CN108182422A - Multi-parameter identity identification method - Google Patents
Multi-parameter identity identification method Download PDFInfo
- Publication number
- CN108182422A CN108182422A CN201810077118.2A CN201810077118A CN108182422A CN 108182422 A CN108182422 A CN 108182422A CN 201810077118 A CN201810077118 A CN 201810077118A CN 108182422 A CN108182422 A CN 108182422A
- Authority
- CN
- China
- Prior art keywords
- image
- face
- eye
- carried out
- human eye
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2411—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on the proximity to a decision surface, e.g. support vector machines
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/34—Smoothing or thinning of the pattern; Morphological operations; Skeletonisation
-
- 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
-
- 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
- G06V10/60—Extraction of image or video features relating to illumination properties, e.g. using a reflectance or lighting model
-
- 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
- G06V40/168—Feature extraction; Face representation
-
- 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
- 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
- G06V40/18—Eye characteristics, e.g. of the iris
-
- 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
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/193—Preprocessing; Feature extraction
-
- 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
- G06V40/18—Eye characteristics, e.g. of the iris
- G06V40/197—Matching; Classification
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Health & Medical Sciences (AREA)
- Human Computer Interaction (AREA)
- General Health & Medical Sciences (AREA)
- Oral & Maxillofacial Surgery (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Ophthalmology & Optometry (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Software Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Collating Specific Patterns (AREA)
Abstract
It is a primary object of the present invention to provide a kind of a kind of physical characteristics collecting method for overcoming human individual's similitude and mutability, in particular, provide a kind of multi-parameter identity identification method, particular by the identification added in face recognition process to eye, eye detection and Pupil diameter, and respective handling is carried out to image, to achieve the purpose that accurate recognition of face.
Description
Technical field
The invention belongs to physical characteristics collecting fields, and in particular to a kind of multi-parameter identity identification method.
Background technology
Living things feature recognition and acquisition technique are exactly, contour by computer and various sensors and biostatistics principle
Technological means are intimately associated, using human body intrinsic physiological property and behavioural characteristic, to carry out the identification of personal identification.Physiology is special
Levy it is inherent, it is mostly geneogenous；Behavioural characteristic is then that custom makes so, mostly posteriority.Physiological characteristic and behavior is special
Sign is referred to as biological characteristic.There is generality, uniqueness, measurability, stability, and right for the biological characteristic of identity authentication
Human body fanout free region largely improves convenience and the safety of certification, overcome it is traditional based on password, password,
The deficiencies of various complicated, easy to be lost easy forgetting is easily attacked present in the authentication of card etc., therefore at present, biological characteristic is known
Not and acquisition refers to every field extensively.
Existing frequently-used biological characteristic has：Fingerprint recognition, personal recognition refer to hand vein recognition, vena metacarpea identification, face knowledge
Not, iris recognition, eye recognition, voice recognition etc..At present, fingerprint recognition, recognition of face, eye recognition are using the most
Extensive living things feature recognition and acquisition technique.The successful key of face identification method is that the core for whether possessing tip is calculated
Method, and make recognition result that there is practical discrimination and recognition speed；" face identification system " is integrated with artificial intelligence, machine
A variety of professional techniques such as identification, machine learning, model theory, expert system, Computer Vision, while need to combine at median
The theory of reason is with realizing.
However, for face recognition algorithms, there is also many technological difficulties, be first difference between Different Individual not
Greatly, the structure of all people's face is all similar or even construction profile of human face is all much like.In this way the characteristics of, is for utilizing people
Face carries out positioning and is advantageous, but is unfavorable for distinguishing human individual using face.Secondly, the shape of face is very unstable
Fixed, people can generate many expressions by the variation of face, and in different viewing angles, the visual pattern of face also differs very
Greatly, in addition, recognition of face is also illuminated by the light many overcover (examples of condition (such as day and night, indoor and outdoors etc.) face
Such as mask, sunglasses, hair, beard) many factors such as age influence.
Invention content
In view of above analysis, it is a primary object of the present invention to overcome drawbacks described above, provides one kind and overcomes human individual's phase
Like property and a kind of physical characteristics collecting method of mutability, a kind of multi-parameter identity identification method is in particular, provided, specifically
By adding in the identification to eye, eye detection and Pupil diameter in face recognition process and carrying out corresponding position to image
Reason, achievees the purpose that accurate recognition of face.
