CN104766063A - Living body human face identifying method - Google Patents
Living body human face identifying method Download PDFInfo
- Publication number
- CN104766063A CN104766063A CN201510161965.3A CN201510161965A CN104766063A CN 104766063 A CN104766063 A CN 104766063A CN 201510161965 A CN201510161965 A CN 201510161965A CN 104766063 A CN104766063 A CN 104766063A
- Authority
- CN
- China
- Prior art keywords
- image
- block
- grad
- human face
- vector
- 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
Landscapes
- Image Processing (AREA)
Abstract
The invention discloses a living body human face identifying method. The method is divided into a training stage and an identifying stage. In the training stage, multiple living body human face images and picture human face images are obtained, the feature vector of a gray level image of each living body human face image is extracted to serve as a positive sample, and the feature vector of a gray level image of the human face image of each picture is extracted to serve as a negative sample, all the positive samples and all the negative samples are input into an SVM classifier to be trained, and an SVM classifier training model is obtained; one frame human face image is obtained in the identifying stage, the human face identifying technology is used for identification, when an identification result shows that a user is legal, the living body detection technology is used for extracting the feature vectors, and the feature vectors are input into the SVM classifier training model to conduct living body detection. The living body human face identifying method has the advantages that the human face identifying technology is used for judging whether the human face is the human face of the legal user or not, the legal user then can judge whether the human face is a living body human face or a counterfeit picture human face through the living body detection technology if the user is legal, and therefore potential safety hazards caused by the picture human face are effectively eliminated.
Description
Technical field
The present invention relates to a kind of face recognition technology, especially relate to a kind of living body faces recognition methods.
Background technology
Face recognition technology is a kind of biometrics identification technology, and it, with the advantage such as convenient, fast, accurate, is obtaining the development of advancing by leaps and bounds in recent years.The input end input of face identification system be generally a facial image containing identity to be detected, and the facial image of some known identities in face database, its output is then a series of human face similarity degree scores, shows the identity of the face identified with this.At present, face recognition technology has been widely used in the fields such as criminal investigation and case detection, banking system, customs inspection, the civil affairs department, work and rest work attendance.But along with the continuous expansion of face recognition technology range of application, some safety problems also occur thereupon, lawless person utilizes the human face photo deception face identification system of forgery, thus causes heavy economic losses to validated user.Therefore, judge to seem particularly important to the source authenticity of facial image, Here it is In vivo detection.
After Google issues Android4.0, for vast machine friend brings the function being unlocked mobile phone by recognition of face, but just useful individual photo replaces true man to unlock the report of mobile phone subsequently, and thus Google is always at careful and conservative use face recognition technology always.Make face identification system step into maturation, this kind of photo face replaces the potential safety hazard of true living body faces to be resolved, and is therefore necessary the technology studying a kind of identifying live face.
Summary of the invention
Technical matters to be solved by this invention is to provide a kind of living body faces recognition methods, and it can judge face whether as validated user, can judge again face source whether as living body faces, effectively eliminate the potential safety hazard that photo face brings.
The present invention solves the problems of the technologies described above adopted technical scheme: a kind of living body faces recognition methods, is characterized in that comprising the following steps:
1. obtain M width include different face object and size be 256 × 256 living body faces image, then obtain the photo facial image of every width living body faces image, the size of every photos facial image is 256 × 256; Then M width living body faces image and M photos facial image are all changed into gray level image, 2M width gray level image is formed a training image set; The proper vector of the every width gray level image then in calculation training image collection; Again using the proper vector of the gray level image of every width living body faces image as a positive sample, and with+1 mark, using the proper vector of the gray level image of every photos facial image as a negative sample, and with-1 mark; Finally all positive samples and all negative samples are input in SVM classifier and train, obtain SVM classifier training pattern;
When 2. needing to carry out living body faces identification, obtain the facial image that a frame includes face object to be identified, then in this facial image, intercept the minimum rectangular area at face object place, carry out regular to the size of rectangular area again, obtain the human face region image to be identified that size is 256 × 256, then human face region image to be identified is changed into gray level image;
3. utilize the gray level image of face recognition technology to human face region image to identify, if recognition result is validated user, then perform step 4.; If recognition result is disabled user, then refuse face verification, face verification failure;
4. In vivo detection technology is utilized, first calculate the proper vector of the gray level image of human face region image, again the proper vector of the gray level image of human face region image is input in SVM classifier training pattern, if SVM classifier training pattern exports+1, then the source of expression human face region image is living body faces, face verification success; If SVM classifier training pattern exports-1, then represent that the source of human face region image is photo face, refusal face verification, face verification failure.
