CN101771539A - Face recognition based method for authenticating identity - Google Patents
Face recognition based method for authenticating identity Download PDFInfo
- Publication number
- CN101771539A CN101771539A CN200810246722A CN200810246722A CN101771539A CN 101771539 A CN101771539 A CN 101771539A CN 200810246722 A CN200810246722 A CN 200810246722A CN 200810246722 A CN200810246722 A CN 200810246722A CN 101771539 A CN101771539 A CN 101771539A
- Authority
- CN
- China
- Prior art keywords
- recognition
- face
- recognition feature
- people
- verified
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 46
- 238000010422 painting Methods 0.000 claims abstract description 51
- 239000000284 extract Substances 0.000 claims abstract description 13
- 230000001815 facial effect Effects 0.000 claims description 31
- 238000004364 calculation method Methods 0.000 claims description 7
- 238000012545 processing Methods 0.000 claims description 6
- 238000004891 communication Methods 0.000 abstract description 2
- 238000012795 verification Methods 0.000 description 9
- 210000004709 eyebrow Anatomy 0.000 description 7
- 238000000605 extraction Methods 0.000 description 3
- VYMDGNCVAMGZFE-UHFFFAOYSA-N phenylbutazonum Chemical compound O=C1C(CCCC)C(=O)N(C=2C=CC=CC=2)N1C1=CC=CC=C1 VYMDGNCVAMGZFE-UHFFFAOYSA-N 0.000 description 3
- 230000008878 coupling Effects 0.000 description 2
- 238000010168 coupling process Methods 0.000 description 2
- 238000005859 coupling reaction Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 238000013475 authorization Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 239000012141 concentrate Substances 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000008676 import Effects 0.000 description 1
- 230000013011 mating Effects 0.000 description 1
- 230000002093 peripheral effect Effects 0.000 description 1
- 238000009394 selective breeding Methods 0.000 description 1
Images
Landscapes
- Collating Specific Patterns (AREA)
Abstract
The invention relates to a face recognition based method for authenticating identity. In the method, recognition characteristic data and a corresponding recognition characteristic region are extracted through face recognition; a drawn portrait painting is generated by a face image; an authenticated person is prompted to adjust the distance and angle with an image acquisition device by the portrait painting when the face image is acquired; when the acquired image is aligned with the portrait painting, a terminal extracts the recognition characteristic region and calculates the recognition characteristic data; and the recognition characteristic data are associated with the saved corresponding recognition characteristic data to authenticate user identity. The method can greatly reduce the calculated amount and the data communication amount of face recognition, and is particularly applicable to identity authentication application of mobile terminal equipment.
Description
Technical field
The invention belongs to information security field, be specifically related to a kind of identity identifying method based on recognition of face.
Background technology
Recognition of face is as a kind of common identity identifying method, and is low to the requirement of equipment peripheral hardware because it only need be equipped with camera, thereby is widely used in multiple authentication occasion.But recognition of face depends on complex image identification and image processing, its operand is often huge, for the equipment requirements height that identification is calculated, its application is subjected to certain limitation, for example can not use on the mobile terminal devices such as PDA that computing capability is limited, the communication data amount is restricted.
Be 200610117905.2 Chinese patent application as application number--have the network login system and the login method of face authentication, this method at first stores the characteristic information that comprises people's face information that the user is submitted to when network system is registered, landing approach by its selection carries out the corresponding landing checking when the user lands described network system once more then, for example, when selecting confirming face to land, the user then gathers people's face information of described user in real time, and people's face information of submitting to when this information and user registered compares to verify, so can confirm the network user's true identity, avoid the losing of stolen and user identity of user cipher.The weak point of this method is that face authentication image transmitted data volume is big, and the operand that recognition of face is calculated is also very big, thereby higher to the performance requirement of treatment facility.
Application number is 200610117142.1 Chinese patent application a--sectorization type human face recognition method for another example, this method is built the face characteristic database that comprises one or more each provincial characteristics data of people's face at first in advance, then people's face to be identified is carried out subregion, and extraction each regional characteristic of people's face behind subregion, set the zone that to compare again, follow the similarity of comparing the corresponding data in corresponding provincial characteristics data and the described face characteristic database and calculate people's face of people's face to be identified and described face characteristic database in the zone of comparing according to the needs that set, with identification people face.The deficiency of this method is uncontrollable people's face angle and size when IMAQ, need handle and correct people's face information of gathering, and has so just improved amount of calculation and intractability.
