CN109166196A - A kind of hotel's disengaging personnel management methods based on single sample recognition of face - Google Patents
A kind of hotel's disengaging personnel management methods based on single sample recognition of face Download PDFInfo
- Publication number
- CN109166196A CN109166196A CN201810643177.1A CN201810643177A CN109166196A CN 109166196 A CN109166196 A CN 109166196A CN 201810643177 A CN201810643177 A CN 201810643177A CN 109166196 A CN109166196 A CN 109166196A
- Authority
- CN
- China
- Prior art keywords
- face
- hotel
- subpattern
- picture
- single sample
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G07—CHECKING-DEVICES
- G07C—TIME OR ATTENDANCE REGISTERS; REGISTERING OR INDICATING THE WORKING OF MACHINES; GENERATING RANDOM NUMBERS; VOTING OR LOTTERY APPARATUS; ARRANGEMENTS, SYSTEMS OR APPARATUS FOR CHECKING NOT PROVIDED FOR ELSEWHERE
- G07C9/00—Individual registration on entry or exit
- G07C9/30—Individual registration on entry or exit not involving the use of a pass
- G07C9/32—Individual registration on entry or exit not involving the use of a pass in combination with an identity check
- G07C9/37—Individual registration on entry or exit not involving the use of a pass in combination with an identity check using biometric data, e.g. fingerprints, iris scans or voice recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/10—Human or animal bodies, e.g. vehicle occupants or pedestrians; Body parts, e.g. hands
- G06V40/16—Human faces, e.g. facial parts, sketches or expressions
- G06V40/172—Classification, e.g. identification
Landscapes
- Engineering & Computer Science (AREA)
- Human Computer Interaction (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Collating Specific Patterns (AREA)
Abstract
The present invention relates to a kind of, and the hotel based on single sample recognition of face passes in and out personnel management methods, it is based only on the recognition of face of single sample training model, greatly reduce the difficulty of acquisition training sample database, the operating mode for verifying hotel disengaging personnel is more succinct more intelligent, reduces pure manual working and causes to omit.In addition, use the division methods put and cut out on the basis of face key point, and introduce external human face data collection in training and be trained, and the method that the similarity in each region of Weighted Fusion is newly added, it improves to higher amplitude single sample training and obtains the accuracy of identification of model.Make increasing hotel's disengaging personnel's verification dynamics, increase criminal enters hotel's difficulty, while improving hotel occupancy personnel safety index, can also alleviate the operating pressure of staff.
Description
Technical field
The present invention relates to the technical field of image recognition more particularly to a kind of hotel based on single sample recognition of face into
Personnel management methods out.
Background technique
With the development of technology, public security department requires, and promotes the use of recognition of face testimony of a witness unification identity in hotel, hotel and tests
Card system, to reinforce the management of public security, and the floating population in hotel hotel is more, so how to verify the body of hotel's disengaging personnel
Part becomes urgent solve the problems, such as.
Now, when the personnel of moving in hotel move in after foreground carries out identity verification, hotel, the peace in hotel can be freed in and out
It protects work and identifies the identity to identify disengaging personnel by memory and human eye mainly by Security Personnel, and artificial identification is often
Inefficiency is easy to produce omission, and when the stream of people is more, some criminals are easy for entering inside hotel, to living in personnel
The person and property safety threaten.
Although face recognition technology can solve this problem, existing many face recognition technologies largely according to
Rely the scale and representativeness in training sample set, and the sample collection of mobile personnel's face is more difficult, if only with single training sample
The recognition of face of this (acquired image information when checking in), obtained accuracy rate and efficiency is lower, is not suitable for
The management of hotel's disengaging personnel.
Summary of the invention
Previous mobile personnel's face sample can be overcome it is an object of the invention to overcome the deficiencies of the prior art and provide a kind of
It acquires difficult defect, the accuracy rate for improving single sample recognition of face and efficiency, reduce the leakiness generated under manual operation
Hotel based on single sample recognition of face pass in and out personnel management methods.
