CN104268585A - Mobile device face recognition method applying two-dimensional principal-element-independent-element comprehensive analysis technology - Google Patents
Mobile device face recognition method applying two-dimensional principal-element-independent-element comprehensive analysis technology Download PDFInfo
- Publication number
- CN104268585A CN104268585A CN201410531181.0A CN201410531181A CN104268585A CN 104268585 A CN104268585 A CN 104268585A CN 201410531181 A CN201410531181 A CN 201410531181A CN 104268585 A CN104268585 A CN 104268585A
- Authority
- CN
- China
- Prior art keywords
- face
- image
- independent
- facial image
- mobile device
- 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
- G06V40/161—Detection; Localisation; Normalisation
- G06V40/166—Detection; Localisation; Normalisation using acquisition arrangements
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
- G06V10/44—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components
- G06V10/443—Local feature extraction by analysis of parts of the pattern, e.g. by detecting edges, contours, loops, corners, strokes or intersections; Connectivity analysis, e.g. of connected components by matching or filtering
- G06V10/449—Biologically inspired filters, e.g. difference of Gaussians [DoG] or Gabor filters
-
- 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)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- Multimedia (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biodiversity & Conservation Biology (AREA)
- Biomedical Technology (AREA)
- Molecular Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Image Analysis (AREA)
Abstract
The invention provides a mobile device face recognition method applying a two-dimensional principal-element-independent-element comprehensive analysis technology. Face recognition of a mobile terminal with a camera is achieved through a 2DPCA-ICA analysis technology. When the mobile device face recognition method is used, the terminal is required to have a photographing function so that face information can be collected, and face recognition is achieved through comparison of the face information through the 2DPCA-ICA analysis technology.
Description
Technical field
The present invention relates to smart identity recognition technology field, specifically a kind of mobile device face identification method using two-dimentional pivot-independent entry Comprehensive Analysis Technique.
Background technology
(1) two-dimentional pivot-independent entry is comprehensively analyzed (2DPCA-ICA)
Tradition independent component analysis (Independent Component Analysis, ICA) be first become vector to ask whitening matrix facial image matrix conversion for recognition of face, then Fixed point algorithm is utilized to ask separation matrix, obtain facial image independence base subspace, thus realize recognition of face.Two-dimensional principal component analysis (Two-dimensional Principle Component Analysis, 2DPCA) facial image matrix conversion need not be become vector, directly utilize two-dimension human face image Matrix Calculating covariance matrix, its eigen vector calculate simplification.2DPCA-ICA, in conjunction with the feature of 2DPCA and ICA, calculates whitening matrix by 2DPCA; Then ICA is utilized to obtain the independent entry of facial image; Then independent base subspace is constructed; The projection properties of last foundation test sample book on independent base subspace realizes recognition of face.
2DPCA is a kind of common method that PARAMETERS IN THE LINEAR MODEL is estimated.Basic thought standardizes to the image array of input, asks its covariance matrix, carry out Eigenvalues Decomposition, chooses wherein larger eigenwert characteristic of correspondence vector and project as direction.Mode card (Card emulation) after projection, is equivalent to the IC-card that adopts RFID technique.Can substitute to swipe the card in a large amount of IC-card (comprising credit card) occasion markets, mass transit card, gate inhibition's control, ticket, admission ticket etc.Under this kind of mode, have a great advantage, that is exactly that card is powered by contactless card reader, even if host's equipment (as mobile phone) does not have electricity can work yet.
In recognition of face, many important informations are included in higher-order statistics.ICA is a kind of decorrelation multi-data processing method based on higher-order statistics.Its basic thought represents a series of stochastic variable with one group of basis function, meanwhile, is statistical iteration or independent as far as possible between each unit.Independent component analysis is one of most effectual way realizing blind source separating.
(2) mobile terminal recognition of face
Face recognition technology is an emerging biological identification technology.It extensively adopts regional characteristics analysis algorithm, computer image processing technology and biostatistics principle are merged in one, utilize computer image processing technology from video, extract portrait unique point, utilize the principle of biostatistics to carry out analysis founding mathematical models, finally realize the confirmation of identity.Along with the universal of the mobile terminal such as mobile phone, panel computer and development, its function from strength to strength, the Newly Sprouted Things such as mobile phone shopping, Mobile banking are accepted gradually, and the safety problem of mobile terminal is also more and more outstanding, and the biological identification technology on mobile terminal is important all the more.
Summary of the invention
The object of this invention is to provide a kind of mobile device face identification method using two-dimentional pivot-independent entry Comprehensive Analysis Technique.
The object of the invention is to realize in the following manner, concrete steps are as follows:
(1) man face image acquiring: gather image by pick-up lens, comprises still image, dynamic image, different positions, different expression aspect all must well be gathered;
(2) Face datection: namely accurate calibration goes out position and the size of face in the picture;
(3) facial image pre-service: the original image that system obtains is owing to being subject to restriction and the random disturbance of various condition, often can not directly use, for facial image, its preprocessing process mainly comprises the light compensation of facial image, greyscale transformation, histogram equalization, normalization, geometry correction, filtering and sharpening;
(4) facial image feature extraction: by 2DPCA-ICA, asks the albefaction of training sample, utilizes Fixed point algorithm to ask separation matrix on this basis, thus obtain independent base subspace according to training sample data;
(5) facial image matching and recognition: by 2DPCA-ICA, the projection properties of training sample in independent base subspace is compared, can recognition of face be realized.
Object beneficial effect of the present invention is: face recognition technology is an emerging biological identification technology.It extensively adopts regional characteristics analysis algorithm, computer image processing technology and biostatistics principle are merged in one, utilize computer image processing technology from video, extract portrait unique point, utilize the principle of biostatistics to carry out analysis founding mathematical models, finally realize the confirmation of identity.Along with the universal of the mobile terminal such as mobile phone, panel computer and development, its function from strength to strength, the Newly Sprouted Things such as mobile phone shopping, Mobile banking are accepted gradually, and the safety problem of mobile terminal is also more and more outstanding, and the biological identification technology on mobile terminal is important all the more.
Accompanying drawing explanation
Fig. 1 is the mobile terminal recognition of face process flow diagram using two-dimentional pivot-independent entry comprehensively to analyze (2DPCA-ICA) technology.
Embodiment
With reference to Figure of description, a kind of mobile device face identification method of two-dimentional pivot-independent entry Comprehensive Analysis Technique that uses of the present invention is described in detail below.
A kind of mobile device face identification method using two-dimentional pivot-independent entry Comprehensive Analysis Technique of the present invention, concrete steps are as follows:
(1) man face image acquiring: gather image by pick-up lens, the aspects such as such as still image, dynamic image, different positions, different expressions can well be gathered;
(2) Face datection: namely accurate calibration goes out position and the size of face in the picture;
(3) facial image pre-service: the original image that system obtains is owing to being subject to restriction and the random disturbance of various condition, often can not directly use, for facial image, its preprocessing process mainly comprises the light compensation of facial image, greyscale transformation, histogram equalization, normalization, geometry correction, filtering and sharpening etc.;
(4) facial image feature extraction: by 2DPCA-ICA, asks the albefaction of training sample, utilizes Fixed point algorithm to ask separation matrix on this basis, thus obtain independent base subspace according to training sample data;
(5) facial image matching and recognition: by 2DPCA-ICA, the projection properties of the projection properties of training sample in independent base subspace and training sample is compared, can recognition of face be realized.
Except the technical characteristic described in instructions, be the known technology of those skilled in the art.
Claims (1)
1. use a mobile device face identification method for two-dimentional pivot-independent entry Comprehensive Analysis Technique, it is characterized in that, concrete steps are as follows:
(1) man face image acquiring: gather image by pick-up lens, comprises still image, dynamic image, different positions, different expression aspect all must well be gathered;
(2) Face datection: namely accurate calibration goes out position and the size of face in the picture;
(3) facial image pre-service: the original image that system obtains is owing to being subject to restriction and the random disturbance of various condition, often can not directly use, for facial image, its preprocessing process mainly comprises the light compensation of facial image, greyscale transformation, histogram equalization, normalization, geometry correction, filtering and sharpening;
(4) facial image feature extraction: by 2DPCA-ICA, asks the albefaction of training sample, utilizes Fixed point algorithm to ask separation matrix on this basis, thus obtain independent base subspace according to training sample data;
(5) facial image matching and recognition: by 2DPCA-ICA, the projection properties of training sample in independent base subspace is compared, can recognition of face be realized.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410531181.0A CN104268585A (en) | 2014-10-10 | 2014-10-10 | Mobile device face recognition method applying two-dimensional principal-element-independent-element comprehensive analysis technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410531181.0A CN104268585A (en) | 2014-10-10 | 2014-10-10 | Mobile device face recognition method applying two-dimensional principal-element-independent-element comprehensive analysis technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN104268585A true CN104268585A (en) | 2015-01-07 |
Family
ID=52160105
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410531181.0A Pending CN104268585A (en) | 2014-10-10 | 2014-10-10 | Mobile device face recognition method applying two-dimensional principal-element-independent-element comprehensive analysis technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN104268585A (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030169908A1 (en) * | 2002-03-04 | 2003-09-11 | Samsung Electronics Co., Ltd. | Method and apparatus of recognizing face using component-based 2nd-order principal component analysis (PCA)/independent component analysis (ICA) |
| CN1975759A (en) * | 2006-12-15 | 2007-06-06 | 中山大学 | Human face identifying method based on structural principal element analysis |
-
2014
- 2014-10-10 CN CN201410531181.0A patent/CN104268585A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20030169908A1 (en) * | 2002-03-04 | 2003-09-11 | Samsung Electronics Co., Ltd. | Method and apparatus of recognizing face using component-based 2nd-order principal component analysis (PCA)/independent component analysis (ICA) |
| CN1975759A (en) * | 2006-12-15 | 2007-06-06 | 中山大学 | Human face identifying method based on structural principal element analysis |
Non-Patent Citations (2)
| Title |
|---|
| 甘俊英等: "2DPCA-ICA算法在人脸识别中的应用", 《电路与系统学报》 * |
| 贾莹: "基于PCA的人脸识别", 《中国优秀硕士学位论文全文数据库 信息科技辑》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103902977B (en) | Face identification method and device based on Gabor binary patterns | |
| EP2608108A1 (en) | Face feature vector construction | |
| CN102254188B (en) | Palmprint recognizing method and device | |
| WO2014210576A2 (en) | Hierarchical classification in credit card data extraction | |
| CN104134061A (en) | Number gesture recognition method for support vector machine based on feature fusion | |
| CN107430678A (en) | Use the inexpensive face recognition of Gauss received field feature | |
| CN102214299A (en) | Method for positioning facial features based on improved ASM (Active Shape Model) algorithm | |
| Zhang et al. | Hand-based single sample biometrics recognition | |
| HN et al. | Human Facial Expression Recognition from static images using shape and appearance feature | |
| Jillela et al. | Iris segmentation for challenging periocular images | |
| KR20180090072A (en) | Device and method to recognize iris | |
| CN104346883A (en) | Point of sale (POS) device capable of detecting customer | |
| CN114550212A (en) | Goat face detection and identification method based on lightweight model | |
| CN113449704A (en) | Face recognition model training method and device, electronic equipment and storage medium | |
| Kwaśniewska et al. | Face detection in image sequences using a portable thermal camera | |
| CN103136546A (en) | Multi-dimension authentication method and authentication device of on-line signature | |
| CN104268585A (en) | Mobile device face recognition method applying two-dimensional principal-element-independent-element comprehensive analysis technology | |
| Vijayarani et al. | Facial feature extraction based on FPD and GLCM algorithms | |
| Brown | Deep face-iris recognition using robust image segmentation and hyperparameter tuning | |
| CN111428670B (en) | Face detection method, face detection device, storage medium and equipment | |
| CN107392223A (en) | A kind of Adaboost is the same as the NCC complete wheat head recognition methods being combined and system | |
| CN112580395A (en) | Depth information-based 3D face living body recognition method, system, device and medium | |
| Gunasekar et al. | Face detection on distorted images using perceptual quality-aware features | |
| CN111723612A (en) | Face recognition and face recognition network training method and device, and storage medium | |
| Ridwan et al. | Performance comparison between principal component analysis and linear discriminant analysis in a gender recognition system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20150107 |
|
| WD01 | Invention patent application deemed withdrawn after publication |