Along with the extensive use of portable terminal, portable terminal needs that a kind of operand is little, the transmitted data on network amount is little, do not need specific optional equipment to using user's identification authentication mode.
Summary of the invention
The object of the present invention is to provide a kind of volume of transmitted data and all less identity identifying method of identification amount of calculation, mainly satisfy the authentication related application of the recognition of face on mobile terminal device based on recognition of face.
In order to realize the foregoing invention purpose, the technical solution used in the present invention is: a kind of identity identifying method based on recognition of face comprises the steps:
(1) obtains the facial image that is verified the people by image collecting device, generate the portrait painting of a correspondence, calculate recognition feature zone and corresponding recognition feature data by face recognition algorithms then;
Select to be verified people's portrait painting when (2) discerning according to the logon information that is verified the people, and corresponding recognition feature zone and corresponding recognition feature data;
(3) be verified the portrait painting position indicating of people by the video acquisition interface that is added to, the distance and the angle of adjustment and image collecting device, when images acquired was alignd with portrait painting, terminal was extracted in the facial image in the recognition feature zone;
(4) facial image in the recognition feature zone of extracting is recomputated the recognition feature data, the recognition feature data corresponding with this recognition feature zone of calculating in the step (1) are mated, and as the match is successful, think that then the current people's of being verified identity is legal; Otherwise think that the current people's of being verified identity is illegal.
Further, aforesaid identity identifying method based on recognition of face, the portrait painting that generates in step (1) is drawn by the monochromatic and transparent simple, straight-forward style of writing portrait of forming, be used to point out and be verified the people and adjust distance and angle with image collecting device in when identification, and with recognition feature zone relative positioning, to reduce the operand of characteristics of image identification.
Further, aforesaid identity identifying method based on recognition of face, be meant the significant image-region of identification characteristics that calculates by the face recognition algorithms of selecting for use in the recognition feature zone described in the step (1), area size is less than facial image, the position is within the portrait painting scope, described identification characteristics is meant significantly according to selected face recognition algorithms proportional numerical value is set that this numerical value guarantees that the feature identification accuracy surpasses the threshold values of setting; Described recognition feature data are meant the data description of the recognition feature that image calculation in the recognition feature zone is gone out according to the face recognition algorithms selected for use.
Further, aforesaid identity identifying method based on recognition of face, a portrait painting adds more than one recognition feature zone is arranged in the step (1), can adopt more than one face recognition algorithms on each recognition feature zone, the corresponding recognition feature data of each face recognition algorithms.
Further again, aforesaid identity identifying method based on recognition of face, the size and the position in the recognition feature zone described in the step (1) are determined according to the face recognition algorithms that is adopted.
Further, aforesaid identity identifying method based on recognition of face, portrait painting is positioned at the front of video acquisition image in step (3), is used to point out be verified distance and the angle that the people regulates its face and video acquisition camera.
Further, aforesaid identity identifying method based on recognition of face under the facial image of terminal equipment video acquisition and condition that portrait painting overlaps substantially, extracts the facial image in the recognition feature zone in the step (3).
Further again, aforesaid identity identifying method based on recognition of face, the facial image of terminal equipment video acquisition overlaps substantially by being verified the people with portrait painting and adjusts in the step (3), terminal equipment does not make a decision, do not guarantee the effectively overlapping of image if be verified the people, then follow-up recognition feature extracted region and recognition feature data generate and will cause being verified people's authentication failure.
Further, aforesaid identity identifying method based on recognition of face, in step (4), the facial image in the recognition feature zone of extracting is recomputated the recognition feature data by face recognition algorithms, this processing procedure is to handle in terminal this locality, or handles at server end; Handle if be chosen in terminal this locality, then will be verified people's portrait painting in the step (2), and the recognition feature data of corresponding recognition feature zone and correspondence send to terminal equipment; Handle if be chosen in server end, then only will be verified people's portrait painting in the step (2), and corresponding recognition feature zone sends to terminal equipment.
Further, aforesaid identity identifying method based on recognition of face, the algorithm during the middle recognition feature data extract of the face recognition algorithms that adopts at picture in the recognition feature zone in the step (4) and step (1) is consistent.
