CN101964056A - Bimodal face authentication method with living body detection function and system - Google Patents

Bimodal face authentication method with living body detection function and system Download PDF

Info

Publication number
CN101964056A
CN101964056A CN 201010519964 CN201010519964A CN101964056A CN 101964056 A CN101964056 A CN 101964056A CN 201010519964 CN201010519964 CN 201010519964 CN 201010519964 A CN201010519964 A CN 201010519964A CN 101964056 A CN101964056 A CN 101964056A
Authority
CN
China
Prior art keywords
face
image
people
module
visible light
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.)
Granted
Application number
CN 201010519964
Other languages
Chinese (zh)
Other versions
CN101964056B (en
Inventor
徐勇
文嘉俊
徐佳杰
杨治银
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.)
Hunan Weilian Intelligent Technology Co., Ltd
Original Assignee
徐勇
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 徐勇 filed Critical 徐勇
Priority to CN2010105199649A priority Critical patent/CN101964056B/en
Publication of CN101964056A publication Critical patent/CN101964056A/en
Application granted granted Critical
Publication of CN101964056B publication Critical patent/CN101964056B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Landscapes

  • Collating Specific Patterns (AREA)
  • Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)

Abstract

The invention relates to data identification, in particular to a bimodal face authentication method with a living body detection function and a system. The authentication method of the invention comprises the following steps: A. establishing a database of visible light training images and near-infrared training images of known faces; and B. simultaneously collecting visible light images and near-infrared images of the heads of people to be authenticated. The invention also provides a bimodal face authentication system with a living body detection function. The invention has the beneficial effects that combined identification with the bimodal characteristics of face near-infrared images and face visible light images is adopted, as a result, the identification and authentication accuracy is improved, identification failure in the case of major changes of faces is avoided; and in addition, a living body detection module is utilized to effectively prevent personators from using photos or models to deceive others.