The technical scheme of the present invention is realized as follows:
A kind of hotel's disengaging personnel management methods based on single sample recognition of face, using the side of single sample training model
Formula only reads the information for moving in people's identity card, while the image initial acquisition subsystem acquisition on foreground by system of checking in
Move in the facial image of people, and by collected facial image and the PC for moving in people's identity information and being transferred to backstage read
Then end carries out processing training to collected facial image and is stored into face database subsystem, enters hotel to obtain
Permission;Whenever the personnel of moving in enter hotel, the face acquisition testing subsystem in access control system will acquire and detect this and enters
The firmly facial image of people carries out identification verifying by recognition of face subsystem, and by verifying, opening gate, authentication failed is then notified
Staff.
Further, described by acquired image and the PC for moving in people's identity information and being transferred to backstage read
Then end carries out processing training to acquired image and is stored into face database subsystem detailed process is as follows:
A-1: by acquired image and the end PC moved in people's identity information and be transferred to backstage read;
A-2: the end PC on backstage carries out gaussian filtering to collected face picture, removes the interference of noise, and normalize
To specified size, then 5 datum marks are demarcated with MTCNN algorithm and divide subpattern region;
A-3: constructing the face subpattern in 5 regions with HOG feature, negative sample subpattern collection is added, using SVM algorithm
It is trained, 5 sub- pattern classifiers of the face are obtained, is stored into face database subsystem.
Further, the face acquisition testing subsystem in the access control system acquires and detects the face for moving in people
Detailed process is as follows for image:
B-1: it is acquired from camera review and obtains video frame;
B-2: real-time video picture is converted to by function in OpenCV;
B-3: picture carries out scaling by way of sampling;
B-4: it is trained using the P-NET layer and R-NET layers of MTCNN algorithm;
B-5: it if there is face in picture, obtains human face region using the O-NET layer of MTCNN algorithm and generates key point;
B-6: if finally obtaining multiple faces, select maximum face frame as target face;
B-7: subpattern region is marked off according to five key points in target face.
Further, the detailed process of the step B-4 and B-5 are as follows: picture is passed to the P-Net layer of MTCNN algorithm, is obtained
The candidate window of human face region and the regression vector of bounding box are obtained, and is returned with the bounding box, candidate window is calibrated,
Then the candidate frame for merging high superposed by non-maxima suppression NMS, is then input to R-Net layers, is returned by bounding box
Return with NMS and removes the region false-positive, it is one more since the network structure and P-Net network structure are variant
Full articulamentum determines in picture defeated again after having face information so the effect for preferably inhibiting false-positive can be obtained
Enter and exports final face frame and characteristic point position to O-Net layers.
Further, it is described by recognition of face subsystem carry out identification verifying detailed process is as follows:
C-1: the subpattern region picture of face to be identified is obtained from face acquisition testing subsystem;
C-2: gaussian filtering and normalized are carried out to picture;
C-3: HOG feature extraction face subpattern is used;
C-4: the classifier that training obtains in 5 subpatterns and face database subsystem by subject face compares,
There is n pattern classifier in model library, then subject face picture then needs to carry out n times Classification and Identification, obtains the n of each subpattern
A classification score;
C-5: classifying to be allocated as Weighted Fusion to each subpattern, is that 5 corresponding subpatterns distribute corresponding weight,
It is weighted the average weighted score i.e. similarity that fusion measures subject face;
C-6: statistics subject face selects similarity maximum the total score of face in face database subsystem,
Again compared with the threshold value being previously set, the identity information of subject face is finally measured, decides whether to pass through.
Compared with prior art, this programme principle and advantage is as follows:
1, be based only on the recognition of face of one training sample, greatly reduce acquisition training sample database difficulty, make hotel into
The operating mode that personnel verify out is more succinct more intelligent, reduces pure manual working and causes to omit.
2, the division methods put and cut out on the basis of face key point are used, and introduce external human face data collection in training
It is trained, and the method that the similarity in each region of Weighted Fusion is newly added, improves to higher amplitude single sample training and obtain
The accuracy of identification of model.
