CN105825186A - Identity authentication method for identity card and card holder based on 3D face data - Google Patents
Identity authentication method for identity card and card holder based on 3D face data Download PDFInfo
- Publication number
- CN105825186A CN105825186A CN201610149770.1A CN201610149770A CN105825186A CN 105825186 A CN105825186 A CN 105825186A CN 201610149770 A CN201610149770 A CN 201610149770A CN 105825186 A CN105825186 A CN 105825186A
- Authority
- CN
- China
- Prior art keywords
- data
- face data
- holder
- dimensional
- dimensional face
- 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
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/60—Type of objects
- G06V20/64—Three-dimensional objects
- G06V20/647—Three-dimensional objects by matching two-dimensional images to three-dimensional objects
-
- 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
- G06V40/161—Detection; Localisation; Normalisation
Abstract
The invention discloses an identity authentication method for an identity card and a card holder based on 3D face data. The method comprises the following steps that 2D face data is read from the resident identity card; 3D face data of the card holder is collected, and a mixed data training set is constructed; deep learning training is carried out to obtain all sample features as well as an optimal network parameter; all the sample features serve as input to train a classifier; and the optimal network parameter obtained by training is used to extract features from test data, and the extracted features are placed in the classifier, a classification result is obtained, and whether the identity card is held by the card holder himself/herself is determined. According to the invention, 3D face information is effectively used to meet requirement of identity authentication of the identity card, the identification robustness is improved, and the problem that identification based on 2D face data tends to be interfered by attitude, light, age and other factors is solved.
Description
Technical field
The present invention relates to technical field of information processing, particularly to the homogeneity authentication method of a kind of identity cards based on three-dimensional face data Yu holder.
Background technology
Degree of depth study is a new field in machine learning research, its motivation is to set up, simulate the neutral net that human brain is analyzed learning, the mechanism that it imitates human brain explains data, such as image, sound and text, this technology is widely used to the artificial intelligence field such as speech recognition, recognition of face at present, has promoted the development of application.
The most common recognition of face is both for the data of isomorphism, such as two-dimension human face image and two-dimension human face image comparison, collection in worksite two-dimension human face image is compared with the registration portrait in resident identification card, this traditional recognition methods, affected by factors such as illumination variation, attitudes vibration, change of age, resident identification card compressions, and fail effectively to utilize the three-dimensional information of face, thus discrimination is the highest, have impact on application.
Summary of the invention
It is an object of the invention to overcome the above-mentioned deficiency in the presence of prior art, there is provided a kind of and veritify demand for the resident identification card testimony of a witness, three-dimensional camera collection site face three-dimensional data is used to compare with two-dimension human face data in resident identification card, to reduce external disturbance, improve and identify robustness.
In order to realize foregoing invention purpose, the invention provides techniques below scheme:
Step one: read the two-dimension human face data in resident identification card by resident identification card card reader；
Step 2: gather holder three-dimensional face data by three-dimensional camera；
Step 3: the holder three-dimensional face data collected two-dimension human face data and the three-dimensional camera of the resident identification card in card reader by Face datection algorithm carry out Face datection and location, and are normalized；
Step 4: to the two-dimension human face data after normalized in step 3, three-dimensional face data construct blended data training set, carry out degree of deep learning training, obtain feature and the optimal network parameter of all samples；
Step 5: using the feature of samples all in step 4 as input, trains grader；
Step 6: first test data are carried out the process of described step 3, then with step 4 being trained the optimal network parameter obtained test data are carried out feature extraction, the feature extracted is put into grader, obtains classification results, it is judged that whether identity card is by holding in person.
Preferably, blended data training set described in step 4 comprises two classes, the most positive sample set, negative sample collection, and often organizing data in positive sample set is same personal data information, and negative sample concentrates often group data to be different people data message；Described often group data include the two-dimension human face data after normalized and three-dimensional face data in described step 3.Described three-dimensional face data are face depth map and face texture maps, or are face depth map, decrease the interference problem at light, age etc..