Description

A kind of bimodal face authentication method and system with live body measuring ability
Technical field
The present invention relates to data identification, particularly a kind of bimodal face authentication method and the system in the data identification with live body measuring ability.
Background technology
At present, the existing face authentication performance that is difficult to obtain owing to the influence that is subjected to illumination variation deeply based on the face authentication system of visible light.Though what propose in recent years can partly overcome the influence of illumination variation based near infrared face authentication system, but recognition time apart from the very long situation of people's face hour of log-on under, because people's face exists under the big situation of change (under the fat or thin situation that alters a great deal of people's face), recognition failures is generally understood by system.In addition, because existing face authentication system does not propose the living body faces detection scheme, be vulnerable to utilize the deception of faceform or photo, promptly steal registered someone facial image or produce this people's faceform after, the personator was easy to successfully fraud system when the personator placed face authentication system the place ahead with the photo of stolen people's face or model, made system think that its identity is stolen personnel selection.This is because very very approaching near the direct imaging of the imaging of (just as usually to the imaging of taking pictures of human face photo with direct very approaching to the imaging of taking pictures of people's face) and face mould and real human face in the direct imaging effect of the secondary imaging effect of the photo of visible light condition human face and real human face.
Summary of the invention
People's face exists under the big situation of change in the prior art in order to solve, recognition failures is generally understood by system, can't detect living body faces, system is subjected to the problem of the deception of photo or model easily, the invention provides a kind of bimodal face authentication method and system with live body measuring ability.
The invention provides a kind of bimodal face authentication method, may further comprise the steps with live body measuring ability:
A, foundation store the visible light training image of known identities people face and the database of near infrared training image;
B, gather head part's to be certified visible images and near-infrared image simultaneously by image capture module;
C, calculate the people's face visible images in the described visible images and the visible light distance of described visible light training image, and calculate the people's face near-infrared image in the described near-infrared image and the near infrared distance of described near infrared training image by distance calculation module;
D, by the live body detection module with the described visible light distance of minimum with set visible light relatively apart from threshold values, and with the described near infrared distance of minimum with set near infrared relatively apart from threshold values, if minimum described visible light distance is less than setting visible light apart from threshold values, and minimum described near infrared distance is greater than setting near infrared apart from threshold values, assert that then people's face to be certified is a non-living body people face, be judged to be fake user and stop authentication, otherwise, carry out next step;
E, calculate the weighted sum of described visible light distance and described near infrared distance by the image authentication module, the described weighted sum that draws is compared with setting weighted sum threshold values, if the described weighted sum that draws is greater than setting the weighted sum threshold values, then authentication is not passed through, be judged to be the disabled user and stop authentication, otherwise, carry out next step;
F, face authentication pass through;
Wherein, the order of described step D and described step e is interchangeable.
As a further improvement on the present invention, described step C comprises following substep:
C1, people's face visible images in the described visible images and described visible light training image are carried out histogram equalization by the histogram equalization module;
C2, calculate the visible light distance of described people's face visible images and described visible light training image, and calculate the people's face near-infrared image in the described near-infrared image and the near infrared distance of described near infrared training image by described distance calculation module;
C3, respectively described visible light distance and described near infrared distance is carried out normalization by the normalization module.
As a further improvement on the present invention, the described weighted sum that draws in the described step e is d, and described visible light distance is d 1, described near infrared distance is d 2, d=0.3 d then 1+ 0.7 d 2, described setting weighted sum threshold values is 0.32.
As a further improvement on the present invention, the setting visible light among the described step D is 0.35 apart from threshold values, and described setting near infrared is 0.6 apart from threshold values.
As a further improvement on the present invention, described step B comprises following substep:
B1, gather head part's to be certified described visible images and described near-infrared image simultaneously by described image capture module;
B2, judge whether and can from described visible images and described near-infrared image, detect people's face simultaneously by people's face detection module, if could not would return described step B1, if could would carry out next step.
As a further improvement on the present invention, described bimodal face authentication method with live body measuring ability is further comprising the steps of:
G, will authenticate the described people's face visible images that passes through by the training sample update module and be set at described visible light training image and updated stored in the database of steps A, described people's face near-infrared image that authentication is passed through is set at described near infrared training image and updated stored in the database of steps A.
The present invention also provides a kind of bimodal face authentication system with live body measuring ability, comprise the visible light training image that stores known identities people face and the database of near infrared training image, can gather the head part's to be certified visible images and the image capture module of near-infrared image simultaneously, can calculate the visible light distance of people's face visible images and described visible light training image in the described visible images and calculate the distance calculation module of the near infrared distance of people's face near-infrared image and described near infrared training image in the described near-infrared image, whether decidable people's face to be certified is whether live body detection module and decidable people's face to be certified of live body is the image authentication module of validated user, wherein, the input end of described distance calculation module respectively with the output terminal of described database, the output terminal of described image capture module connects, the output terminal of described distance calculation module is connected with the input end of described live body detection module, and the output terminal of described live body detection module is connected with the input end of described image authentication module.
As a further improvement on the present invention, described image authentication module is connected with the training sample update module, the output terminal of described training sample update module is connected with the input end of described database, described image capture module comprises at least two visible image capturing heads, is coated with optical filter on one of them described visible image capturing head to gather people's face near-infrared image.
As a further improvement on the present invention, described bimodal face authentication system with live body measuring ability also comprises the histogram equalization module, normalization module and people's face detection module that can judge whether from described visible images and described near-infrared image, to detect simultaneously people's face, wherein, the input end of described people's face detection module is connected with the output terminal of described image capture module, the output terminal of described people's face detection module is connected with the input end of described image capture module and the input end of described histogram equalization module respectively, the output terminal of described histogram equalization module is connected with the input end of described distance calculation module, the input end of described normalization module links to each other with the output terminal of described distance calculation module, and the output terminal of described normalization module is connected with the input end of described live body detection module.
The present invention also provides a kind of bimodal face authentication system with live body measuring ability, comprise the visible light training image that stores known identities people face and the database of near infrared training image, can gather the head part's to be certified visible images and the image capture module of near-infrared image simultaneously, can calculate the visible light distance of people's face visible images in the described visible images and described visible light training image and calculate people's face near-infrared image in the described near-infrared image and the distance calculation module of the near infrared distance of described near infrared training image, whether decidable people's face to be certified is whether live body detection module and decidable people's face to be certified of live body is the image authentication module of validated user, wherein, the input end of described distance calculation module respectively with the output terminal of described database, the output terminal of described image capture module connects, the output terminal of described distance calculation module is connected with the input end of described image authentication module, and the output terminal of described image authentication module is connected with the input end of described live body detection module.