3, hotel's disengaging personnel's verification dynamics is being increased, increase criminal enters hotel's difficulty, improves hotel occupancy
While personnel safety index, it can also alleviate the operating pressure of staff.
Detailed description of the invention
Fig. 1 is the flow chart that a kind of hotel based on single sample recognition of face of the present invention passes in and out personnel management methods;
Fig. 2 is to acquire image in the present invention, handled, trained and be stored into face database subsystem to the image of acquisition
The flow chart of system;
Fig. 3 is that face acquisition testing subsystem acquires and detect the flow chart for moving in personnel's facial image;
Fig. 4 is face key point region division schematic diagram;
Fig. 5 is the flow chart that recognition of face is carried out in the present invention.
Specific embodiment
The present invention is further explained in the light of specific embodiments:
As shown in Figure 1, a kind of hotel based on single sample recognition of face passes in and out personnel management methods, using single sample training
The mode of model only reads the information for moving in people's identity card by system of checking in, while the image initial on foreground acquires son
System acquisition moves in the facial image of people, and collected facial image and the people's identity information of moving in read are transferred to
Then the end PC on backstage carries out processing training to collected facial image and is stored into face database subsystem, to obtain
Into the permission in hotel;Whenever the personnel of moving in enter hotel, the face acquisition testing subsystem in access control system will acquire and
The facial image for moving in personnel is detected, identification verifying is carried out by recognition of face subsystem, passes through verifying, opening gate, verifying
Failure, then notify staff.
The above method is explained in detail below:
The image initial acquisition subsystem on foreground uses the high-definition camera containing SDK, small in size easy to use, passes through
The secondary development of SDK is realized the realtime graphic that video camera obtains being transferred to the end PC.
The face database subsystem in hotel mainly includes staff and the face information for moving in personnel, staff
Data input it is more convenient, and move in that flow of personnel is larger, so simplifying human face photo using the method for single specimen discerning
Acquisition complicated processes, it is only necessary to extracting photo from register system can be obtained training sample, for constructing subpattern point
Class device, detailed process is as follows, as shown in Figure 2:
A-1: by acquired image and the end PC moved in people's identity information and be transferred to backstage read;
A-2: the end PC on backstage carries out gaussian filtering to collected face picture, removes the interference of noise, and normalize
To specified size, then 5 datum marks are demarcated with MTCNN algorithm and divide subpattern region;
A-3: constructing the face subpattern in 5 regions with HOG feature, negative sample subpattern collection is added, using SVM algorithm
It is trained, 5 sub- pattern classifiers of the face are obtained, is stored into face database subsystem.
Face recognition technology reaches its maturity in recent years, while also having reached very high discrimination, and the present embodiment uses
Subpattern division methods based on face datum mark, this method first use multitask concatenated convolutional neural network (MTCNN,
Multi-task Cascaded Convolutional Networks) locating human face position and estimate the side of face's key point
Method extracts the accurate positionin that advanced features are used for key point (left eye, right eye, nose, the left corners of the mouth, the right corners of the mouth) from face area,
Face will finally be tested according to the subpattern of datum mark 5 fixed sizes of division, detailed process is as follows, as shown in Figure 3:
B-1: it is acquired from camera review and obtains video frame;
B-2: real-time video picture is converted to by function in OpenCV;
B-3: picture carries out scaling by way of sampling;
B-4: it is trained using the P-NET layer and R-NET layers of MTCNN algorithm;
B-5: it if there is face in picture, obtains human face region using the O-NET layer of MTCNN algorithm and generates key point;
B-6: if finally obtaining multiple faces, select maximum face frame as target face;
B-7: subpattern region is marked off according to five key points in target face, as shown in Figure 4.