Described step 1. in the acquisition process of acquisition process and the described step 4. proper vector of the gray level image of middle human face region image of proper vector of every width gray level image in training image set identical, using the gray level image of the every width gray level image in training image set and human face region image all as a pending image, the acquisition process of the proper vector of pending image is:
A, pending image to be divided into
the size of individual non-overlapping copies is the image block of 64 × 64;
B, i-th pending image block current in pending image is defined as current image block, wherein, 1≤i≤16, the initial value of i is 1;
C, the moving window adopting size to be 3 × 3 slide by pixel in current image block, current image block is divided into (64-2) × (64-2) individual equitant size is the sub-block of 3 × 3;
D, the Sobel operator of eight different directions is done convolution operation with each sub-block in current image block respectively, obtain the Grad of each sub-block in current image block at eight different directions, the Grad of the sub-block of the jth in current image block in a kth direction is designated as
wherein, the Sobel operator of eight different directions is respectively the Sobel operator of 0 °, the Sobel operator of 45 °, the Sobel operator of 90 °, the Sobel operator of 135 °, the Sobel operator of 180 °, the Sobel operator of 225 °, the Sobel operator of 270 °, the Sobel operator of 315 °, 1≤j≤(64-2) × (64-2), 1≤k≤8;
E, by the order of all sub-blocks in current image block, the Grad arrangement of all sub-blocks in current image block in each direction is formed the Grad vector that the dimension of current image block in each direction is (64-2) × (64-2), the current image block that the Grad arrangement of all sub-blocks in current image block in a kth direction is formed is designated as at the Grad vector that the dimension in a kth direction is (64-2) × (64-2)
Wherein, be vector representation symbol at this symbol " [] ",
represent the Grad of the 1st sub-block in a kth direction in current image block,
represent the Grad of the 2nd sub-block in a kth direction in current image block,
represent the Grad of (64-2) × (64-2)-1 sub-block in a kth direction in current image block,
represent the Grad of the individual sub-block of (64-2) × (64-2) in a kth direction in current image block;
F, make i=i+1, using image block next pending in pending image as current image block, then return step c to continue to perform, until all image blocks in pending image are disposed, the each image block obtained in pending image is the Grad vector of (64-2) × (64-2) at the dimension of eight different directions, wherein, "=" in i=i+1 is assignment;
G, by the order of all image blocks in pending image, the arrangement of the Grad of each for all image blocks in pending image comfortable eight different directions vector is formed the proper vector of pending image, is designated as T, T=[TV
1 1, TV
2 1..., TV
8 1, TV
1 2, TV
2 2..., TV
8 2..., TV
1 16, TV
2 16..., TV
8 16], wherein, be vector representation symbol at this symbol " [] ", TV
1 1represent that the 1st image block is the Grad vector of (64-2) × (64-2) at the dimension in the 1st direction, TV
2 1represent that the 1st image block is the Grad vector of (64-2) × (64-2) at the dimension in the 2nd direction, TV
8 1represent that the 1st image block is the Grad vector of (64-2) × (64-2) at the dimension in the 8th direction, TV
1 2represent that the 2nd image block is the Grad vector of (64-2) × (64-2) at the dimension in the 1st direction, TV
2 2represent that the 2nd image block is the Grad vector of (64-2) × (64-2) at the dimension in the 2nd direction, TV
8 2represent that the 2nd image block is the Grad vector of (64-2) × (64-2) at the dimension in the 8th direction, TV
1 16represent that the 16th image block is the Grad vector of (64-2) × (64-2) at the dimension in the 1st direction, TV
2 16represent that the 16th image block is the Grad vector of (64-2) × (64-2) at the dimension in the 2nd direction, TV
8 16represent that the 16th image block is the Grad vector of (64-2) × (64-2) at the dimension in the 8th direction.
Compared with prior art, the invention has the advantages that:
1) the inventive method adds In vivo detection technology on the basis of existing face recognition technology, the inventive method is carried out training in the training stage to several living body faces images and multiple photos facial image and is obtained SVM classifier training pattern, in authentication procedures, face recognition technology is utilized to judge face whether as validated user, and utilize In vivo detection technology first to calculate the proper vector of human face region image, again the proper vector of human face region image is input in SVM classifier training pattern, judge face source as living body faces still as personation photo face, thus effectively eliminate the potential safety hazard that photo face brings, achieve the double shield of private information safety.
2) the inventive method is applicable to the platform of reduction process ability, as android system.
3) the inventive method only needs a camera, can determine whether living body faces by extracting a frame facial image, what greatly reduce system resource takies proportion, and without the need to adding extra image utility appliance, and cooperating with on one's own initiative without the need to user, very naturally.
4) the inventive method identified the image in Nanjing Aero-Space University (NUAA) living body faces storehouse in the experimental verification stage, identified the rate of accuracy reached of two class facial images to 98.718%.
Accompanying drawing explanation
Fig. 1 be the inventive method totally realize block diagram;
Fig. 2 a is the Grad vector fractional integration series Butut of each comfortable eight different directions of all image blocks in the gray level image of a width living body faces image;
Fig. 2 b is the Grad vector fractional integration series Butut of each comfortable eight different directions of all image blocks in the gray level image of the photo facial image of the living body faces image that Fig. 2 a is corresponding;
Fig. 3 is the operating characteristic ROC curve map of the In vivo detection technology in the inventive method.
Embodiment
Below in conjunction with accompanying drawing embodiment, the present invention is described in further detail.