The invention has the beneficial effects as follows: pass through such scheme, adopt the identification of uniting of people's face near-infrared image and people's face visible images bimodal feature, improved the identification authentication precision, effectively avoid people's face to have the problem of recognition failures under the big situation of change, by the live body detection module, effectively avoided the personator to cheat by photo or model.
Description of drawings
Fig. 1 is the schematic flow sheet of the embodiment one of a kind of bimodal face authentication method with live body measuring ability of the present invention;
Fig. 2 is the structural representation of the embodiment one of the bimodal face authentication system with live body measuring ability of the present invention;
Fig. 3 is the schematic flow sheet of the embodiment two of a kind of bimodal face authentication method with live body measuring ability of the present invention;
Fig. 4 is the structural representation of the embodiment two of the bimodal face authentication system with live body measuring ability of the present invention.
Embodiment
The present invention is further described below in conjunction with description of drawings and embodiment.
Drawing reference numeral among Fig. 1 to Fig. 4 is: database 101; Image capture module 102; People's face detection module 103; Histogram equalization module 104; Distance calculation module 105; Normalization module 106; Live body detection module 107; Image authentication module 108; Training sample update module 109.
As shown in Figure 1, a kind of embodiment one with bimodal face authentication method of live body measuring ability may further comprise the steps:
A, foundation store the visible light training image of known identities people face and the database 101 of near infrared training image;
B1, gather head part's to be certified visible images and near-infrared image simultaneously by described image capture module 102;
B2, judge whether and from described visible images and described near-infrared image, to detect people's face simultaneously by people's face detection module, if could not would return described step B1, if could the human face region in the described visible images would be intercepted out as " people's face visible images ", with the human face region in the described near-infrared image intercept out as " people's face near-infrared image ", and carry out next step;
C1, described people's face visible images and described visible light training image are carried out histogram equalization by histogram equalization module 104;
C2, calculate the visible light distance of described people's face visible images and described visible light training image, and calculate the near infrared distance of described people's face near-infrared image and described near infrared training image by described distance calculation module 105;
C3, respectively described visible light distance and described near infrared distance is carried out normalization by normalization module 106.
D, by live body detection module 107 with the described visible light distance of minimum with set visible light relatively apart from threshold values, and with the described near infrared distance of minimum with set near infrared relatively apart from threshold values, if minimum described visible light distance is less than setting visible light apart from threshold values, and minimum described near infrared distance is greater than setting near infrared apart from threshold values, assert that then people's face to be certified is a non-living body people face, be judged to be fake user and stop authentication, otherwise, carry out next step;
E, calculate the weighted sum of described visible light distance and described near infrared distance by image authentication module 108, the described weighted sum that draws is compared with setting weighted sum threshold values, if the described weighted sum that draws is greater than setting the weighted sum threshold values, then authentication is not passed through, be judged to be the disabled user and stop authentication, otherwise, carry out next step;
F, face authentication pass through;
G, will authenticate the described people's face visible images that passes through by training sample update module 109 and be set at described visible light training image and updated stored in the database 101 of steps A, described people's face near-infrared image that authentication is passed through is set at described near infrared training image and updated stored in the database 101 of steps A.
Wherein, the order of described step D and described step e is interchangeable, whether comprise people's face in the image that can determine to collect by step B2, avoid authenticating not collecting people's face or gather the incomplete situation of people's face that step G can effectively avoid people's face to have the situation of bigger variation.
Can on the normalization basis, carry out the matching score layer and merge, and draw the final authentication result of people's face according to fusion results.
The described weighted sum that draws in the described step e is d, and described visible light distance is d 1, described near infrared distance is d 2, d=0.3 d then 1+ 0.7 d 2, described setting weighted sum threshold values is preferably 0.32.
Setting visible light among the described step D is preferably 0.35 apart from threshold values, and described setting near infrared is preferably 0.6 apart from threshold values.
A kind of embodiment one with bimodal face authentication method of live body measuring ability provided by the invention can also may further comprise the steps, concentrate some neighbour's samples of determining people's face near-infrared image to be certified from everyone the near infrared training image of face, and from the concentrated some neighbour's samples of determining people's face visible images to be certified of the visible light training image of everyone face, people's face near-infrared image to be certified is expressed as the linear combination of corresponding neighbour's sample, goes out similarity between this people's face near-infrared image and all categories according to the coefficient calculations of linear combination; People's face visible images to be certified is expressed as the linear combination of corresponding neighbour's sample, goes out similarity between this people's face visible images and all categories according to the coefficient calculations of linear combination.
As shown in Figure 2, a kind of embodiment one with bimodal face authentication system of live body measuring ability, comprise the visible light training image that stores known identities people face and the database 101 of near infrared training image, can gather the head part's to be certified visible images and the image capture module 102 of near-infrared image simultaneously, can calculate the visible light distance of people's face visible images in the described visible images and described visible light training image and calculate people's face near-infrared image in the described near-infrared image and the distance calculation module 103 of the near infrared distance of described near infrared training image, whether decidable people's face to be certified is whether live body detection module 107 and decidable people's face to be certified of live body is the image authentication module 108 of validated user, wherein, the input end of described distance calculation module 105 respectively with the output terminal of described database 101, the output terminal of described image capture module 102 connects, the output terminal of described distance calculation module 105 is connected with the input end of described live body detection module 107, and the output terminal of described live body detection module 107 is connected with the input end of described image authentication module 108.
As shown in Figure 2, bimodal face authentication system with live body measuring ability also comprises training sample update module 109, the output terminal of described image authentication module 108 is connected with the input end of training sample update module 109, the output terminal of described training sample update module 109 is connected with the input end of described database 101, described image capture module 102 comprises at least two visible image capturing heads, be coated with optical filter on one of them described visible image capturing head to gather people's face near-infrared image, adopt two visible image capturing heads can avoid using outer camera, can reduce cost.
As shown in Figure 2, described bimodal face authentication system with live body measuring ability also comprises histogram equalization module 104, normalization module 106 and people's face detection module 103 that can judge whether from described visible images and described near-infrared image, to detect simultaneously people's face, wherein, the input end of described people's face detection module 103 is connected with the output terminal of described image capture module 102, the output terminal of described people's face detection module 103 is connected with the input end of described image capture module 102 and the input end of described histogram equalization module 104 respectively, the output terminal of described histogram equalization module 104 is connected with the input end of described distance calculation module 105, the input end of described normalization module 106 links to each other with the output terminal of described distance calculation module 105, and the output terminal of described normalization module 106 is connected with the input end of described live body detection module 107.
The practical operation of the embodiment one of a kind of bimodal face authentication system with live body measuring ability provided by the invention can be: the user at first touch-screen of the bimodal face authentication system by having the live body measuring ability imports its ID number, system accepts this ID number, trigger two camera work immediately, and take the visible images and the near-infrared image of people face simultaneously, behind the people's face visible images that detects the active user and people's face near-infrared image, system will call and take out its previously stored corresponding with the ID that receives number everyone face visible light training image and near infrared training image, and compare with above-mentioned visible light training image and near infrared training image respectively by active user's people's face visible light and people's face near-infrared image.
In order to shoot near-infrared image more clearly, can have arrangement near-infrared LED light source in the bimodal face authentication system of live body measuring ability, this near-infrared LED light emitted wavelength is 850nm.