Effect of the present invention is: because a lot of recognition of face characteristic distribution density difference, generally concentrate near density height such as canthus, the corners of the mouth, nose, ear, for the different characteristic zone, the characteristic remarkable of the result of calculation of different face recognition algorithms also there are differences.Technical scheme provided by the present invention is by characteristic areaization, in the characteristic area that facial image is littler relatively, can better calculate recognition feature, and be verified the people by the prompting of monochromatic portrait painting and adjust distance and angle with the IMAQ terminal voluntarily, when further reducing amount of calculation, can accurately extract the image in the recognition feature zone of portrait painting location association, reduce the operand of characteristics of image identification significantly.This method is simple to operate, has reduced the amount of calculation of recognition of face significantly, and processing speed is fast, terminal equipment is required low, is specially adapted to identity on the terminal such as PDA and differentiates and use.
Description of drawings
Fig. 1 is the flow chart of a kind of recognition of face checking feature extraction in the embodiment of the invention;
Fig. 2 is the flow chart of a kind of recognition of face authentication in the embodiment of the invention;
Fig. 3 is the facial image of gathering in the embodiment of the invention;
Fig. 4 is the portrait painting that generates in the embodiment of the invention;
Fig. 5 is characteristic area and the portrait painting location schematic diagram of the portrait painting A of the facial image that obtains in the embodiment of the invention;
The schematic diagram that portrait painting that Fig. 6 is in the embodiment of the invention to be obtained and facial image are complementary.
Embodiment
The invention will be further described below in conjunction with the drawings and specific embodiments.
A kind of identity identifying method based on recognition of face mainly comprises two parts: whether promptly at the recognition of face checking feature extraction that is verified the people, and it is legal to use the characteristic checking of extracting to be landed people's identity.
As shown in Figure 1, a kind of based on the checking of the recognition of face in the authentication of recognition of face feature extracting method, may further comprise the steps:
F11: obtain the facial image that is verified the people by the video acquisition terminal.
Concrete implementation step is: at first input is verified people's information, so that can index corresponding authorization information.The facial image that obtains from video capture device, video equipment are the present video equipment that everybody is used always, as it is first-class to make a video recording.Can be one group of multi-angle images, each image can be according to the mode circular treatment of this method explanation.
F12: generate corresponding portrait painting.Generate the algorithm of portrait painting by facial image, by existing techniques in realizing, typical method has portrait painting generating algorithm based on feature, based on the portrait painting generating algorithm of sample learning etc.
F13: select face recognition algorithms of the prior art, can set a plurality of recognizer circular treatment.In the prior art there being typical face recognition algorithms: the face recognition algorithms that merges mutually based on the face recognition algorithms of PCA and ICA, based on SVD and KL projection, keeps the DT-CWT feature face recognition algorithms of throwing etc. based on the quadrature neighborhood, different face recognition algorithms exist advantage and limitation separately, and the technical staff can choose as required voluntarily.
F14: according to the face recognition algorithms of select using, will characteristic value at facial image after, according to numerical point position distribution situation (mainly referring to distribution density and intensity), extract characteristic area according to the threshold values of setting.
In the present embodiment, as choose the DT-CWT feature face recognition algorithms that keeps projection based on the quadrature neighborhood, the DT-CWT character numerical value that facial image is calculated, project on the zone of 0-100, setting threshold values is 70, and density is not less than 9 pixels, connects area and is not less than 200 pixels, region shape is minimum boundary rectangle, then 6 characteristic areas that satisfy condition of Ti Quing S21 left side eyebrow district, the right eyebrow of S22 district, S23 right eye district, S24 left eye district, S25 nose portion, S26 mouth shape district as shown in Figure 5.
F15: whether satisfy in the checking recognition feature zone and set requirement.In the present embodiment, the recognition feature zone that setting satisfies condition, carrying out face recognition algorithms in the recognition feature zone once more handles, its recognition feature density is between 30-80, and the length in zone and width all between 20pt-200pt, think that then this recognition feature zone recognition feature data inner with it are effective.
F16: recognition feature zone is related with correspondence position on the portrait painting, and relevant information is kept at portrait painting, so that subsequent authentication is called.