A kind of living body faces recognition methods that the present invention proposes, it is applicable to android system, and it totally realizes block diagram as shown in Figure 1, and it comprises the following steps:
1. by mobile phone camera obtain M width include different face object and size be 256 × 256 living body faces image, obtained the photo facial image of every width living body faces image again by mobile phone camera, the size of every photos facial image is 256 × 256; Then M width living body faces image and M photos facial image are all changed into gray level image, 2M width gray level image is formed a training image set; The proper vector of the every width gray level image then in calculation training image collection; Again using the proper vector of the gray level image of every width living body faces image as a positive sample, and with+1 mark, using the proper vector of the gray level image of every photos facial image as a negative sample, and with-1 mark; Finally all positive samples and all negative samples are input in SVM classifier and train, obtain SVM classifier training pattern; Wherein, M >=50, the training stage usually the classification results of SVM classifier training pattern that obtains more at most of positive sample and negative sample more accurately, what therefore during concrete operations, M can be suitable gets larger value, as M=261 desirable when concrete operations.
At this, the face object in M width living body faces image is different, namely takes M different face and obtains different living body faces image; And photo facial image is face on comparison film once takes the image obtained again.
When 2. needing to carry out living body faces identification, the facial image that a frame includes face object to be identified is obtained by mobile phone camera, then in this facial image, intercept the minimum rectangular area at face object place, carry out regular to the size of rectangular area again, obtain the human face region image to be identified that size is 256 × 256, then human face region image to be identified is changed into gray level image.
3. utilize the gray level image of existing face recognition technology to human face region image to identify, if recognition result is validated user, then perform step 4.; If recognition result is disabled user, then refuse face verification, face verification failure.At this, when recognition result is disabled user, the source of this human face region image may be living body faces, and be also likely photo face, the people namely beyond user cannot pass through face verification.
4. In vivo detection technology is utilized, first calculate the proper vector of the gray level image of human face region image, again the proper vector of the gray level image of human face region image is input in SVM classifier training pattern, if SVM classifier training pattern exports+1, then the source of expression human face region image is living body faces, face verification success; If SVM classifier training pattern exports-1, then represent that the source of human face region image is photo face, refusal face verification, face verification failure.
In this particular embodiment, step 1. in the acquisition process of acquisition process and the step 4. proper vector of the gray level image of middle human face region image of proper vector of every width gray level image in training image set identical, using the gray level image of the every width gray level image in training image set and human face region image all as a pending image, because living body faces and the larger difference of personation photo face are that the mirror-reflection amount of the latter is far longer than the former, the light intensity diffused that real human face surface produces always is directly proportional to the light intensity of face surface all directions incident light and the cosine value of incident angle, and palm off photo face and do not meet facial concavo-convex situation, and smooth degree is high, mirror-reflection amount is high, photo face object will be the linear combination of diffuse reflection and specular components, mirror-reflection amount and diffuse reflection amount share weight, therefore pending image is divided into the image block of 16 non-overlapping copies by the inventive method, then each image block being divided into the individual equitant size of (64-2) × (64-2) is the sub-block of 3 × 3, the Sobel operator recycling each sub-block and eight different directions does the result of convolution operation to obtain the proper vector of pending image, namely the acquisition process of the proper vector of pending image is:
A, pending image to be divided into
the size of individual non-overlapping copies is the image block of 64 × 64.
B, i-th pending image block current in pending image is defined as current image block, wherein, 1≤i≤16, the initial value of i is 1.
C, the moving window adopting size to be 3 × 3 slide by pixel in current image block, current image block is divided into (64-2) × (64-2) individual equitant size is the sub-block of 3 × 3.
D, the Sobel operator of eight different directions is done convolution operation with each sub-block in current image block respectively, obtain the Grad of each sub-block in current image block at eight different directions, the Grad of the sub-block of the jth in current image block in a kth direction is designated as
obtain for the jth sub-block in the Sobel operator in a kth direction and current image block is done convolution operation; Wherein, as listed in table 1, the Sobel operator of eight different directions is respectively the Sobel operator of 0 °, the Sobel operator of 45 °, the Sobel operator of 90 °, the Sobel operator of 135 °, the Sobel operator of 180 °, the Sobel operator of 225 °, the Sobel operator of 270 °, the Sobel operator of 315 °, 1≤j≤(64-2) × (64-2), 1≤k≤8.
The Sobel operator of table 1 eight different directions
E, by the order of all sub-blocks in current image block, the Grad arrangement of all sub-blocks in current image block in each direction is formed the Grad vector that the dimension of current image block in each direction is (64-2) × (64-2), the current image block that the Grad arrangement of all sub-blocks in current image block in a kth direction is formed is designated as at the Grad vector that the dimension in a kth direction is (64-2) × (64-2)
Wherein, be vector representation symbol at this symbol " [] ",
represent the Grad of the 1st sub-block in a kth direction in current image block,
represent the Grad of the 2nd sub-block in a kth direction in current image block,
represent the Grad of (64-2) × (64-2)-1 sub-block in a kth direction in current image block,
represent the Grad of the individual sub-block of (64-2) × (64-2) in a kth direction in current image block.