A kind of two visible image capturing heads of embodiment one preferred employing provided by the invention with bimodal face authentication system of live body measuring ability, rather than adopt infrared camera to take near-infrared image, its concrete scheme is, cover optical filter therein on visible image capturing head and gather near-infrared image, make native system have low-cost characteristics, the optical filter that native system adopts is to stop wavelength to pass through greater than the ripple of 715 nm by allowing wavelength less than the ripple of 715 nm, and its center cutoff wavelength is about 756nm, and wavelength is the transmittance general about 90% of the ripple of 850nm.
As shown in Figure 3, a kind of embodiment two with bimodal face authentication method of live body measuring ability may further comprise the steps:
A, foundation store the visible light training image of known identities people face and the database 101 of near infrared training image;
B1, gather head part's to be certified visible images and near-infrared image simultaneously by described image capture module 102;
B2, judge whether and from described visible images and described near-infrared image, to detect people's face simultaneously by people's face detection module, if could not would return described step B1, if could the human face region in the described visible images would be intercepted out as " people's face visible images ", with the human face region in the described near-infrared image intercept out as " people's face near-infrared image ", and carry out next step;
C1, described people's face visible images and described visible light training image are carried out histogram equalization by histogram equalization module 104;
C2, calculate the visible light distance of described people's face visible images and described visible light training image, and calculate the near infrared distance of described people's face near-infrared image and described near infrared training image by described distance calculation module 105;
C3, respectively described visible light distance and described near infrared distance is carried out normalization by normalization module 106.
E, calculate the weighted sum of described visible light distance and described near infrared distance by image authentication module 108, the described weighted sum that draws is compared with setting weighted sum threshold values, if the described weighted sum that draws is greater than setting the weighted sum threshold values, then authentication is not passed through, be judged to be the disabled user and stop authentication, otherwise, carry out next step;
D, by live body detection module 107 with the described visible light distance of minimum with set visible light relatively apart from threshold values, and with the described near infrared distance of minimum with set near infrared relatively apart from threshold values, if minimum described visible light distance is less than setting visible light apart from threshold values, and minimum described near infrared distance is greater than setting near infrared apart from threshold values, assert that then people's face to be certified is a non-living body people face, be judged to be fake user and stop authentication, otherwise, carry out next step;
F, face authentication pass through;
G, will authenticate the described people's face visible images that passes through by training sample update module 109 and be set at described visible light training image and updated stored in the database 101 of steps A, described people's face near-infrared image that authentication is passed through is set at described near infrared training image and updated stored in the database 101 of steps A.
Wherein, the order of described step D and described step e is interchangeable, and step G can effectively avoid people's face to have the situation of bigger variation.
Can on the normalization basis, carry out the matching score layer and merge, and draw the final authentication result of people's face according to fusion results.
The described weighted sum that draws in the described step e is d, and described visible light distance is d 1, described near infrared distance is d 2, d=0.3 d then 1+ 0.7 d 2, described setting weighted sum threshold values is preferably 0.32.
Setting visible light among the described step D is preferably 0.35 apart from threshold values, and described setting near infrared is preferably 0.6 apart from threshold values.
A kind of embodiment two with bimodal face authentication method of live body measuring ability provided by the invention can also may further comprise the steps, concentrate some neighbour's samples of determining people's face near-infrared image to be certified from everyone the near infrared training image of face, and from the concentrated some neighbour's samples of determining people's face visible images to be certified of the visible light training image of everyone face, people's face near-infrared image to be certified is expressed as the linear combination of corresponding neighbour's sample, goes out similarity between this people's face near-infrared image and all categories according to the coefficient calculations of linear combination; People's face visible images to be certified is expressed as the linear combination of corresponding neighbour's sample, goes out similarity between this people's face visible images and all categories according to the coefficient calculations of linear combination.
As shown in Figure 4, a kind of embodiment two with bimodal face authentication system of live body measuring ability, comprise the visible light training image that stores known identities people face and the database 101 of near infrared training image, can gather the head part's to be certified visible images and the image capture module 102 of near-infrared image simultaneously, can calculate the visible light distance of people's face visible images in the described visible images and described visible light training image and calculate people's face near-infrared image in the described near-infrared image and the distance calculation module 105 of the near infrared distance of described near infrared training image, whether decidable people's face to be certified is whether live body detection module 107 and decidable people's face to be certified of live body is the image authentication module 108 of validated user, wherein, the input end of described distance calculation module 105 respectively with the output terminal of described database 101, the output terminal of described image capture module 102 connects, the output terminal of described distance calculation module 105 is connected with the input end of described image authentication module 108, and the output terminal of described image authentication module 108 is connected with the input end of described live body detection module 107.
As shown in Figure 4, bimodal face authentication system with live body measuring ability also comprises training sample update module 109, the output terminal of described image authentication module 108 is connected with the input end of described training sample update module 109, the output terminal of described training sample update module 109 is connected with the input end of described database 101, described image capture module 102 comprises at least two visible image capturing heads, is coated with optical filter on one of them described visible image capturing head.
As shown in Figure 4, described bimodal face authentication system with live body measuring ability also comprises histogram equalization module 104, normalization module 106 and people's face detection module 103 that can judge whether from described visible images and described near-infrared image, to detect simultaneously people's face, wherein, the input end of described people's face detection module 103 is connected with the output terminal of described image capture module 102, the output terminal of described people's face detection module 103 is connected with the input end of described image capture module 102 and the input end of described histogram equalization module 104 respectively, the output terminal of described histogram equalization module 104 is connected with the input end of described distance calculation module 105, the input end of described normalization module 106 links to each other with the output terminal of described distance calculation module 105, and the output terminal of described normalization module 106 is connected with the input end of described live body detection module 107.
The practical operation of the embodiment two of a kind of bimodal face authentication system with live body measuring ability provided by the invention can be: the user at first touch-screen of the bimodal face authentication system by having the live body measuring ability imports its ID number, system accepts this ID number, trigger two camera work immediately, and take the visible images and the near-infrared image of people face simultaneously, behind the people's face visible images that detects the active user and people's face near-infrared image, system will call and take out its previously stored corresponding with the ID that receives number everyone face visible light training image and near infrared training image, and compare with above-mentioned visible light training image and near infrared training image respectively by active user's people's face visible light and people's face near-infrared image.
In order to shoot near-infrared image more clearly, can have arrangement near-infrared LED light source in the bimodal face authentication system of live body measuring ability, this near-infrared LED light emitted wavelength is 850nm.
A kind of two visible image capturing heads of embodiment two preferred employings provided by the invention with bimodal face authentication system of live body measuring ability, rather than adopt infrared camera to take near-infrared image, its concrete scheme is, cover optical filter therein on visible image capturing head and gather near-infrared image, make native system have low-cost characteristics, the optical filter that native system adopts is to stop wavelength to pass through greater than the ripple of 715 nm by allowing wavelength less than the ripple of 715 nm, and its center cutoff wavelength is about 756nm, and wavelength is the transmittance general about 90% of the ripple of 850nm.
Above content be in conjunction with concrete preferred implementation to further describing that the present invention did, can not assert that concrete enforcement of the present invention is confined to these explanations.For the general technical staff of the technical field of the invention, without departing from the inventive concept of the premise, can also make some simple deduction or replace, all should be considered as belonging to protection scope of the present invention.