The verification msg that comprises portrait painting, recognition feature zone, forms at the face recognition algorithms and the recognition feature data of recognition feature intra-zone that generates in the step F 15, wherein the recognition feature zone can be determined by a kind of face recognition algorithms, the recognition feature data that it is inner, determine to select face recognition algorithms to calculate once more behind the recognition feature zone, that is to say that a recognition feature zone can related a plurality of face recognition algorithms, each face recognition algorithms correspondence calculates recognition feature data.
In present embodiment, calculate 6 effective recognition characteristic areas, but in the practice process, can select only to use the subregion.In the present embodiment, eyebrow district, a S21 left side, S25 nose portion, 3 recognition feature zones, S26 mouth shape district are only used in artificial selection, promptly generate portrait painting that verification msg comprises 1,3 recognition feature zones, at the face recognition algorithms DT-CWT title of each recognition feature intra-zone, and the verification msg (being expressed as feature A respectively, feature B and feature C) of corresponding recognition feature data composition.
If above-mentioned steps is obtained a plurality of facial images, then circular treatment from video capture device.Present embodiment has only been gathered an image.Be verified people's portrait painting, and corresponding recognition feature zone and corresponding recognition feature data can be kept on server end or the portable terminal, will be verified people's portrait painting, corresponding recognition feature zone and corresponding recognition feature storage in the present embodiment at server end.
The verification msg of using above-mentioned generation is described below, to being verified the handling process that people's identity is differentiated: as shown in Fig. 2:
S11: be verified the people and on portable terminal PDA, import user's name, this user profile is submitted on the server, whois lookup is to being verified people's verification msg, this verification msg generally comprises portrait painting and recognition feature area information, if directly verify calculating on terminal equipment, then verification msg also comprises corresponding face recognition algorithms in recognition feature zone and the recognition feature data that calculate.
Download to the verification msg of terminal in the present embodiment, portrait painting as shown in Figure 5, and only S21 left side eyebrow district, S25 nose portion, 3 recognition feature zones, S26 mouth shape district, with employing face recognition algorithms DT-CWT title, and the recognition feature data that calculate are formed, recognition feature data at eyebrow district, a S21 left side, S25 nose portion, S26 mouth shape district are expressed as feature A here respectively, feature B and feature C.
S12: portrait painting is shown on the video capture device of terminal, adjust voluntarily and the distance of video capture device, angle etc., make and gather facial image and overlap with portrait painting substantially in order to the prompting user.As shown in Fig. 6.
Here portrait is depicted as monochromatic and transparent composition, and portrait painting is presented at the front end of video acquisition image on portable terminal, can watch the situation of video acquisition image by transparent part.Here the portrait painting monochrome can be provided with, and the typical case can switched between shades of colours such as hiding, white, black, grey on the mobile phone.
S13: with portrait painting coupling, extract the zone according to recognition feature, extract with the portrait painting position on facial image in the characteristic area of locating, and the facial image in the characteristic area that extracts recomputated the recognition feature data.
Present embodiment only extracts eyebrow district, a S21 left side, S25 nose portion, 3 recognition feature zones, S26 mouth shape district.
In this step, carry out on server if image recognition is calculated, the image uploading that then needs to extract is carried out the S14 step process by server to server; Carry out on terminal if image recognition is calculated, then comprise face recognition algorithms DT-CWT title in the verification msg that need in step S11, download at each recognition feature intra-zone, and corresponding recognition feature data.
Recomputating the processing of recognition feature data, can also can be in server-side processes in the local processing of terminal.And must be in full accord with the algorithm of recognition feature data extract among the step S11 at the face recognition algorithms that picture in the characteristic area adopts.Earlier pass through face recognition algorithms in the present embodiment at facial image, to eyebrow district, a S21 left side, S25 nose portion, 3 recognition feature zones, S26 mouth shape district, adopt the DT-CWT feature face recognition algorithms that keeps projection based on the quadrature neighborhood respectively, calculate it and be feature A ', feature B ' and feature C '.
S14: mate with source recognition feature data.
The recognition feature data that this step specifically recomputates by face recognition algorithms the facial image in the characteristic area that extracts, with the corresponding recognition feature Data Matching of this characteristic area that is stored in the server, promptly with step F 15 in the feature A, the feature B that calculate and the numerical value of feature C mate, if numerical value is in range of tolerable variance, then think and mate, promptly the Dui Ying people's identity that is verified is legal, otherwise thinks that then to be verified people's identity illegal.