Then, pass through the collected figure information of video camera and face of the face acquisition testing subsystem in access control system
Face information in database subsystem compares, and identifies whether detected object has the permission of entrance, then decide whether to lead to
Row.Method of the present embodiment selection based on subpattern Classification and Identification carry out the identification of face, will extract in target face first
Subregion picture is pre-processed, then with HOG Feature Extraction Technology (Histogram Of Oriented Gradient feature)
To carry out sub- mode region the building of face subpattern, then the subpattern classifier with building lane database compares one by one,
Since influence degree of each region of face to discrimination is different, takes the classification results to each subpattern to do weighting and melt
The method of conjunction finally obtains optimal recognition result.Detailed process is as follows, as shown in Figure 5:
C-1: the subpattern region picture of face to be identified is obtained from face acquisition testing subsystem;
C-2: gaussian filtering and normalized are carried out to picture;
C-3: HOG feature extraction face subpattern is used;
C-4: the classifier that training obtains in 5 subpatterns and face database subsystem by subject face compares,
There is n pattern classifier in model library, then subject face picture then needs to carry out n times Classification and Identification, obtains the n of each subpattern
A classification score;
C-5: classifying to be allocated as Weighted Fusion to each subpattern, is that 5 corresponding subpatterns distribute corresponding weight,
It is weighted the average weighted score i.e. similarity that fusion measures subject face;
C-6: statistics subject face selects similarity maximum the total score of face in face database subsystem,
Again compared with the threshold value being previously set, the identity information of subject face is finally measured, decides whether to pass through.
The present embodiment is based only on the recognition of face of one training sample, greatly reduces the difficulty of acquisition training sample database, makes
The operating mode that hotel passes in and out personnel's verification is more succinct more intelligent, reduces pure manual working and causes to omit.In addition, using with people
The division methods cut out are put on the basis of face key point, and are introduced external human face data collection in training and be trained, and new addition
The method of the similarity in each region of Weighted Fusion improves to higher amplitude single sample training and obtains the accuracy of identification of model.Make
Dynamics is verified increasing hotel disengaging personnel, increase criminal enters hotel's difficulty, improves hotel occupancy personnel safety and refers to
While number, it can also alleviate the operating pressure of staff.
The examples of implementation of the above are only the preferred embodiments of the invention, and implementation model of the invention is not limited with this
It encloses, therefore all shapes according to the present invention, changes made by principle, should all be included within the scope of protection of the present invention.
Claims (5)
1. a kind of hotel based on single sample recognition of face passes in and out personnel management methods, which is characterized in that use and be based only on single sample
The mode of this training pattern only reads the information for moving in people's identity card, while the image initial on foreground by system of checking in
Acquisition subsystem, which acquires, moves in the facial image of people, and by collected facial image and what is read move in people's identity information
It is transferred to the end PC on backstage, processing training then is carried out to collected facial image and is stored into face database subsystem,
To obtain the permission for entering hotel;Whenever the personnel of moving in enter hotel, the face acquisition testing subsystem in access control system will be adopted
Collect and detect the facial image for moving in personnel, identification verifying is carried out by recognition of face subsystem, by verifying, opens door
Prohibit, authentication failed then notifies staff.
2. a kind of hotel based on single sample recognition of face according to claim 1 passes in and out personnel management methods, feature
It is, it is described by acquired image and the end PC moved in people's identity information and be transferred to backstage read, then to acquisition
To image carry out processing training and be stored into face database subsystem detailed process is as follows:
A-1: by acquired image and the end PC moved in people's identity information and be transferred to backstage read;
A-2: the end PC on backstage carries out gaussian filtering to collected face picture, removes the interference of noise, and normalize to finger
Determine size, then demarcates 5 datum marks with MTCNN algorithm and divide subpattern region;
A-3: constructing the face subpattern in 5 regions with HOG feature, negative sample subpattern collection is added, using SVM algorithm to it
It is trained, obtains 5 sub- pattern classifiers of the face, store into face database subsystem.
3. a kind of hotel based on single sample recognition of face according to claim 1 passes in and out personnel management methods, feature
It is, the face acquisition testing subsystem in the access control system acquires and detect the specific of the facial image for moving in personnel
Process is as follows:
B-1: it is acquired from camera review and obtains video frame;
B-2: real-time video picture is converted to by function in OpenCV;
B-3: picture carries out scaling by way of sampling;
B-4: it is trained using the P-NET layer and R-NET layers of MTCNN algorithm;
B-5: it if there is face in picture, obtains human face region using the O-NET layer of MTCNN algorithm and generates key point;
B-6: if finally obtaining multiple faces, select maximum face frame as target face;
B-7: subpattern region is marked off according to five key points in target face.