Claims (10)

1. the bimodal face authentication method with live body measuring ability is characterized in that, may further comprise the steps:
A, foundation store the visible light training image of known identities people face and the database of near infrared training image;
B, gather head part's to be certified visible images and near-infrared image simultaneously by image capture module;
C, calculate the people's face visible images in the described visible images and the visible light distance of described visible light training image, and calculate the people's face near-infrared image in the described near-infrared image and the near infrared distance of described near infrared training image by distance calculation module;
D, by the live body detection module with the described visible light distance of minimum with set visible light relatively apart from threshold values, and with the described near infrared distance of minimum with set near infrared relatively apart from threshold values, if minimum described visible light distance is less than setting visible light apart from threshold values, and minimum described near infrared distance is greater than setting near infrared apart from threshold values, assert that then people's face to be certified is a non-living body people face, be judged to be fake user and stop authentication, otherwise, carry out next step;
E, calculate the weighted sum of described visible light distance and described near infrared distance by the image authentication module, the described weighted sum that draws is compared with setting weighted sum threshold values, if the described weighted sum that draws is greater than setting the weighted sum threshold values, then authentication is not passed through, be judged to be the disabled user and stop authentication, otherwise, carry out next step;
F, face authentication pass through;
Wherein, the order of described step D and described step e is interchangeable.
2. according to the described bimodal face authentication method of claim 1, it is characterized in that described step C comprises following substep with live body measuring ability:
C1, people's face visible images in the described visible images and described visible light training image are carried out histogram equalization by the histogram equalization module;
C2, calculate the visible light distance of described people's face visible images and described visible light training image, and calculate the people's face near-infrared image in the described near-infrared image and the near infrared distance of described near infrared training image by described distance calculation module;
C3, respectively described visible light distance and described near infrared distance is carried out normalization by the normalization module.
3. according to the described bimodal face authentication method with live body measuring ability of claim 2, it is characterized in that the described weighted sum that draws in the described step e is d, described visible light distance is d 1, described near infrared distance is d 2, d=0.3 d then 1+ 0.7 d 2, described setting weighted sum threshold values is 0.32.
4. according to the described bimodal face authentication method with live body measuring ability of claim 2, it is characterized in that: the setting visible light among the described step D is 0.35 apart from threshold values, and described setting near infrared is 0.6 apart from threshold values.
5. according to the described bimodal face authentication method of claim 1, it is characterized in that described step B comprises following substep with live body measuring ability:
B1, gather head part's to be certified described visible images and described near-infrared image simultaneously by described image capture module;
B2, judge whether and can from described visible images and described near-infrared image, detect people's face simultaneously by people's face detection module, if could not would return described step B1, if could would carry out next step.
6. according to the described bimodal face authentication method of claim 1, it is characterized in that described bimodal face authentication method with live body measuring ability is further comprising the steps of with live body measuring ability:
G, will authenticate the described people's face visible images that passes through by the training sample update module and be set at described visible light training image and updated stored in the database of steps A, described people's face near-infrared image that authentication is passed through is set at described near infrared training image and updated stored in the database of steps A.
7. bimodal face authentication system with live body measuring ability, it is characterized in that: comprise the visible light training image that stores known identities people face and the database of near infrared training image, can gather the head part's to be certified visible images and the image capture module of near-infrared image simultaneously, can calculate the visible light distance of people's face visible images in the described visible images and described visible light training image and calculate people's face near-infrared image in the described near-infrared image and the distance calculation module of the near infrared distance of described near infrared training image, whether decidable people's face to be certified is whether live body detection module and decidable people's face to be certified of live body is the image authentication module of validated user, wherein, the input end of described distance calculation module respectively with the output terminal of described database, the output terminal of described image capture module connects, the output terminal of described distance calculation module is connected with the input end of described live body detection module, and the output terminal of described live body detection module is connected with the input end of described image authentication module.
8. according to the described bimodal face authentication system of claim 7 with live body measuring ability, it is characterized in that: described bimodal face authentication system with live body measuring ability comprises the training sample update module, the output terminal of described image authentication module is connected with the input end of described training sample update module, the output terminal of described training sample update module is connected with the input end of described database, described image capture module comprises at least two visible image capturing heads, is coated with optical filter on one of them described visible image capturing head.
9. according to the described bimodal face authentication system of claim 7 with live body measuring ability, it is characterized in that: described bimodal face authentication system with live body measuring ability also comprises the histogram equalization module, normalization module and people's face detection module that can judge whether from described visible images and described near-infrared image, to detect simultaneously people's face, wherein, the input end of described people's face detection module is connected with the output terminal of described image capture module, the output terminal of described people's face detection module is connected with the input end of described image capture module and the input end of described histogram equalization module respectively, the output terminal of described histogram equalization module is connected with the input end of described distance calculation module, the input end of described normalization module links to each other with the output terminal of described distance calculation module, and the output terminal of described normalization module is connected with the input end of described live body detection module.
10. bimodal face authentication system with live body measuring ability, it is characterized in that: comprise the visible light training image that stores known identities people face and the database of near infrared training image, can gather the head part's to be certified visible images and the image capture module of near-infrared image simultaneously, can calculate the visible light distance of people's face visible images in the described visible images and described visible light training image and calculate people's face near-infrared image in the described near-infrared image and the distance calculation module of the near infrared distance of described near infrared training image, whether decidable people's face to be certified is whether live body detection module and decidable people's face to be certified of live body is the image authentication module of validated user, wherein, the input end of described distance calculation module respectively with the output terminal of described database, the output terminal of described image capture module connects, the output terminal of described distance calculation module is connected with the input end of described image authentication module, and the output terminal of described image authentication module is connected with the input end of described live body detection module.
CN2010105199649A 2010-10-26 2010-10-26 Bimodal face authentication method with living body detection function and system Active CN101964056B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN2010105199649A CN101964056B (en) 2010-10-26 2010-10-26 Bimodal face authentication method with living body detection function and system

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN2010105199649A CN101964056B (en) 2010-10-26 2010-10-26 Bimodal face authentication method with living body detection function and system

Publications (2)

Publication Number Publication Date
CN101964056A true CN101964056A (en) 2011-02-02
CN101964056B CN101964056B (en) 2012-06-27

Family

ID=43516921

Family Applications (1)

Application Number Title Priority Date Filing Date
CN2010105199649A Active CN101964056B (en) 2010-10-26 2010-10-26 Bimodal face authentication method with living body detection function and system

Country Status (1)

Country Link
CN (1) CN101964056B (en)