Tolerance in the above-mentioned steps is meant the condition that satisfies following setting that comprises: the coupling number of 1) mating the recognition feature data in recognition feature zone at least; 2) recognition feature Data Matching, promptly the difference of two recognition feature data in the scope of setting, usually this scope be set at two recognition feature numerical standard differences 8% in, perhaps directly specify the size of its scope.
Consider the description of this invention disclosed herein and special embodiment, other embodiment of the present invention are conspicuous for a person skilled in the art.These explanations and embodiment only consider as an example that they all belong to by within the indicated protection scope of the present invention and spirit of claims.
Claims (10)
1. the identity identifying method based on recognition of face comprises the steps:
(1) obtains the facial image that is verified the people by image collecting device, generate the portrait painting of a correspondence, calculate recognition feature zone and corresponding recognition feature data by face recognition algorithms then;
Select to be verified people's portrait painting when (2) discerning according to the logon information that is verified the people, and corresponding recognition feature zone and corresponding recognition feature data;
(3) be verified the portrait painting position indicating of people by the video acquisition interface that is added to, the distance and the angle of adjustment and image collecting device, when images acquired was alignd with portrait painting, terminal was extracted in the facial image in the recognition feature zone;
(4) facial image in the recognition feature zone of extracting is recomputated the recognition feature data, the recognition feature data corresponding with this recognition feature zone of calculating in the step (1) are mated, and as the match is successful, think that then the current people's of being verified identity is legal; Otherwise think that the current people's of being verified identity is illegal.
2. the identity identifying method based on recognition of face as claimed in claim 1, it is characterized in that: the portrait painting that generates in step (1) is drawn by the monochromatic and transparent simple, straight-forward style of writing portrait of forming, be used to point out and be verified the people and adjust distance and angle with image collecting device in when identification, and with recognition feature zone relative positioning, to reduce the operand of characteristics of image identification.
3. the identity identifying method based on recognition of face as claimed in claim 1 or 2, it is characterized in that: be meant the significant image-region of identification characteristics that calculates by the face recognition algorithms of selecting for use in the recognition feature zone described in the step (1), area size is less than facial image, the position is within the portrait painting scope, described identification characteristics is meant significantly according to selected face recognition algorithms proportional numerical value is set that this numerical value guarantees that the feature identification accuracy surpasses the threshold values of setting; Described recognition feature data are meant the data description of the recognition feature that image calculation in the recognition feature zone is gone out according to the face recognition algorithms selected for use.
4. the identity identifying method based on recognition of face as claimed in claim 3, it is characterized in that: a portrait painting adds more than one recognition feature zone is arranged in the step (1), can adopt more than one face recognition algorithms on each recognition feature zone, the corresponding recognition feature data of each face recognition algorithms.
5. the identity identifying method based on recognition of face as claimed in claim 4 is characterized in that: the size and the position in the recognition feature zone described in the step (1), determine according to the face recognition algorithms that is adopted.
6. the identity identifying method based on recognition of face as claimed in claim 1 is characterized in that: portrait painting is positioned at the front of video acquisition image in step (3), is used to point out be verified distance and the angle that the people regulates its face and video acquisition camera.
7. as claim 1 or 6 described identity identifying methods, it is characterized in that: under the facial image of terminal equipment video acquisition and condition that portrait painting overlaps substantially, extract the facial image in the recognition feature zone in the step (3) based on recognition of face.
8. the identity identifying method based on recognition of face as claimed in claim 7, it is characterized in that: the facial image of terminal equipment video acquisition overlaps substantially by being verified the people with portrait painting and adjusts in the step (3), terminal equipment does not make a decision, do not guarantee the effectively overlapping of image if be verified the people, then follow-up recognition feature extracted region and recognition feature data generate and will cause being verified people's authentication failure.
9. the identity identifying method based on recognition of face as claimed in claim 1, it is characterized in that: in step (4), the facial image in the recognition feature zone of extracting is recomputated the recognition feature data by face recognition algorithms, this processing procedure is to handle in terminal this locality, or handles at server end; Handle if be chosen in terminal this locality, then will be verified people's portrait painting in the step (2), and the recognition feature data of corresponding recognition feature zone and correspondence send to terminal equipment; Handle if be chosen in server end, then only will be verified people's portrait painting in the step (2), and corresponding recognition feature zone sends to terminal equipment.