F, make i=i+1, using image block next pending in pending image as current image block, then return step c to continue to perform, until all image blocks in pending image are disposed, the each image block obtained in pending image is the Grad vector of (64-2) × (64-2) at the dimension of eight different directions, wherein, "=" in i=i+1 is assignment.
G, by the order of all image blocks in pending image, the arrangement of the Grad of each for all image blocks in pending image comfortable eight different directions vector is formed the proper vector of pending image, is designated as T, T=[TV
1 1, TV
2 1..., TV
8 1, TV
1 2, TV
2 2..., TV
8 2..., TV
1 16, TV
2 16..., TV
8 16], wherein, be vector representation symbol at this symbol " [] ", TV
1 1represent that the 1st image block is the Grad vector of (64-2) × (64-2) at the dimension in the 1st direction, TV
2 1represent that the 1st image block is the Grad vector of (64-2) × (64-2) at the dimension in the 2nd direction, TV
8 1represent that the 1st image block is the Grad vector of (64-2) × (64-2) at the dimension in the 8th direction, TV
1 2represent that the 2nd image block is the Grad vector of (64-2) × (64-2) at the dimension in the 1st direction, TV
2 2represent that the 2nd image block is the Grad vector of (64-2) × (64-2) at the dimension in the 2nd direction, TV
8 2represent that the 2nd image block is the Grad vector of (64-2) × (64-2) at the dimension in the 8th direction, TV
1 16represent that the 16th image block is the Grad vector of (64-2) × (64-2) at the dimension in the 1st direction, TV
2 16represent that the 16th image block is the Grad vector of (64-2) × (64-2) at the dimension in the 2nd direction, TV
8 16represent that the 16th image block is the Grad vector of (64-2) × (64-2) at the dimension in the 8th direction.
For further illustrating feasibility and the validity of the inventive method, experimental verification is carried out to the inventive method.
The Sample Storehouse that Matlab experiment porch is selected adopts disclosed NUAA In vivo detection face database, 522 sub-pictures are randomly drawed in NUAA In vivo detection face database, comprise the photo facial image (i.e. photo facial image totally 261 width) of 261 width living body faces images and every width living body faces image, the size of every width image is 256 × 256.The type of every width image is RGB Three Channel Color image, converts it into gray level image, facilitates image procossing.Every width image is divided into
the size of individual non-overlapping copies is the image block of 64 × 64, then adopt size be 3 × 3 moving window slide by pixel in each image block, each image block is divided into (64-2) × (64-2) individual equitant size is the sub-block of 3 × 3, again the Sobel operator of eight different directions is done convolution operation with each sub-block in each image block respectively, obtain the Grad of each sub-block in each image block at eight different directions, and then obtain the Grad vector of each image block in each direction.Fig. 2 a gives the Grad vector distribution of each comfortable eight different directions of all image blocks in the gray level image of a width living body faces image, and as can be seen from Fig. 2 a, the number percent of all image blocks shared by the Grad vector in each direction is different.Fig. 2 b gives the Grad vector distribution of each comfortable eight different directions of all image blocks in the gray level image of the photo facial image of living body faces image corresponding to Fig. 2 a, as can be seen from Fig. 2 b, the number percent of all image blocks shared by the Grad vector in each direction is different.Comparison diagram 2a and Fig. 2 b, can find out that the level otherness of the distribution shown in Fig. 2 b is larger.
According to the Grad vector of each comfortable eight different directions of all image blocks in the gray level image of all living body faces images obtained above, obtain the proper vector of the gray level image of all living body faces images, and random selecting
m proper vector is as positive sample; And it is vectorial according to the Grad of each comfortable eight different directions of all image blocks in the gray level image of the photo facial image of all living body faces images obtained above, obtain the proper vector of the gray level image of the photo facial image of all living body faces images, and using positive sample characteristic of correspondence vector as negative sample; All positive samples and all negative samples are input in SVM classifier and train, obtain SVM classifier training pattern.By remaining
the proper vector of the gray level image of M living body faces image and remaining
the proper vector of the gray level image of the photo facial image of M living body faces image is input in SVM classifier training pattern respectively as the proper vector of testing, Fig. 3 gives the operating characteristic ROC curve of the In vivo detection technology in the inventive method, in Fig. 3, horizontal ordinate represents false positive probability (False Positive Rate), ordinate represents real probability (True Positive Rate), area below the ROC curve provided from Fig. 3 is known, the verification and measurement ratio of the In vivo detection technology in the inventive method reaches 98.718%, detect 167 seconds used times altogether, on average often open face processing consuming time less than one second, this fully indicates the inventive method and has lower complexity, application for Android platform provides good theoretical foundation, this makes the In vivo detection technology in the inventive method greatly improve the feasibility improving face recognition technology, the more sound assurance safety in utilization of face identification system.