Cited By (46)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102831379A (en) * 2011-06-14 2012-12-19 汉王科技股份有限公司 Face image recognition method and device
WO2013131407A1 (en) * 2012-03-08 2013-09-12 无锡中科奥森科技有限公司 Double verification face anti-counterfeiting method and device
CN103400108A (en) * 2013-07-10 2013-11-20 北京小米科技有限责任公司 Face identification method and device as well as mobile terminal
WO2014004179A1 (en) * 2012-06-26 2014-01-03 Qualcomm Incorporated Systems and method for facial verification
WO2014043003A1 (en) * 2012-09-12 2014-03-20 Google Inc. Method and device for authentication of live human faces using infra red images
CN103975343A (en) * 2011-11-09 2014-08-06 塔塔咨询服务有限公司 A system and method for enhancing human counting by fusing results of human detection modalities
CN105023005A (en) * 2015-08-05 2015-11-04 王丽婷 Face recognition apparatus and recognition method thereof
CN105069448A (en) * 2015-09-29 2015-11-18 厦门中控生物识别信息技术有限公司 True and false face identification method and device
CN105187727A (en) * 2015-06-17 2015-12-23 广州市巽腾信息科技有限公司 Image information acquisition device, image acquisition method and use of image information acquisition device
CN105187726A (en) * 2015-06-17 2015-12-23 广州市巽腾信息科技有限公司 Multifunctional mobile image processing device, processing method of utilizing multifunctional mobile image processing device, and use of multifunctional mobile image processing device
CN105654028A (en) * 2015-09-29 2016-06-08 厦门中控生物识别信息技术有限公司 True and false face identification method and apparatus thereof
CN105718925A (en) * 2016-04-14 2016-06-29 苏州优化智能科技有限公司 Real person living body authentication terminal equipment based on near infrared and facial micro expression
CN105844240A (en) * 2016-03-23 2016-08-10 深圳云天励飞技术有限公司 Method and device for detecting human faces in infrared temperature measurement system
CN105912908A (en) * 2016-04-14 2016-08-31 苏州优化智能科技有限公司 Infrared-based real person living body identity verification method
CN105930780A (en) * 2016-04-14 2016-09-07 苏州优化智能科技有限公司 Near infrared and micro expression based living body identity verification method
CN105938546A (en) * 2016-04-14 2016-09-14 苏州优化智能科技有限公司 Real living identity verification terminal equipment based on infrared technology
WO2017000116A1 (en) * 2015-06-29 2017-01-05 北京旷视科技有限公司 Living body detection method, living body detection system, and computer program product
CN106372601A (en) * 2016-08-31 2017-02-01 上海依图网络科技有限公司 In vivo detection method based on infrared visible binocular image and device
CN106372615A (en) * 2016-09-19 2017-02-01 厦门中控生物识别信息技术有限公司 Face anti-counterfeiting identification method and apparatus
WO2017070920A1 (en) 2015-10-30 2017-05-04 Microsoft Technology Licensing, Llc Spoofed face detection
CN106778607A (en) * 2016-12-15 2017-05-31 国政通科技股份有限公司 A kind of people based on recognition of face and identity card homogeneity authentication device and method
CN106951762A (en) * 2017-03-29 2017-07-14 中控智慧科技股份有限公司 A kind of personal identification method and system
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
CN107633198A (en) * 2017-07-25 2018-01-26 百度在线网络技术(北京)有限公司 Biopsy method, device, equipment and storage medium
CN107798279A (en) * 2016-09-07 2018-03-13 北京眼神科技有限公司 Face living body detection method and device
CN107918773A (en) * 2017-12-13 2018-04-17 汉王科技股份有限公司 A kind of human face in-vivo detection method, device and electronic equipment
US9996726B2 (en) 2013-08-02 2018-06-12 Qualcomm Incorporated Feature identification using an RGB-NIR camera pair
CN108363944A (en) * 2017-12-28 2018-08-03 杭州宇泛智能科技有限公司 Recognition of face terminal is double to take the photograph method for anti-counterfeit, apparatus and system
CN108491805A (en) * 2018-03-27 2018-09-04 百度在线网络技术(北京)有限公司 Identity identifying method and device
CN108629305A (en) * 2018-04-27 2018-10-09 朱旭辉 A kind of face recognition method
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
CN108959874A (en) * 2017-05-17 2018-12-07 武汉默联股份有限公司 Information Authentication method and device
CN108985134A (en) * 2017-06-01 2018-12-11 重庆中科云丛科技有限公司 Face In vivo detection and brush face method of commerce and system based on binocular camera
CN109002786A (en) * 2018-07-06 2018-12-14 深圳市富士智能系统有限公司 Method for detecting human face, equipment and computer readable storage medium
CN109284597A (en) * 2018-11-22 2019-01-29 北京旷视科技有限公司 A kind of face unlocking method, device, electronic equipment and computer-readable medium
CN109543640A (en) * 2018-11-29 2019-03-29 中国科学院重庆绿色智能技术研究院 A kind of biopsy method based on image conversion
CN109886240A (en) * 2019-03-01 2019-06-14 厦门狄耐克智能科技股份有限公司 A kind of building talkback gateway machine face identification mechanism
CN109977741A (en) * 2017-12-28 2019-07-05 北京京东尚科信息技术有限公司 Face identification method, device, system and medium
CN110008783A (en) * 2018-01-04 2019-07-12 杭州海康威视数字技术股份有限公司 Human face in-vivo detection method, device and electronic equipment based on neural network model
CN110069970A (en) * 2018-01-22 2019-07-30 三星电子株式会社 Activity test method and equipment
CN110309767A (en) * 2019-06-28 2019-10-08 广州致远电子有限公司 In vivo detection equipment, recognition methods, device and storage medium
WO2019200575A1 (en) * 2018-04-18 2019-10-24 深圳阜时科技有限公司 Identity authentication method, identity authentication device, and electronic apparatus
CN110874588A (en) * 2020-01-17 2020-03-10 南京甄视智能科技有限公司 Method and device for dynamically optimizing light influence in face recognition
JP2020195140A (en) * 2016-05-16 2020-12-03 キヤノン株式会社 Image processing apparatus, image processing method, and program
TWI722872B (en) * 2020-04-17 2021-03-21 技嘉科技股份有限公司 Face recognition device and face recognition method
CN113128481A (en) * 2021-05-19 2021-07-16 济南博观智能科技有限公司 Face living body detection method, device, equipment and storage medium

Families Citing this family (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE102013009474A1 (en) * 2013-06-06 2014-12-11 Modi Modular Digits Gmbh Apparatus for automatically verifying a person's identity document and method for generating identification data of a person for use in an automated identity control station

Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101196987A (en) * 2007-12-25 2008-06-11 哈尔滨工业大学 On-line palm print, palm vein image personal identification method and its special capturing instrument
CN101303724A (en) * 2007-05-10 2008-11-12 中国银联股份有限公司 Authentication authorization method and system
CN101404060A (en) * 2008-11-10 2009-04-08 北京航空航天大学 Human face recognition method based on visible light and near-infrared Gabor information amalgamation

Patent Citations (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101303724A (en) * 2007-05-10 2008-11-12 中国银联股份有限公司 Authentication authorization method and system
CN101196987A (en) * 2007-12-25 2008-06-11 哈尔滨工业大学 On-line palm print, palm vein image personal identification method and its special capturing instrument
CN101404060A (en) * 2008-11-10 2009-04-08 北京航空航天大学 Human face recognition method based on visible light and near-infrared Gabor information amalgamation

Cited By (66)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102831379B (en) * 2011-06-14 2015-11-25 汉王科技股份有限公司 facial image recognition method and device
CN102831379A (en) * 2011-06-14 2012-12-19 汉王科技股份有限公司 Face image recognition method and device
CN103975343A (en) * 2011-11-09 2014-08-06 塔塔咨询服务有限公司 A system and method for enhancing human counting by fusing results of human detection modalities
CN103975343B (en) * 2011-11-09 2018-06-01 塔塔咨询服务有限公司 For enhancing the system and method that the mankind count by merging the result of mankind's sensed-mode
WO2013131407A1 (en) * 2012-03-08 2013-09-12 无锡中科奥森科技有限公司 Double verification face anti-counterfeiting method and device
CN104364798B (en) * 2012-06-26 2019-04-02 高通股份有限公司 System and method for face verification
CN104364798A (en) * 2012-06-26 2015-02-18 高通股份有限公司 Systems and method for facial verification
US10452894B2 (en) 2012-06-26 2019-10-22 Qualcomm Incorporated Systems and method for facial verification
WO2014004179A1 (en) * 2012-06-26 2014-01-03 Qualcomm Incorporated Systems and method for facial verification
WO2014043003A1 (en) * 2012-09-12 2014-03-20 Google Inc. Method and device for authentication of live human faces using infra red images
WO2015003522A1 (en) * 2013-07-10 2015-01-15 小米科技有限责任公司 Face recognition method, apparatus, and mobile terminal
CN103400108B (en) * 2013-07-10 2017-07-14 小米科技有限责任公司 Face identification method, device and mobile terminal
CN103400108A (en) * 2013-07-10 2013-11-20 北京小米科技有限责任公司 Face identification method and device as well as mobile terminal
US9996726B2 (en) 2013-08-02 2018-06-12 Qualcomm Incorporated Feature identification using an RGB-NIR camera pair
CN105187726A (en) * 2015-06-17 2015-12-23 广州市巽腾信息科技有限公司 Multifunctional mobile image processing device, processing method of utilizing multifunctional mobile image processing device, and use of multifunctional mobile image processing device
CN105187727A (en) * 2015-06-17 2015-12-23 广州市巽腾信息科技有限公司 Image information acquisition device, image acquisition method and use of image information acquisition device
US10621454B2 (en) 2015-06-29 2020-04-14 Beijing Kuangshi Technology Co., Ltd. Living body detection method, living body detection system, and computer program product
WO2017000116A1 (en) * 2015-06-29 2017-01-05 北京旷视科技有限公司 Living body detection method, living body detection system, and computer program product
CN105023005B (en) * 2015-08-05 2018-12-07 王丽婷 Face identification device and its recognition methods
CN105023005A (en) * 2015-08-05 2015-11-04 王丽婷 Face recognition apparatus and recognition method thereof
CN105654028A (en) * 2015-09-29 2016-06-08 厦门中控生物识别信息技术有限公司 True and false face identification method and apparatus thereof
CN105069448A (en) * 2015-09-29 2015-11-18 厦门中控生物识别信息技术有限公司 True and false face identification method and device
CN107111750B (en) * 2015-10-30 2020-06-05 微软技术许可有限责任公司 Detection of deceptive faces
WO2017070920A1 (en) 2015-10-30 2017-05-04 Microsoft Technology Licensing, Llc Spoofed face detection
EP3369036A4 (en) * 2015-10-30 2019-05-22 Microsoft Technology Licensing, LLC Spoofed face detection
US10452935B2 (en) 2015-10-30 2019-10-22 Microsoft Technology Licensing, Llc Spoofed face detection
CN107111750A (en) * 2015-10-30 2017-08-29 微软技术许可有限责任公司 The detection of duplicity face
CN105844240A (en) * 2016-03-23 2016-08-10 深圳云天励飞技术有限公司 Method and device for detecting human faces in infrared temperature measurement system
CN105912908A (en) * 2016-04-14 2016-08-31 苏州优化智能科技有限公司 Infrared-based real person living body identity verification method
CN105718925A (en) * 2016-04-14 2016-06-29 苏州优化智能科技有限公司 Real person living body authentication terminal equipment based on near infrared and facial micro expression
CN105938546A (en) * 2016-04-14 2016-09-14 苏州优化智能科技有限公司 Real living identity verification terminal equipment based on infrared technology
CN105930780A (en) * 2016-04-14 2016-09-07 苏州优化智能科技有限公司 Near infrared and micro expression based living body identity verification method
JP2020195140A (en) * 2016-05-16 2020-12-03 キヤノン株式会社 Image processing apparatus, image processing method, and program
CN106372601A (en) * 2016-08-31 2017-02-01 上海依图网络科技有限公司 In vivo detection method based on infrared visible binocular image and device
CN107798279A (en) * 2016-09-07 2018-03-13 北京眼神科技有限公司 Face living body detection method and device
CN107798279B (en) * 2016-09-07 2022-01-25 北京眼神科技有限公司 Face living body detection method and device
CN106372615A (en) * 2016-09-19 2017-02-01 厦门中控生物识别信息技术有限公司 Face anti-counterfeiting identification method and apparatus
CN106778607A (en) * 2016-12-15 2017-05-31 国政通科技股份有限公司 A kind of people based on recognition of face and identity card homogeneity authentication device and method
CN106951762A (en) * 2017-03-29 2017-07-14 中控智慧科技股份有限公司 A kind of personal identification method and system
CN108959874A (en) * 2017-05-17 2018-12-07 武汉默联股份有限公司 Information Authentication method and device
CN108985134A (en) * 2017-06-01 2018-12-11 重庆中科云丛科技有限公司 Face In vivo detection and brush face method of commerce and system based on binocular camera
CN107633198A (en) * 2017-07-25 2018-01-26 百度在线网络技术(北京)有限公司 Biopsy method, device, equipment and storage medium
US10699103B2 (en) 2017-07-26 2020-06-30 Baidu Online Network Technology (Beijing) Co., Ltd. Living body detecting method and apparatus, device and storage medium
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
CN107918773A (en) * 2017-12-13 2018-04-17 汉王科技股份有限公司 A kind of human face in-vivo detection method, device and electronic equipment
CN108363944A (en) * 2017-12-28 2018-08-03 杭州宇泛智能科技有限公司 Recognition of face terminal is double to take the photograph method for anti-counterfeit, apparatus and system
CN109977741A (en) * 2017-12-28 2019-07-05 北京京东尚科信息技术有限公司 Face identification method, device, system and medium
US11321963B2 (en) 2018-01-04 2022-05-03 Hangzhou Hikvision Digital Technology Co., Ltd. Face liveness detection based on neural network model
CN110008783A (en) * 2018-01-04 2019-07-12 杭州海康威视数字技术股份有限公司 Human face in-vivo detection method, device and electronic equipment based on neural network model
CN110069970A (en) * 2018-01-22 2019-07-30 三星电子株式会社 Activity test method and equipment
CN108491805A (en) * 2018-03-27 2018-09-04 百度在线网络技术(北京)有限公司 Identity identifying method and device
CN108491805B (en) * 2018-03-27 2022-02-22 百度在线网络技术(北京)有限公司 Identity authentication method and device
WO2019200575A1 (en) * 2018-04-18 2019-10-24 深圳阜时科技有限公司 Identity authentication method, identity authentication device, and electronic apparatus
CN108629305A (en) * 2018-04-27 2018-10-09 朱旭辉 A kind of face recognition method
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
CN109002786A (en) * 2018-07-06 2018-12-14 深圳市富士智能系统有限公司 Method for detecting human face, equipment and computer readable storage medium
CN109002786B (en) * 2018-07-06 2022-02-18 深圳市富士智能系统有限公司 Face detection method, face detection equipment and computer-readable storage medium
CN109284597A (en) * 2018-11-22 2019-01-29 北京旷视科技有限公司 A kind of face unlocking method, device, electronic equipment and computer-readable medium
CN109543640A (en) * 2018-11-29 2019-03-29 中国科学院重庆绿色智能技术研究院 A kind of biopsy method based on image conversion
CN109543640B (en) * 2018-11-29 2022-06-17 中国科学院重庆绿色智能技术研究院 Living body detection method based on image conversion
CN109886240A (en) * 2019-03-01 2019-06-14 厦门狄耐克智能科技股份有限公司 A kind of building talkback gateway machine face identification mechanism
CN110309767A (en) * 2019-06-28 2019-10-08 广州致远电子有限公司 In vivo detection equipment, recognition methods, device and storage medium
CN110874588A (en) * 2020-01-17 2020-03-10 南京甄视智能科技有限公司 Method and device for dynamically optimizing light influence in face recognition
TWI722872B (en) * 2020-04-17 2021-03-21 技嘉科技股份有限公司 Face recognition device and face recognition method
US11417149B2 (en) 2020-04-17 2022-08-16 Giga-Byte Technology Co., Ltd. Face recognition device and face recognition method
CN113128481A (en) * 2021-05-19 2021-07-16 济南博观智能科技有限公司 Face living body detection method, device, equipment and storage medium