10. as claim 1 or 9 described identity identifying methods based on recognition of face, it is characterized in that: the algorithm during the middle recognition feature data extract of the face recognition algorithms that adopts at picture in the recognition feature zone in the step (4) and step (1) is consistent.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200810246722XA CN101771539B (en) | 2008-12-30 | 2008-12-30 | Face recognition based method for authenticating identity |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN200810246722XA CN101771539B (en) | 2008-12-30 | 2008-12-30 | Face recognition based method for authenticating identity |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN101771539A true CN101771539A (en) | 2010-07-07 |
| CN101771539B CN101771539B (en) | 2012-07-04 |
Family
ID=42504160
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN200810246722XA Expired - Fee Related CN101771539B (en) | 2008-12-30 | 2008-12-30 | Face recognition based method for authenticating identity |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN101771539B (en) |
Cited By (23)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102096806A (en) * | 2010-12-29 | 2011-06-15 | 上海华勤通讯技术有限公司 | Face identification security mobile phone and implementation method thereof |
| CN102254164A (en) * | 2011-08-04 | 2011-11-23 | 蔡翔 | Face recognition method with prompt function |
| WO2012139269A1 (en) * | 2011-04-11 | 2012-10-18 | Intel Corporation | Tracking and recognition of faces using selected region classification |
| CN103218609A (en) * | 2013-04-25 | 2013-07-24 | 中国科学院自动化研究所 | Multi-pose face recognition method based on hidden least square regression and device thereof |
| CN103473494A (en) * | 2013-09-03 | 2013-12-25 | 小米科技有限责任公司 | Application running method, device and terminal device |
| CN103646201A (en) * | 2013-12-09 | 2014-03-19 | 东南大学 | Verification method achieved by combining human faces with identities |
| CN104143086A (en) * | 2014-07-18 | 2014-11-12 | 吴建忠 | Application technology of portrait comparison to mobile terminal operating system |
| CN104408354A (en) * | 2014-11-26 | 2015-03-11 | 成都市锐信安信息安全技术有限公司 | Stand-alone facial recognition smart power grid mobile operation and security access main switching circuit |
| CN105100108A (en) * | 2015-08-18 | 2015-11-25 | 赛肯(北京)科技有限公司 | Login authentication method, device and system based on face identification |
| CN105184133A (en) * | 2015-07-30 | 2015-12-23 | 广东欧珀移动通信有限公司 | Authentication method and apparatus, and corresponding mobile terminal |
| CN105760817A (en) * | 2016-01-28 | 2016-07-13 | 深圳泰首智能技术有限公司 | Method and device for recognizing, authenticating, unlocking and encrypting storage space by using human face |
| CN106022313A (en) * | 2016-06-16 | 2016-10-12 | 湖南文理学院 | Scene-automatically adaptable face recognition method |
| CN107423687A (en) * | 2017-06-15 | 2017-12-01 | 易联众信息技术股份有限公司 | A kind of identity identifying method and device based on face recognition technology |
| CN108171202A (en) * | 2018-01-17 | 2018-06-15 | 深圳市爱克信智能股份有限公司 | A kind of face recognition algorithms |
| CN108388842A (en) * | 2018-01-31 | 2018-08-10 | 广东欧珀移动通信有限公司 | Intelligent prompt method and Related product |
| CN108549848A (en) * | 2018-03-27 | 2018-09-18 | 百度在线网络技术（北京）有限公司 | Method and apparatus for output information |
| CN108700468A (en) * | 2017-09-29 | 2018-10-23 | 深圳市大疆创新科技有限公司 | Method for checking object, object detection terminal and computer-readable medium |
| CN109951437A (en) * | 2019-01-14 | 2019-06-28 | 平安科技（深圳）有限公司 | Safety certifying method, device and server based on recognition of face |
| CN110852150A (en) * | 2019-09-25 | 2020-02-28 | 珠海格力电器股份有限公司 | Face verification method, system, equipment and computer readable storage medium |
| WO2020041971A1 (en) * | 2018-08-28 | 2020-03-05 | 华为技术有限公司 | Face recognition method and apparatus |
| CN111182167A (en) * | 2019-11-25 | 2020-05-19 | 广东小天才科技有限公司 | File scanning method, electronic equipment and storage medium |
| CN112504628A (en) * | 2020-11-23 | 2021-03-16 | 江苏科技大学 | Ship model test pool wave making machine control system and method based on face recognition |