Claims (2)
1. a living body faces recognition methods, is characterized in that comprising the following steps:
1. obtain M width include different face object and size be 256 × 256 living body faces image, then obtain the photo facial image of every width living body faces image, the size of every photos facial image is 256 × 256; Then M width living body faces image and M photos facial image are all changed into gray level image, 2M width gray level image is formed a training image set; The proper vector of the every width gray level image then in calculation training image collection; Again using the proper vector of the gray level image of every width living body faces image as a positive sample, and with+1 mark, using the proper vector of the gray level image of every photos facial image as a negative sample, and with-1 mark; Finally all positive samples and all negative samples are input in SVM classifier and train, obtain SVM classifier training pattern;
When 2. needing to carry out living body faces identification, obtain the facial image that a frame includes face object to be identified, then in this facial image, intercept the minimum rectangular area at face object place, carry out regular to the size of rectangular area again, obtain the human face region image to be identified that size is 256 × 256, then human face region image to be identified is changed into gray level image;
3. utilize the gray level image of face recognition technology to human face region image to identify, if recognition result is validated user, then perform step 4.; If recognition result is disabled user, then refuse face verification, face verification failure;
4. In vivo detection technology is utilized, first calculate the proper vector of the gray level image of human face region image, again the proper vector of the gray level image of human face region image is input in SVM classifier training pattern, if SVM classifier training pattern exports+1, then the source of expression human face region image is living body faces, face verification success; If SVM classifier training pattern exports-1, then represent that the source of human face region image is photo face, refusal face verification, face verification failure.
2. a kind of living body faces recognition methods according to claim 1, it is characterized in that the acquisition process of the proper vector of the gray level image of human face region image during the acquisition process of the proper vector of the every width gray level image during described step 1. in training image set and described step are 4. is identical, using the gray level image of the every width gray level image in training image set and human face region image all as a pending image, the acquisition process of the proper vector of pending image is:
A, pending image to be divided into
the size of individual non-overlapping copies is the image block of 64 × 64;
B, i-th pending image block current in pending image is defined as current image block, wherein, 1≤i≤16, the initial value of i is 1;
C, the moving window adopting size to be 3 × 3 slide by pixel in current image block, current image block is divided into (64-2) × (64-2) individual equitant size is the sub-block of 3 × 3;
D, the Sobel operator of eight different directions is done convolution operation with each sub-block in current image block respectively, obtain the Grad of each sub-block in current image block at eight different directions, the Grad of the sub-block of the jth in current image block in a kth direction is designated as
wherein, the Sobel operator of eight different directions is respectively the Sobel operator of 0 °, the Sobel operator of 45 °, the Sobel operator of 90 °, the Sobel operator of 135 °, the Sobel operator of 180 °, the Sobel operator of 225 °, the Sobel operator of 270 °, the Sobel operator of 315 °, 1≤j≤(64-2) × (64-2), 1≤k≤8;
E, by the order of all sub-blocks in current image block, the Grad arrangement of all sub-blocks in current image block in each direction is formed the Grad vector that the dimension of current image block in each direction is (64-2) × (64-2), the current image block that the Grad arrangement of all sub-blocks in current image block in a kth direction is formed is designated as at the Grad vector that the dimension in a kth direction is (64-2) × (64-2)
Wherein, be vector representation symbol at this symbol " [] ",
represent the Grad of the 1st sub-block in a kth direction in current image block,
represent the Grad of the 2nd sub-block in a kth direction in current image block,
represent the Grad of (64-2) × (64-2)-1 sub-block in a kth direction in current image block,
represent the Grad of the individual sub-block of (64-2) × (64-2) in a kth direction in current image block;
F, make i=i+1, using image block next pending in pending image as current image block, then return step c to continue to perform, until all image blocks in pending image are disposed, the each image block obtained in pending image is the Grad vector of (64-2) × (64-2) at the dimension of eight different directions, wherein, "=" in i=i+1 is assignment;