Also Published As

Publication number Publication date
CN101964056B (en) 2012-06-27

Similar Documents

Publication Publication Date Title
CN101964056B (en) Bimodal face authentication method with living body detection function and system
CN106204815B (en) A kind of access control system based on human face detection and recognition
CN103841108B (en) The authentication method and system of user biological feature
CN102622588B (en) Dual-certification face anti-counterfeit method and device
WO2019080579A1 (en) 3d face identity authentication method and apparatus
US8422746B2 (en) Face authentication system and authentication method thereof
CN101587485B (en) Face information automatic login method based on face recognition technology
CN104348778A (en) Remote identity authentication system, terminal and method carrying out initial face identification at handset terminal
CN108985134A (en) Face In vivo detection and brush face method of commerce and system based on binocular camera
CN105427421A (en) Entrance guard control method based on face recognition
CN104881632A (en) Hyperspectral face recognition method
CN107688775A (en) Binocular camera recognition of face right discriminating system and method based on elevator scene
CN103530659B (en) With reference to the face identification method and attendance checking system of original and symmetrical face facial image
CN103559485A (en) Identity authentication method and device based on remote bank VTM
CN103279764A (en) Real-name network authentication system based on face identification
CN201845343U (en) Image acquisition device for human face recognition
CN105975938A (en) Smart community manager service system with dynamic face identification function
CN103324911A (en) Anti-cheating system based on face recognition
CN107609515B (en) Double-verification face comparison system and method based on Feiteng platform
CN201867835U (en) System combining fingerprint identification with near-infrared face identification
CN106603569A (en) Multimodal biometric feature fusion social insurance identity authentication system and method
CN111104859A (en) Authentication method and system based on multispectral identification
CN109754504A (en) A kind of intelligent access control system
CN111445640A (en) Express delivery pickup method, device, equipment and storage medium based on iris recognition
CN105184571A (en) Payment authentication system based on combination of hand veins and multiple fingerprints

Legal Events

Date Code Title Description
C06 Publication
PB01 Publication
C10 Entry into substantive examination
SE01 Entry into force of request for substantive examination
C14 Grant of patent or utility model
GR01 Patent grant
TR01 Transfer of patent right

Effective date of registration: 20200331

Address after: Room 704, building C1, Lugu Yuyuan, No. 27, Wenxuan Road, Changsha hi tech Development Zone, Changsha City, Hunan Province

Patentee after: Hunan Weilian Intelligent Technology Co., Ltd

Address before: 518000 building C, Innovation Research Institute, Nanshan District hi tech Zone, Guangdong, Shenzhen 1-6

Patentee before: Xu Yong

TR01 Transfer of patent right