| CN112738067A (en) * | 2020-12-25 | 2021-04-30 | 中国农业银行股份有限公司 | Face recognition method, device and equipment |
Family Cites Families (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101089874B (en) * | 2006-06-12 | 2010-08-18 | 华为技术有限公司 | Identify recognizing method for remote human face image |
| JP2007334623A (en) * | 2006-06-15 | 2007-12-27 | Toshiba Corp | Face authentication device, face authentication method, and access control device |
| KR100899804B1 (en) * | 2007-05-11 | 2009-05-28 | 포항공과대학교 산학협력단 | Method for recognizing face using two-dimensional canonical correlation analysis |
-
2008
- 2008-12-30 CN CN200810246722XA patent/CN101771539B/en not_active Expired - Fee Related
Cited By (34)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102096806A (en) * | 2010-12-29 | 2011-06-15 | 上海华勤通讯技术有限公司 | Face identification security mobile phone and implementation method thereof |
| WO2012139269A1 (en) * | 2011-04-11 | 2012-10-18 | Intel Corporation | Tracking and recognition of faces using selected region classification |
| US9489567B2 (en) | 2011-04-11 | 2016-11-08 | Intel Corporation | Tracking and recognition of faces using selected region classification |
| CN102254164A (en) * | 2011-08-04 | 2011-11-23 | 蔡翔 | Face recognition method with prompt function |
| CN102254164B (en) * | 2011-08-04 | 2013-05-01 | 蔡翔 | Face recognition method with prompt function |
| CN103218609A (en) * | 2013-04-25 | 2013-07-24 | 中国科学院自动化研究所 | Multi-pose face recognition method based on hidden least square regression and device thereof |
| CN103218609B (en) * | 2013-04-25 | 2016-01-20 | 中国科学院自动化研究所 | A kind of Pose-varied face recognition method based on hidden least square regression and device thereof |
| CN103473494A (en) * | 2013-09-03 | 2013-12-25 | 小米科技有限责任公司 | Application running method, device and terminal device |
| CN103473494B (en) * | 2013-09-03 | 2016-08-17 | 小米科技有限责任公司 | A kind of run the method for application, device and terminal unit |
| CN103646201A (en) * | 2013-12-09 | 2014-03-19 | 东南大学 | Verification method achieved by combining human faces with identities |
| CN104143086A (en) * | 2014-07-18 | 2014-11-12 | 吴建忠 | Application technology of portrait comparison to mobile terminal operating system |
| CN104408354B (en) * | 2014-11-26 | 2018-01-19 | 成都市锐信安信息安全技术有限公司 | Free-standing face recognition intelligent grid movement job safety access total switch circuit |
| CN104408354A (en) * | 2014-11-26 | 2015-03-11 | 成都市锐信安信息安全技术有限公司 | Stand-alone facial recognition smart power grid mobile operation and security access main switching circuit |
| CN105184133B (en) * | 2015-07-30 | 2017-11-10 | 广东欧珀移动通信有限公司 | A kind of method for authenticating, device and corresponding mobile terminal |
| CN105184133A (en) * | 2015-07-30 | 2015-12-23 | 广东欧珀移动通信有限公司 | Authentication method and apparatus, and corresponding mobile terminal |
| CN105100108A (en) * | 2015-08-18 | 2015-11-25 | 赛肯(北京)科技有限公司 | Login authentication method, device and system based on face identification |
| CN105100108B (en) * | 2015-08-18 | 2018-04-13 | 广州密码科技有限公司 | A kind of login authentication method based on recognition of face, apparatus and system |
| CN105760817A (en) * | 2016-01-28 | 2016-07-13 | 深圳泰首智能技术有限公司 | Method and device for recognizing, authenticating, unlocking and encrypting storage space by using human face |
| CN106022313A (en) * | 2016-06-16 | 2016-10-12 | 湖南文理学院 | Scene-automatically adaptable face recognition method |
| CN107423687A (en) * | 2017-06-15 | 2017-12-01 | 易联众信息技术股份有限公司 | A kind of identity identifying method and device based on face recognition technology |
| CN108700468A (en) * | 2017-09-29 | 2018-10-23 | 深圳市大疆创新科技有限公司 | Method for checking object, object detection terminal and computer-readable medium |
| CN108171202A (en) * | 2018-01-17 | 2018-06-15 | 深圳市爱克信智能股份有限公司 | A kind of face recognition algorithms |
| CN108388842A (en) * | 2018-01-31 | 2018-08-10 | 广东欧珀移动通信有限公司 | Intelligent prompt method and Related product |
| CN108388842B (en) * | 2018-01-31 | 2019-07-23 | Oppo广东移动通信有限公司 | Intelligent prompt method and Related product |
| CN108549848A (en) * | 2018-03-27 | 2018-09-18 | 百度在线网络技术（北京）有限公司 | Method and apparatus for output information |
| WO2020041971A1 (en) * | 2018-08-28 | 2020-03-05 | 华为技术有限公司 | Face recognition method and apparatus |
| CN109951437A (en) * | 2019-01-14 | 2019-06-28 | 平安科技（深圳）有限公司 | Safety certifying method, device and server based on recognition of face |
| CN110852150A (en) * | 2019-09-25 | 2020-02-28 | 珠海格力电器股份有限公司 | Face verification method, system, equipment and computer readable storage medium |
| CN110852150B (en) * | 2019-09-25 | 2022-12-20 | 珠海格力电器股份有限公司 | Face verification method, system, equipment and computer readable storage medium |
| CN111182167A (en) * | 2019-11-25 | 2020-05-19 | 广东小天才科技有限公司 | File scanning method, electronic equipment and storage medium |
| CN112504628A (en) * | 2020-11-23 | 2021-03-16 | 江苏科技大学 | Ship model test pool wave making machine control system and method based on face recognition |
| CN112504628B (en) * | 2020-11-23 | 2023-04-18 | 江苏科技大学 | Ship model test pool wave making machine control system and method based on face recognition |
| CN112738067A (en) * | 2020-12-25 | 2021-04-30 | 中国农业银行股份有限公司 | Face recognition method, device and equipment |
| CN112738067B (en) * | 2020-12-25 | 2023-03-24 | 中国农业银行股份有限公司 | Face recognition method, device and equipment |
Also Published As
| Publication number | Publication date |
|---|---|
| CN101771539B (en) | 2012-07-04 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN101771539B (en) | Face recognition based method for authenticating identity | |
| CN111340008B (en) | Method and system for generation of counterpatch, training of detection model and defense of counterpatch | |
| CN111460962B (en) | Face recognition method and face recognition system for mask | |
| WO2021036436A1 (en) | Facial recognition method and apparatus | |
| CN104834839B (en) | A kind of code generating method, method for authenticating and associated terminal based on bar code | |
| US10922399B2 (en) | Authentication verification using soft biometric traits | |
| CN106529414A (en) | Method for realizing result authentication through image comparison | |
| CN103473564B (en) | A kind of obverse face detection method based on sensitizing range | |
| CN105450411A (en) | Method, device and system for utilizing card characteristics to perform identity verification | |
| CN107622246B (en) | Face recognition method and related product | |
| CN103577801A (en) | Quality metrics method and system for biometric authentication | |
| CN104063690A (en) | Identity authentication method based on face recognition technology, device thereof and system thereof | |
| CN102646190A (en) | Authentication method, device and system based on biological characteristics | |
| KR20190136349A (en) | Face verifying method and apparatus based on 3d image | |
| US20220262163A1 (en) | Method of face anti-spoofing, device, and storage medium | |
| CN204791017U (en) | Mobile terminal users authentication device based on many biological characteristics mode | |
| CN112232324B (en) | Face fake-verifying method and device, computer equipment and storage medium | |
| CN113055377A (en) | Network security protection system based on authority authentication | |
| CN108335099A (en) | Method, apparatus, mobile terminal and the storage medium of mobile payment | |
| KR102188979B1 (en) | User authentication system using artificial intelligence on a blockchain basis | |
| CN104156643A (en) | Eye sight-based password inputting method and hardware device thereof | |
| KR101622377B1 (en) | USB Dvice having an Iris Recognition Security Function and Controlling Method for the Same | |
| KR101266603B1 (en) | A face recognition system for user authentication of an unmanned receipt system | |
| CN105631285A (en) | Biological feature identity recognition method and apparatus | |
| Tian et al. | Real-time driver's eye state detection |
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 | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20120704 Termination date: 20141230 |
|
| EXPY | Termination of patent right or utility model |