G, by the order of all image blocks in pending image, the arrangement of the Grad of each for all image blocks in pending image comfortable eight different directions vector is formed the proper vector of pending image, is designated as T,
Wherein, be vector representation symbol at this symbol " [] ", TV
1 1represent that the 1st image block is the Grad vector of (64-2) × (64-2) at the dimension in the 1st direction, TV
2 1represent that the 1st image block is the Grad vector of (64-2) × (64-2) at the dimension in the 2nd direction, TV
8 1represent that the 1st image block is the Grad vector of (64-2) × (64-2) at the dimension in the 8th direction, TV
1 2represent that the 2nd image block is the Grad vector of (64-2) × (64-2) at the dimension in the 1st direction, TV
2 2represent that the 2nd image block is the Grad vector of (64-2) × (64-2) at the dimension in the 2nd direction, TV
8 2represent that the 2nd image block is the Grad vector of (64-2) × (64-2) at the dimension in the 8th direction, TV
1 16represent that the 16th image block is the Grad vector of (64-2) × (64-2) at the dimension in the 1st direction, TV
2 16represent that the 16th image block is the Grad vector of (64-2) × (64-2) at the dimension in the 2nd direction, TV
8 16represent that the 16th image block is the Grad vector of (64-2) × (64-2) at the dimension in the 8th direction.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510161965.3A CN104766063B (en) | 2015-04-08 | 2015-04-08 | A kind of living body faces recognition methods |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510161965.3A CN104766063B (en) | 2015-04-08 | 2015-04-08 | A kind of living body faces recognition methods |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN104766063A true CN104766063A (en) | 2015-07-08 |
| CN104766063B CN104766063B (en) | 2018-01-05 |
Family
ID=53647877
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510161965.3A Active CN104766063B (en) | 2015-04-08 | 2015-04-08 | A kind of living body faces recognition methods |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104766063B (en) |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105389553A (en) * | 2015-11-06 | 2016-03-09 | 北京汉王智远科技有限公司 | Living body detection method and apparatus |
| CN105389554A (en) * | 2015-11-06 | 2016-03-09 | 北京汉王智远科技有限公司 | Face-identification-based living body determination method and equipment |
| WO2017070920A1 (en) * | 2015-10-30 | 2017-05-04 | Microsoft Technology Licensing, Llc | Spoofed face detection |
| CN107122744A (en) * | 2017-04-28 | 2017-09-01 | 武汉神目信息技术有限公司 | A kind of In vivo detection system and method based on recognition of face |
| CN107122709A (en) * | 2017-03-17 | 2017-09-01 | 上海云从企业发展有限公司 | Biopsy method and device |
| CN107368817A (en) * | 2017-07-26 | 2017-11-21 | 湖南云迪生物识别科技有限公司 | Face identification method and device |
| CN107392135A (en) * | 2017-07-14 | 2017-11-24 | 广东欧珀移动通信有限公司 | Biopsy method and Related product |
| CN107609494A (en) * | 2017-08-31 | 2018-01-19 | 北京飞搜科技有限公司 | A kind of human face in-vivo detection method and system based on silent formula |
| CN107679457A (en) * | 2017-09-06 | 2018-02-09 | 阿里巴巴集团控股有限公司 | User identity method of calibration and device |
| CN107680185A (en) * | 2017-09-22 | 2018-02-09 | 芜湖星途机器人科技有限公司 | The method for using robot register in meeting-place |
| CN107818313A (en) * | 2017-11-20 | 2018-03-20 | 腾讯科技（深圳）有限公司 | Vivo identification method, device, storage medium and computer equipment |
| CN107958236A (en) * | 2017-12-28 | 2018-04-24 | 深圳市金立通信设备有限公司 | The generation method and terminal of recognition of face sample image |
| CN108389053A (en) * | 2018-03-19 | 2018-08-10 | 广州逗号智能零售有限公司 | Method of payment, device, electronic equipment and readable storage medium storing program for executing |
| CN108494778A (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 |
| CN108629260A (en) * | 2017-03-17 | 2018-10-09 | 北京旷视科技有限公司 | Live body verification method and device and storage medium |
| CN108875473A (en) * | 2017-06-29 | 2018-11-23 | 北京旷视科技有限公司 | Living body verification method, device and system and storage medium |
| CN109409344A (en) * | 2018-12-23 | 2019-03-01 | 广东腾晟信息科技有限公司 | Human face data accurately compares and judgment method |
| CN110334238A (en) * | 2019-03-27 | 2019-10-15 | 特斯联（北京）科技有限公司 | A kind of Missing Persons based on recognition of face trace method and system |
| CN111222380A (en) * | 2018-11-27 | 2020-06-02 | 杭州海康威视数字技术股份有限公司 | Living body detection method and device and recognition model training method thereof |
| CN111488764A (en) * | 2019-01-26 | 2020-08-04 | 天津大学青岛海洋技术研究院 | Face recognition algorithm for ToF image sensor |
| WO2020159437A1 (en) * | 2019-01-29 | 2020-08-06 | Agency For Science, Technology And Research | Method and system for face liveness detection |
| CN110321872B (en) * | 2019-07-11 | 2021-03-16 | 京东方科技集团股份有限公司 | Facial expression recognition method and device, computer equipment and readable storage medium |