4. a kind of hotel based on single sample recognition of face according to claim 3 passes in and out personnel management methods, feature
It is, the detailed process of the step B-4 and B-5 are as follows: picture is passed to the P-Net layer of MTCNN algorithm, obtains human face region
The regression vector of candidate window and bounding box, and returned with the bounding box, candidate window is calibrated, non-pole is then passed through
Big value inhibits NMS to merge the candidate frame of high superposed, is then input to R-Net layers, is returned by bounding box with NMS and is removed
The region false-positive, since the network structure and P-Net network structure are variant, more full articulamentums, so
The effect for preferably inhibiting false-positive can be obtained, determines in picture and is input to O-Net layers after having face information again, it is defeated
Final face frame and characteristic point position out.
5. a kind of hotel based on single sample recognition of face according to claim 1 passes in and out personnel management methods, feature
Be, it is described by recognition of face subsystem carry out identification verifying detailed process is as follows:
C-1: the subpattern region picture of face to be identified is obtained from face acquisition testing subsystem;
C-2: gaussian filtering and normalized are carried out to picture;
C-3: HOG feature extraction face subpattern is used;
C-4: the classifier that training obtains in 5 subpatterns and face database subsystem by subject face compares, in mould
There is n pattern classifier in type library, then subject face picture then needs to carry out n times Classification and Identification, obtains n points of each subpattern
Class score;
C-5: classifying to be allocated as Weighted Fusion to each subpattern, is that 5 corresponding subpatterns distribute corresponding weight, passes through
Weighted Fusion measures the average weighted score i.e. similarity of subject face;
C-6: statistics subject face selects similarity maximum the total score of face in face database subsystem, then with
The threshold value being previously set compares, and finally measures the identity information of subject face, decides whether to pass through.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810643177.1A CN109166196A (en) | 2018-06-21 | 2018-06-21 | A kind of hotel's disengaging personnel management methods based on single sample recognition of face |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810643177.1A CN109166196A (en) | 2018-06-21 | 2018-06-21 | A kind of hotel's disengaging personnel management methods based on single sample recognition of face |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109166196A true CN109166196A (en) | 2019-01-08 |
Family
ID=64897180
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810643177.1A Pending CN109166196A (en) | 2018-06-21 | 2018-06-21 | A kind of hotel's disengaging personnel management methods based on single sample recognition of face |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109166196A (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109814717A (en) * | 2019-01-29 | 2019-05-28 | 珠海格力电器股份有限公司 | A kind of home equipment control method, device, control equipment and readable storage medium storing program for executing |
CN110738147A (en) * | 2019-09-28 | 2020-01-31 | 济南轨道交通集团有限公司 | Face recognition system and method for rail transit |
CN111967289A (en) * | 2019-05-20 | 2020-11-20 | 高新兴科技集团股份有限公司 | Uncooperative human face in-vivo detection method and computer storage medium |
CN112734626A (en) * | 2019-10-14 | 2021-04-30 | 成都武侯珍妍医疗美容门诊部有限公司 | Nose virtual shaping method of deep learning model |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103617665A (en) * | 2013-11-26 | 2014-03-05 | 江门市大前门智能门控科技有限公司 | Face recognition type hotel occupancy management system |
CN104766062A (en) * | 2015-04-07 | 2015-07-08 | 广西大学 | Face recognition system and register and recognition method based on lightweight class intelligent terminal |
CN106599863A (en) * | 2016-12-21 | 2017-04-26 | 中国科学院光电技术研究所 | Deep face identification method based on transfer learning technology |
CN107895160A (en) * | 2017-12-21 | 2018-04-10 | 曙光信息产业(北京)有限公司 | Human face detection and tracing device and method |
-
2018
- 2018-06-21 CN CN201810643177.1A patent/CN109166196A/en active Pending
