-11 纬创资通股份有限公司 Living face identification system and method
TWI761739B (en) * 2019-12-10 2022-04-21 緯創資通股份有限公司 Live facial recognition system and method
US11335123B2 (en) 2019-12-10 2022-05-17 Wistron Corporation Live facial recognition system and method
CN112949364B (en) * 2019-12-10 2023-12-08 纬创资通股份有限公司 Living face recognition system and method
CN112115925A (en) * 2020-11-18 2020-12-22 鹏城实验室 Face recognition method and device and computer readable storage medium
CN112784714A (en) * 2021-01-11 2021-05-11 江苏大学 Real-time detection system and method for reading attention of user group based on library shared space

Similar Documents

Publication Publication Date Title
CN103020600B (en) A kind of face indentification device for live person for face identification system
CN106446873B (en) Face detection method and device
US10204262B2 (en) Infrared imaging recognition enhanced by 3D verification
CN103034846A (en) Face indentification device for live person
CN106372601B (en) Living body detection method and device based on infrared visible binocular images
CN107292283A (en) Mix face identification method
US11682231B2 (en) Living body detection method and device
CN104361315A (en) 3D (three-dimensional) fingerprint recognition device based on monocular and multi-view stereoscopic machine vision
CN105574509B (en) A kind of face identification system replay attack detection method and application based on illumination
CN101464751B (en) Electronic white board system based on image detection and detection method thereof
Taini et al. Facial expression recognition from near-infrared video sequences
CN105574525A (en) Method and device for obtaining complex scene multi-mode biology characteristic image
Linder et al. Real-time full-body human gender recognition in (RGB)-D data
CN103336950A (en) Human face identification method and system
WO2018210048A1 (en) Fpga-based hardware iris recognition system and method, and readable storage medium
CN103077382A (en) Human identification device used for face recognition system
CN111539348A (en) Face living body detection method based on polarization imaging
CN203054868U (en) Real-person discriminating device used for face identification system
CN202956772U (en) Living body human face identification device for human face identification system
CN202956771U (en) Living body face identification device
Shieh et al. Fast facial detection by depth map analysis
CN106295497B (en) A device and method for generating and identifying a three-dimensional surface light field encoding signal
Yu et al. Sltp: A fast descriptor for people detection in depth images
CN108513661A (en) Identification authentication method, identification authentication device and electronic equipment
WO2017173639A1 (en) Personal recognition device and method on the basis of multi-mode biological recognition information

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C02 Deemed withdrawal of patent application after publication (patent law 2001)
WD01 Invention patent application deemed withdrawn after publication

Application publication date: 20130410