| CN113221767A (en) * | 2021-05-18 | 2021-08-06 | 北京百度网讯科技有限公司 | Method for training living body face recognition model and method for recognizing living body face and related device |
| CN113239761A (en) * | 2021-04-29 | 2021-08-10 | 广州杰赛科技股份有限公司 | Face recognition method, face recognition device and storage medium |
| TWI766201B (en) * | 2018-12-29 | 2022-06-01 | 大陸商北京市商湯科技開發有限公司 | Methods and devices for biological testing and storage medium thereof |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120070041A1 (en) * | 2010-09-16 | 2012-03-22 | Jie Wang | System And Method For Face Verification Using Video Sequence |
| CN103020599A (en) * | 2012-12-12 | 2013-04-03 | 山东神思电子技术股份有限公司 | Identity authentication method based on face |
| CN103116763A (en) * | 2013-01-30 | 2013-05-22 | 宁波大学 | Vivo-face detection method based on HSV (hue, saturation, value) color space statistical characteristics |
| CN103440479A (en) * | 2013-08-29 | 2013-12-11 | 湖北微模式科技发展有限公司 | Method and system for detecting living body human face |
| CN103605958A (en) * | 2013-11-12 | 2014-02-26 | 北京工业大学 | Living body human face detection method based on gray scale symbiosis matrixes and wavelet analysis |
-
2015
- 2015-04-08 CN CN201510161965.3A patent/CN104766063B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120070041A1 (en) * | 2010-09-16 | 2012-03-22 | Jie Wang | System And Method For Face Verification Using Video Sequence |
| CN103020599A (en) * | 2012-12-12 | 2013-04-03 | 山东神思电子技术股份有限公司 | Identity authentication method based on face |
| CN103116763A (en) * | 2013-01-30 | 2013-05-22 | 宁波大学 | Vivo-face detection method based on HSV (hue, saturation, value) color space statistical characteristics |
| CN103440479A (en) * | 2013-08-29 | 2013-12-11 | 湖北微模式科技发展有限公司 | Method and system for detecting living body human face |
| CN103605958A (en) * | 2013-11-12 | 2014-02-26 | 北京工业大学 | Living body human face detection method based on gray scale symbiosis matrixes and wavelet analysis |
Cited By (41)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2017070920A1 (en) * | 2015-10-30 | 2017-05-04 | 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 |
| CN107111750B (en) * | 2015-10-30 | 2020-06-05 | 微软技术许可有限责任公司 | Detection of deceptive faces |
| US10452935B2 (en) | 2015-10-30 | 2019-10-22 | Microsoft Technology Licensing, Llc | Spoofed face detection |
| CN105389553A (en) * | 2015-11-06 | 2016-03-09 | 北京汉王智远科技有限公司 | Living body detection method and apparatus |
| CN105389554A (en) * | 2015-11-06 | 2016-03-09 | 北京汉王智远科技有限公司 | Face-identification-based living body determination method and equipment |
| CN105389554B (en) * | 2015-11-06 | 2019-05-17 | 北京汉王智远科技有限公司 | Living body determination method and equipment based on recognition of face |
| CN108629260A (en) * | 2017-03-17 | 2018-10-09 | 北京旷视科技有限公司 | Live body verification method and device and storage medium |
| CN107122709A (en) * | 2017-03-17 | 2017-09-01 | 上海云从企业发展有限公司 | Biopsy method and device |
| CN107122744B (en) * | 2017-04-28 | 2020-11-10 | 武汉神目信息技术有限公司 | Living body detection system and method based on face recognition |
| CN107122744A (en) * | 2017-04-28 | 2017-09-01 | 武汉神目信息技术有限公司 | A kind of In vivo detection system and method based on recognition of face |
| CN108875473A (en) * | 2017-06-29 | 2018-11-23 | 北京旷视科技有限公司 | Living body verification method, device and system and storage medium |
| CN107392135A (en) * | 2017-07-14 | 2017-11-24 | 广东欧珀移动通信有限公司 | Biopsy method and Related product |
| CN107368817A (en) * | 2017-07-26 | 2017-11-21 | 湖南云迪生物识别科技有限公司 | Face identification method and device |
| CN107368817B (en) * | 2017-07-26 | 2020-02-21 | 湖南云迪生物识别科技有限公司 | Face recognition method and device |
| CN107609494A (en) * | 2017-08-31 | 2018-01-19 | 北京飞搜科技有限公司 | A kind of human face in-vivo detection method and system based on silent formula |
| CN107679457A (en) * | 2017-09-06 | 2018-02-09 | 阿里巴巴集团控股有限公司 | User identity method of calibration and device |
| CN107680185A (en) * | 2017-09-22 | 2018-02-09 | 芜湖星途机器人科技有限公司 | The method for using robot register in meeting-place |
| CN107818313A (en) * | 2017-11-20 | 2018-03-20 | 腾讯科技（深圳）有限公司 | Vivo identification method, device, storage medium and computer equipment |
| US11176393B2 (en) | 2017-11-20 | 2021-11-16 | Tencent Technology (Shenzhen) Company Limited | Living body recognition method, storage medium, and computer device |
| CN107818313B (en) * | 2017-11-20 | 2019-05-14 | 腾讯科技（深圳）有限公司 | Vivo identification method, device and storage medium |
| CN107958236B (en) * | 2017-12-28 | 2021-03-19 | 深圳市金立通信设备有限公司 | Face recognition sample image generation method and terminal |
| CN107958236A (en) * | 2017-12-28 | 2018-04-24 | 深圳市金立通信设备有限公司 | The generation method and terminal of recognition of face sample image |
| CN108389053A (en) * | 2018-03-19 | 2018-08-10 | 广州逗号智能零售有限公司 | Method of payment, device, electronic equipment and readable storage medium storing program for executing |
| CN108494778A (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 |
| CN111222380B (en) * | 2018-11-27 | 2023-11-03 | 杭州海康威视数字技术股份有限公司 | Living body detection method and device and recognition model training method thereof |