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103617665A (en) * | 2013-11-26 | 2014-03-05 | 江门市大前门智能门控科技有限公司 | Face recognition type hotel occupancy management system |
CN104766062A (en) * | 2015-04-07 | 2015-07-08 | 广西大学 | Face recognition system and register and recognition method based on lightweight class intelligent terminal |
CN106599863A (en) * | 2016-12-21 | 2017-04-26 | 中国科学院光电技术研究所 | Deep face identification method based on transfer learning technology |
CN107895160A (en) * | 2017-12-21 | 2018-04-10 | 曙光信息产业(北京)有限公司 | Human face detection and tracing device and method |
Non-Patent Citations (1)
Title |
---|
张晓林等: "基于深度学习的证件照人脸识别方法", 《计算机系统应用》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109814717A (en) * | 2019-01-29 | 2019-05-28 | 珠海格力电器股份有限公司 | A kind of home equipment control method, device, control equipment and readable storage medium storing program for executing |
CN109814717B (en) * | 2019-01-29 | 2020-12-25 | 珠海格力电器股份有限公司 | Household equipment control method and device, control equipment and readable storage medium |
CN111967289A (en) * | 2019-05-20 | 2020-11-20 | 高新兴科技集团股份有限公司 | Uncooperative human face in-vivo detection method and computer storage medium |
CN110738147A (en) * | 2019-09-28 | 2020-01-31 | 济南轨道交通集团有限公司 | Face recognition system and method for rail transit |
CN110738147B (en) * | 2019-09-28 | 2022-10-14 | 济南轨道交通集团有限公司 | Face recognition system and method for rail transit |
CN112734626A (en) * | 2019-10-14 | 2021-04-30 | 成都武侯珍妍医疗美容门诊部有限公司 | Nose virtual shaping method of deep learning model |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109166196A (en) | A kind of hotel's disengaging personnel management methods based on single sample recognition of face | |
KR101877981B1 (en) | System for recognizing disguised face using gabor feature and svm classifier and method thereof | |
CN101739555B (en) | Method and system for detecting false face, and method and system for training false face model | |
US7215798B2 (en) | Method for forgery recognition in fingerprint recognition by using a texture classification of gray scale differential images | |
CN109558810B (en) | Target person identification method based on part segmentation and fusion | |
CN106203294A (en) | The testimony of a witness unification auth method analyzed based on face character | |
CN105205480B (en) | Human-eye positioning method and system in a kind of complex scene | |
CN104036278B (en) | The extracting method of face algorithm standard rules face image | |
CN106599870A (en) | Face recognition method based on adaptive weighting and local characteristic fusion | |
CN106355138A (en) | Face recognition method based on deep learning and key features extraction | |
CN104504362A (en) | Face detection method based on convolutional neural network | |
KR20080065866A (en) | Method and apparatus for generating face descriptor using extended local binary pattern, and method and apparatus for recognizing face using it | |
CN109697430A (en) | The detection method that working region safety cap based on image recognition is worn | |
CN106169071A (en) | A kind of Work attendance method based on dynamic human face and chest card recognition and system | |
CN108171223A (en) | A kind of face identification method and system based on multi-model multichannel | |
CN105760858A (en) | Pedestrian detection method and apparatus based on Haar-like intermediate layer filtering features | |
CN103530648A (en) | Face recognition method based on multi-frame images | |
CN106650623A (en) | Face detection-based method for verifying personnel and identity document for exit and entry | |
CN109993061A (en) | A kind of human face detection and tracing method, system and terminal device | |
CN105975952A (en) | Beard detection method and system in video image | |
Gale et al. | Evolution of performance analysis of iris recognition system by using hybrid methods of feature extraction and matching by hybrid classifier for iris recognition system | |
CN109492509A (en) | Personal identification method, device, computer-readable medium and system | |
CN110222660B (en) | Signature authentication method and system based on dynamic and static feature fusion | |
CN107392105A (en) | A kind of expression recognition method based on reverse collaboration marking area feature | |
Saeed et al. | Classification of live scanned fingerprints using histogram of gradient descriptor |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190108 |
|
RJ01 | Rejection of invention patent application after publication |