The purpose of the present invention is what is be achieved through the following technical solutions.
A kind of physical characteristics collecting method, includes the following steps：
1st, Nogata normalized is carried out to the face image of input；
2nd, human face region is obtained using Face datection category division device；
3rd, eyes are positioned by eye detection and pupil positioning method；
4th, human face posture correction is carried out to input picture and template is handled, obtain face effective coverage；
5th, feature extraction is carried out with 8 × 8 sample rate to face effective coverage, obtains the spy corresponding to face effective coverage
Sign.
Further, normalized includes：
(1) rotation of image is carried out so that the line of left eye and right eye keeps horizontal；
(2) it according to human face's proportionate relationship, carries out image and cuts.
(3) image scaling processing is carried out, obtains the normalized image of unified size, it is specified that the size of image is 128 × 128
Pixel makes the distance between two for 64 pixel fixed length.
Further, the third step further includes following steps：
Human eye detection, human eye feature extraction, the detection of human eye cascade classifier, human eye area positioning, chroma space, pupil
Hole centralized positioning.
Wherein, human eye feature behaviour eye is different from the notable feature of other organs of face, and human eye is realized using integral image
The quick calculating of feature, human eye cascade classifier, as Weak Classifier, pass through several simplification of training using simplifying support vector machine
Support vector machines is as strong classifier.
Wherein, pupil center's positioning includes detecting reflection light point from left and right eye region, utilizes position and luminance information
The detection of eyes block is carried out, the higher connection block of brightness is deleted from left and right eye region, selection is positioned at the connection of extreme lower position
Block is as eyes block, if not detecting reflection light point, carries out eyes positioning with the brightness value of pixel, utilizes eyes block
Boundary information divides gray scale eye image from gray level image.
Wherein, pupil center's positioning further includes following steps：Chroma space is carried out, retains luminance component, obtains people
The luminance picture in Vitrea eye domain, enhances luminance picture into column hisgram linear equalization and contrast, and mill is covered to eye areas implementation
Processing, eliminating non-pupil region influences；Threshold transformation, and the image after threshold transformation is corroded and expansion process, to upper
Two-value human eye area of stating that treated is implemented Gauss and is filtered with median smoothing, and threshold transformation is carried out again to the image after smooth,
Edge detection is carried out again, and ellipse fitting simultaneously detects the circle in profile, and the circle of detection radius maximum obtains the center of pupil.
Further, the feature extraction of above-mentioned 5th step includes facial image is calculated as below：
Wherein,
Wherein,X, y represent facial image pixel
Coordinate value, u=0,1 ..., 7, K represent sum, v for calculate the factor, v=0,1 ..., 4, k, σ be window function parameter.
Technical scheme of the present invention has the following advantages：
A kind of a kind of physical characteristics collecting method for overcoming human individual's similitude and mutability is provided, is in particular, provided
A kind of multi-parameter identity identification method, particular by adding in identification to eye in face recognition process, eye detection and
Pupil diameter and to image carry out respective handling, achieve the purpose that accurate recognition of face..
Description of the drawings
Fig. 1 shows flow chart according to the method for the present invention.
Specific embodiment
As shown in Figure 1, a kind of physical characteristics collecting method, includes the following steps：
1st, Nogata normalized is carried out to the face image of input；
2nd, human face region is obtained using Face datection category division device；
3rd, eyes are positioned by eye detection and pupil positioning method；
4th, human face posture correction is carried out to input picture and template is handled, obtain face effective coverage；
5th, feature extraction is carried out with 8 × 8 sample rate to face effective coverage, obtains the spy corresponding to face effective coverage
Sign.
Further, normalized includes：
(1) rotation of image is carried out so that the line of left eye and right eye keeps horizontal；
(2) it according to human face's proportionate relationship, carries out image and cuts.
(3) image scaling processing is carried out, obtains the normalized image of unified size, it is specified that the size of image is 128 × 128
Pixel makes the distance between two for 64 pixel fixed length.
Further, the third step further includes following steps：
Human eye detection, human eye feature extraction, the detection of human eye cascade classifier, human eye area positioning, chroma space, pupil
Hole centralized positioning.
Wherein, human eye feature behaviour eye is different from the notable feature of other organs of face, and human eye is realized using integral image
The quick calculating of feature, human eye cascade classifier, as Weak Classifier, pass through several simplification of training using simplifying support vector machine
Support vector machines is as strong classifier.
Wherein, pupil center's positioning includes detecting reflection light point from left and right eye region, utilizes position and luminance information
The detection of eyes block is carried out, the higher connection block of brightness is deleted from left and right eye region, selection is positioned at the connection of extreme lower position
Block is as eyes block, if not detecting reflection light point, carries out eyes positioning with the brightness value of pixel, utilizes eyes block
Boundary information divides gray scale eye image from gray level image.
Wherein, pupil center's positioning further includes following steps：Chroma space is carried out, retains luminance component, obtains people
The luminance picture in Vitrea eye domain, enhances luminance picture into column hisgram linear equalization and contrast, and mill is covered to eye areas implementation
Processing, eliminating non-pupil region influences；Threshold transformation, and the image after threshold transformation is corroded and expansion process, to upper
Two-value human eye area of stating that treated is implemented Gauss and is filtered with median smoothing, and threshold transformation is carried out again to the image after smooth,
Edge detection is carried out again, and ellipse fitting simultaneously detects the circle in profile, and the circle of detection radius maximum obtains the center of pupil.
Further, the feature extraction of above-mentioned 5th step includes facial image is calculated as below：
Wherein,
Wherein,X, y represent facial image pixel
Coordinate value, u=0,1 ..., 7, K represent sum, v for calculate the factor, v=0,1 ..., 4, k, σ be window function parameter.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all essences in the present invention
All any modification, equivalent and improvement made within refreshing and principle etc., should all be included in the protection scope of the present invention.
Claims (4)
1. a kind of multi-parameter identity identification method, includes the following steps：
(1) Nogata normalized is carried out to the face image of input；
(2) human face region is obtained using Face datection category division device；
(3) eyes are positioned by eye detection and pupil positioning method；
(4) human face posture correction is carried out to input picture and template is handled, obtain face effective coverage；
(5) feature extraction is carried out with 8 × 8 sample rate to face effective coverage, obtains the feature corresponding to face effective coverage.
2. multi-parameter identity identification method as described in claim 1, the normalized include：
A. the rotation of image is carried out so that the line of left eye and right eye keeps horizontal；
B. it according to human face's proportionate relationship, carries out image and cuts.
C. image scaling processing is carried out, obtains the normalized image of unified size, it is specified that the size of image is 128 × 128 pixels
Point makes the distance between two for 64 pixel fixed length.
3. multi-parameter identity identification method as described in claim 1, described (3) step further include following steps：
In human eye detection, human eye feature extraction, the detection of human eye cascade classifier, human eye area positioning, chroma space, pupil
The heart positions；
Wherein, human eye feature behaviour eye is different from the notable feature of other organs of face, and human eye feature is realized using integral image
Quick calculating, human eye cascade classifier as Weak Classifier, passes through several simplified supports of training using simplifying support vector machine
Vector machine is as strong classifier；
Wherein, pupil center's positioning includes detecting reflection light point from left and right eye region, is carried out using position and luminance information
The detection of eyes block, deletes the higher connection block of brightness from left and right eye region, and selection is made positioned at the connection block of extreme lower position
For eyes block, if not detecting reflection light point, eyes positioning is carried out with the brightness value of pixel, utilizes the boundary of eyes block
Information divides gray scale eye image from gray level image；
Wherein, pupil center's positioning further includes following steps：Chroma space is carried out, retains luminance component, obtains human eye area
The luminance picture in domain, enhances luminance picture into column hisgram linear equalization and contrast, and mill processing is covered to eye areas implementation,
Eliminating non-pupil region influences；Threshold transformation, and the image after threshold transformation is corroded and expansion process, to above-mentioned processing
Two-value human eye area afterwards is implemented Gauss and is filtered with median smoothing, and threshold transformation is carried out again, then carry out to the image after smooth
Edge detection, ellipse fitting simultaneously detect the circle in profile, and the circle of detection radius maximum obtains the center of pupil.
4. multi-parameter identity identification method as described in claim 1, the feature extraction of above-mentioned (5) step is included to face figure
As being calculated as below：
Wherein,
Wherein,X, y represent the coordinate of facial image pixel
Value, u=0,1 ..., 7, K represent sum, and v is to calculate the factor, v=0,1 ..., 4, k, σ is the parameter of window function.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810077118.2A CN108182422A (en) | 2018-01-26 | 2018-01-26 | Multi-parameter identity identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810077118.2A CN108182422A (en) | 2018-01-26 | 2018-01-26 | Multi-parameter identity identification method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108182422A true CN108182422A (en) | 2018-06-19 |
Family
ID=62551428
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810077118.2A Pending CN108182422A (en) | 2018-01-26 | 2018-01-26 | Multi-parameter identity identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108182422A (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103619232A (en) * | 2011-06-21 | 2014-03-05 | 郑夏哲 | Apparatus for capturing image of anterior part of iris and medical monitoring system using smart phone |
| CN105205480A (en) * | 2015-10-31 | 2015-12-30 | 潍坊学院 | Complex scene human eye locating method and system |
-
2018
- 2018-01-26 CN CN201810077118.2A patent/CN108182422A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103619232A (en) * | 2011-06-21 | 2014-03-05 | 郑夏哲 | Apparatus for capturing image of anterior part of iris and medical monitoring system using smart phone |
| CN105205480A (en) * | 2015-10-31 | 2015-12-30 | 潍坊学院 | Complex scene human eye locating method and system |
Non-Patent Citations (2)
| Title |
|---|
| 宋加涛: "基于二值边缘图像的眼睛定位和人脸识别", 《中国优秀博硕士学位论文全文数据库(博士) 信息科技辑》 * |
| 李外云: "基于ARM架构的嵌入式人脸识别技术研究", 《中国优秀博硕士学位论文全文数据库(博士) 信息科技辑》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105447466B (en) | A kind of identity integrated recognition method based on Kinect sensor | |
| CN104123543B (en) | A kind of eye movement recognition methods based on recognition of face | |
| CN101359365B (en) | Iris positioning method based on maximum between-class variance and gray scale information | |
| CN103761519B (en) | Non-contact sight-line tracking method based on self-adaptive calibration | |
| US8655029B2 (en) | Hash-based face recognition system | |
| JP2021034035A (en) | System, method, and device for intelligent vehicle loaded fatigue detection based on facial discrimination | |
| CN106980852B (en) | Based on Corner Detection and the medicine identifying system matched and its recognition methods | |
| CN108053615A (en) | Driver tired driving condition detection method based on micro- expression | |
| CN106778664A (en) | The dividing method and its device of iris region in a kind of iris image | |
| Burge et al. | Ear biometrics for machine vision | |
| CN103902958A (en) | Method for face recognition | |
| CN104794693B (en) | A kind of portrait optimization method of face key area automatic detection masking-out | |
| CN105138954A (en) | Image automatic screening, query and identification system | |
| CN106503644B (en) | Glasses attribute detection method based on edge projection and color characteristic | |
| CN106570447B (en) | Based on the matched human face photo sunglasses automatic removal method of grey level histogram | |
| CN107844736A (en) | iris locating method and device | |
| CN104794449B (en) | Gait energy diagram based on human body HOG features obtains and personal identification method | |
| CN106980819A (en) | Similarity judgement system based on human face five-sense-organ | |
| Singh et al. | Face detection and eyes extraction using sobel edge detection and morphological operations | |
| CN106599785A (en) | Method and device for building human body 3D feature identity information database | |
| CN109409298A (en) | A kind of Eye-controlling focus method based on video processing | |
| CN111178130A (en) | Face recognition method, system and readable storage medium based on deep learning | |
| CN107480586A (en) | Bio-identification photo bogus attack detection method based on human face characteristic point displacement | |
| CN108446642A (en) | A kind of Distributive System of Face Recognition | |
| CN108288040A (en) | Multi-parameter face identification system based on face contour |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180619 |