Preferably, the model of described degree of deep learning training is degree of depth convolutional neural networks, using data set as input, utilizes degree of depth convolutional neural networks that input data are carried out feature extraction successively, makes acquisition characteristics of image have more preferable identification ability.
Preferably, described grader is two-value grader, and classification speed is fast.
Compared with prior art, beneficial effects of the present invention: the present invention is directed to the resident identification card testimony of a witness and veritify demand, effectively utilize the three-dimensional information of face, improve and identify robustness, solve the problem that two-dimension human face identification is disturbed by factors such as attitude, light, ages；Use degree of deep learning network to extract face characteristic, make acquisition characteristics of image have more preferable identification ability.
Accompanying drawing explanation
Fig. 1 is the flow chart of the present invention；
Fig. 2 is the positive sample set in the present invention and negative sample collection figure；
Fig. 3 is the flow chart of embodiments of the invention；
Fig. 4 is the flow chart of embodiments of the invention.
Detailed description of the invention
Below in conjunction with test example and detailed description of the invention, the present invention is described in further detail.But this should not being interpreted as, the scope of the above-mentioned theme of the present invention is only limitted to below example, and all technology realized based on present invention belong to the scope of the present invention.
Embodiment
As it is shown in figure 1, identity cards based on three-dimensional face data and the homogeneity authentication method of holder, comprise the following steps:
Step one: read the two-dimension human face data in resident identification card by resident identification card card reader；
Step 2: gather holder three-dimensional face data by three-dimensional camera；
Step step 3: the holder three-dimensional face data collected two-dimension human face data and the three-dimensional camera of the resident identification card in card reader by Face datection algorithm carry out Face datection and location, and are normalized；
Step 4: to the two-dimension human face data after normalized in step 3, three-dimensional face data construct blended data training set, carry out degree of deep learning training, the model of described degree of deep learning training is degree of depth convolutional neural networks, using data set as input, utilize degree of depth convolutional neural networks that input data are carried out feature extraction successively, obtain feature and the optimal network parameter of all samples；
Step 5: using the feature of samples all in step 4 as input, trains two-value grader；
Step 6: first test data are carried out the process of described step 3, then with step 4 being trained the optimal network parameter obtained test data are carried out feature extraction, the feature extracted is put into grader, obtains classification results, it is judged that whether identity card is by holding in person.
As in figure 2 it is shown, practice data set to comprise two classes, the most positive sample set, negative sample collection, often organizing data in positive sample set is same personal data information, and negative sample concentrates often group data to be different people data message；Described often group data include the two-dimension human face data after normalized and three-dimensional face data in described step 3.
As it is shown on figure 3, described three-dimensional face data are face depth map and face texture maps,
Concrete, as shown in Figure 4, described three-dimensional face data can be face depth map, can also effectively utilize the three-dimensional information of face while reducing data volume, improves and identifies robustness.
Claims (6)
1. identity cards based on three-dimensional face data and a homogeneity authentication method for holder, is characterized in that, comprise the following steps:
Step one: read the two-dimension human face data of resident identification card by resident identification card card reader；
Step 2: gathered the three-dimensional face data of holder by three-dimensional camera；
Step 3: the holder three-dimensional face data collected two-dimension human face data and the three-dimensional camera of the resident identification card in card reader by Face datection algorithm carry out Face datection and location, and are normalized；
Step 4: to the two-dimension human face data after normalized in step 3, three-dimensional face data construct blended data training set, carry out degree of deep learning training, obtain feature and the optimal network parameter of all samples；
Step 5: using the feature of samples all in step 4 as input, trains grader；
Step 6: first test data are carried out the process of described step 3, then with step 4 being trained the optimal network parameter obtained test data are carried out feature extraction, the feature extracted is put into grader, obtains classification results, it is judged that whether identity card is by holding in person.
Identity card based on three-dimensional face data the most according to claim 1 and the homogeneity authentication method of holder, it is characterized in that, blended data training set described in step 4 comprises two class data, it is respectively positive sample set, negative sample collection, often organizing data in positive sample set is same personal data information, and negative sample concentrates often group data to be different people data message；Described often group data include the two-dimension human face data after normalized and described three-dimensional face data in described step 3.
Identity card based on three-dimensional face data the most according to claim 1 and the homogeneity authentication method of holder, it is characterized in that, the model of the degree of deep learning training in step 4 is degree of depth convolutional neural networks, using blended data training set as input, utilize degree of depth convolutional neural networks that input data are carried out feature extraction successively.
Identity card based on three-dimensional face data the most according to claim 1 and the homogeneity authentication method of holder, is characterized in that, the two-dimension human face data that test data are holder described in step 6 and three-dimensional face data.
Identity card based on three-dimensional face data the most according to claim 1 and the homogeneity authentication method of holder, is characterized in that, described three-dimensional face data are face depth map and face texture maps, or are face depth map.
Identity card based on three-dimensional face data the most according to claim 1 and the homogeneity authentication method of holder, is characterized in that, described grader is two-value grader.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610149770.1A CN105825186A (en) | 2016-03-16 | 2016-03-16 | Identity authentication method for identity card and card holder based on 3D face data |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610149770.1A CN105825186A (en) | 2016-03-16 | 2016-03-16 | Identity authentication method for identity card and card holder based on 3D face data |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105825186A true CN105825186A (en) | 2016-08-03 |
Family
ID=56523461
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610149770.1A Pending CN105825186A (en) | 2016-03-16 | 2016-03-16 | Identity authentication method for identity card and card holder based on 3D face data |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105825186A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106407914A (en) * | 2016-08-31 | 2017-02-15 | 北京旷视科技有限公司 | Method for detecting human faces, device and remote teller machine system |
| CN108537191A (en) * | 2018-04-17 | 2018-09-14 | 广州云从信息科技有限公司 | A kind of three-dimensional face identification method based on structure light video camera head |
| CN110069968A (en) * | 2018-01-22 | 2019-07-30 | 耐能有限公司 | Face recognition and face recognition method |
| CN110110118A (en) * | 2017-12-27 | 2019-08-09 | 广东欧珀移动通信有限公司 | Dressing recommended method, device, storage medium and mobile terminal |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7127087B2 (en) * | 2000-03-27 | 2006-10-24 | Microsoft Corporation | Pose-invariant face recognition system and process |
| CN102254154A (en) * | 2011-07-05 | 2011-11-23 | 南京大学 | Method for authenticating human-face identity based on three-dimensional model reconstruction |
| CN102779269A (en) * | 2012-06-13 | 2012-11-14 | 合肥工业大学 | Human face identification algorithm based on image sensor imaging system |
| CN102902959A (en) * | 2012-04-28 | 2013-01-30 | 王浩 | Face recognition method and system for storing identification photo based on second-generation identity card |
| CN105426875A (en) * | 2015-12-18 | 2016-03-23 | 武汉科技大学 | Face identification method and attendance system based on deep convolution neural network |
-
2016
- 2016-03-16 CN CN201610149770.1A patent/CN105825186A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7127087B2 (en) * | 2000-03-27 | 2006-10-24 | Microsoft Corporation | Pose-invariant face recognition system and process |
| CN102254154A (en) * | 2011-07-05 | 2011-11-23 | 南京大学 | Method for authenticating human-face identity based on three-dimensional model reconstruction |
| CN102902959A (en) * | 2012-04-28 | 2013-01-30 | 王浩 | Face recognition method and system for storing identification photo based on second-generation identity card |
| CN102779269A (en) * | 2012-06-13 | 2012-11-14 | 合肥工业大学 | Human face identification algorithm based on image sensor imaging system |
| CN105426875A (en) * | 2015-12-18 | 2016-03-23 | 武汉科技大学 | Face identification method and attendance system based on deep convolution neural network |
Non-Patent Citations (5)
| Title |
|---|
| KWANG HO AN等: "Pose-Robust Face Recognition Based on TextureMapping", 《PROCEEDINGS OF THE 17TH IEEE INTERNATIONAL SYMPOSIUM ON ROBOT AND HUMANINTERACTIVE COMMUNICATION》 * |
| 周立等: "《数字测绘技术与数字交通建设》", 30 April 2005, 西安地图出版社 * |
| 杨铁军等: "《产业专利分析报告》", 30 June 2015, 知识产权出版社 * |
| 谢剑斌等: "《视觉感知与智能视频监控》", 31 March 2012, 国防科技大学出版社 * |
| 马燕等: "《二维及三维人脸识别技术》", 31 August 2007, 百家出版社 * |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106407914A (en) * | 2016-08-31 | 2017-02-15 | 北京旷视科技有限公司 | Method for detecting human faces, device and remote teller machine system |
| CN106407914B (en) * | 2016-08-31 | 2019-12-10 | 北京旷视科技有限公司 | Method and device for detecting human face and remote teller machine system |
| CN110110118A (en) * | 2017-12-27 | 2019-08-09 | 广东欧珀移动通信有限公司 | Dressing recommended method, device, storage medium and mobile terminal |
| CN110110118B (en) * | 2017-12-27 | 2021-11-16 | Oppo广东移动通信有限公司 | Dressing recommendation method and device, storage medium and mobile terminal |
| CN110069968A (en) * | 2018-01-22 | 2019-07-30 | 耐能有限公司 | Face recognition and face recognition method |
| CN108537191A (en) * | 2018-04-17 | 2018-09-14 | 广州云从信息科技有限公司 | A kind of three-dimensional face identification method based on structure light video camera head |
| CN108537191B (en) * | 2018-04-17 | 2020-11-20 | 云从科技集团股份有限公司 | Three-dimensional face recognition method based on structured light camera |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN104143079B (en) | The method and system of face character identification | |
| WO2020151489A1 (en) | Living body detection method based on facial recognition, and electronic device and storage medium | |
| CN103426016B (en) | Method and device for authenticating second-generation identity card | |
| CN103593598B (en) | User's on-line authentication method and system based on In vivo detection and recognition of face | |
| CN103116763B (en) | A kind of living body faces detection method based on hsv color Spatial Statistical Character | |
| CN104751108B (en) | Facial image identification device and facial image recognition method | |
| CN103810490B (en) | A kind of method and apparatus for the attribute for determining facial image | |
| CN104123545B (en) | A kind of real-time human facial feature extraction and expression recognition method | |
| CN106446754A (en) | Image identification method, metric learning method, image source identification method and devices | |
| CN109460734B (en) | Video behavior identification method and system based on hierarchical dynamic depth projection difference image representation | |
| CN108229427A (en) | A kind of identity-based certificate and the identity security verification method and system of recognition of face | |
| CN105825186A (en) | Identity authentication method for identity card and card holder based on 3D face data | |
| CN106557726A (en) | A kind of band is mourned in silence the system for face identity authentication and its method of formula In vivo detection | |
| CN107333071A (en) | Video processing method and device, electronic equipment and storage medium | |
| CN104850825A (en) | Facial image face score calculating method based on convolutional neural network | |
| CN106127164A (en) | The pedestrian detection method with convolutional neural networks and device is detected based on significance | |
| CN105740780A (en) | Method and device for human face in-vivo detection | |
| CN105740779A (en) | Method and device for human face in-vivo detection | |
| CN102682309A (en) | Face feature registering method and device based on template learning | |
| CN110796101A (en) | Face recognition method and system of embedded platform | |
| CN103105397A (en) | Painting and calligraphy identification device | |
| CN105956570B (en) | Smiling face's recognition methods based on lip feature and deep learning | |
| CN108985200A (en) | A kind of In vivo detection algorithm of the non-formula based on terminal device | |
| CN105320948A (en) | Image based gender identification method, apparatus and system | |
| CN107526994A (en) | A kind of information processing method, device and mobile terminal |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20160803 |
|
| RJ01 | Rejection of invention patent application after publication |