| CN111222380A (en) * | 2018-11-27 | 2020-06-02 | 杭州海康威视数字技术股份有限公司 | Living body detection method and device and recognition model training method thereof |
| CN109409344A (en) * | 2018-12-23 | 2019-03-01 | 广东腾晟信息科技有限公司 | Human face data accurately compares and judgment method |
| US11393256B2 (en) | 2018-12-29 | 2022-07-19 | Beijing Sensetime Technology Development Co., Ltd. | Method and device for liveness detection, and storage medium |
| TWI766201B (en) * | 2018-12-29 | 2022-06-01 | 大陸商北京市商湯科技開發有限公司 | Methods and devices for biological testing and storage medium thereof |
| CN111488764A (en) * | 2019-01-26 | 2020-08-04 | 天津大学青岛海洋技术研究院 | Face recognition algorithm for ToF image sensor |
| CN111488764B (en) * | 2019-01-26 | 2024-04-30 | 天津大学青岛海洋技术研究院 | Face recognition method for ToF image sensor |
| WO2020159437A1 (en) * | 2019-01-29 | 2020-08-06 | Agency For Science, Technology And Research | Method and system for face liveness detection |
| CN110334238B (en) * | 2019-03-27 | 2020-01-31 | 特斯联（北京）科技有限公司 | missing population tracing method and system based on face recognition |
| CN110334238A (en) * | 2019-03-27 | 2019-10-15 | 特斯联（北京）科技有限公司 | A kind of Missing Persons based on recognition of face trace method and system |
| CN110321872B (en) * | 2019-07-11 | 2021-03-16 | 京东方科技集团股份有限公司 | Facial expression recognition method and device, computer equipment and readable storage medium |
| US11281895B2 (en) | 2019-07-11 | 2022-03-22 | Boe Technology Group Co., Ltd. | Expression recognition method, computer device, and computer-readable storage medium |
| CN113239761A (en) * | 2021-04-29 | 2021-08-10 | 广州杰赛科技股份有限公司 | Face recognition method, face recognition device and storage medium |
| CN113239761B (en) * | 2021-04-29 | 2023-11-14 | 广州杰赛科技股份有限公司 | Face recognition method, device and storage medium |
| CN113221767A (en) * | 2021-05-18 | 2021-08-06 | 北京百度网讯科技有限公司 | Method for training living body face recognition model and method for recognizing living body face and related device |
| CN113221767B (en) * | 2021-05-18 | 2023-08-04 | 北京百度网讯科技有限公司 | Method for training living body face recognition model and recognizing living body face and related device |
Also Published As
| Publication number | Publication date |
|---|---|
| CN104766063B (en) | 2018-01-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104766063A (en) | Living body human face identifying method | |
| Zhang et al. | Face morphing detection using Fourier spectrum of sensor pattern noise | |
| CN103116763B (en) | A kind of living body faces detection method based on hsv color Spatial Statistical Character | |
| CN105574509B (en) | A kind of face identification system replay attack detection method and application based on illumination | |
| CN103605958A (en) | Living body human face detection method based on gray scale symbiosis matrixes and wavelet analysis | |
| CN108960088A (en) | The detection of facial living body characteristics, the recognition methods of specific environment | |
| KR101443139B1 (en) | Single image-based fake face detection | |
| KR102275803B1 (en) | Apparatus and method for detecting forgery or alteration of the face | |
| CN105488486A (en) | Face recognition method and device for preventing photo attack | |
| CN104361319A (en) | Fake fingerprint detection method based on SVM-RFE (support vector machine-recursive feature elimination) | |
| CN107742094A (en) | Improve the image processing method of testimony of a witness comparison result | |
| CN111222380A (en) | Living body detection method and device and recognition model training method thereof | |
| Naveen et al. | Face recognition and authentication using LBP and BSIF mask detection and elimination | |
| CN101364257A (en) | Human face recognizing method for recognizing image origin | |
| Long et al. | Detection of Face Morphing Attacks Based on Patch‐Level Features and Lightweight Networks | |
| CN106845520A (en) | A kind of image processing method and terminal | |
| CN104408736A (en) | Characteristic-similarity-based synthetic face image quality evaluation method | |
| CN104615985B (en) | A kind of recognition methods of human face similarity degree | |
| CN106845500A (en) | A kind of human face light invariant feature extraction method based on Sobel operators | |
| Teja | Real-time live face detection using face template matching and DCT energy analysis | |
| Cheng et al. | Illumination normalization based on different smoothing filters quotient image | |
| CN110929681B (en) | Wrinkle detection method | |
| CN114898137A (en) | Face recognition-oriented black box sample attack resisting method, device, equipment and medium | |
| Basavaraj et al. | Offline-line signature verification and recognition: An approach based on four speed stroke angle | |
| Zaim et al. | A new method for iris recognition using gray-level coccurence matrix |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| EXSB | Decision made by sipo to initiate substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |