CN103793692A - Low-resolution multi-spectral palm print and palm vein real-time identity recognition method and system - Google Patents
Low-resolution multi-spectral palm print and palm vein real-time identity recognition method and system Download PDFInfo
- Publication number
- CN103793692A CN103793692A CN201410043629.4A CN201410043629A CN103793692A CN 103793692 A CN103793692 A CN 103793692A CN 201410043629 A CN201410043629 A CN 201410043629A CN 103793692 A CN103793692 A CN 103793692A
- Authority
- CN
- China
- Prior art keywords
- image
- metacarpus
- spectrum
- module
- light source
- 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
Images
Landscapes
- Collating Specific Patterns (AREA)
Abstract
The invention discloses a low-resolution multi-spectral palm print and palm vein real-time identity recognition method and system. Palm images are collected by the system under the condition of five spectrums, and complementarity of multi-spectrum image information is fully utilized to improve the system recognition rate; meanwhile, palm vein information is collected under the condition of near infrared spectrums so that the system can have the living body detection ability and the counterfeit attack preventing ability of the system can be improved; characteristic extraction speed and other postprocessing speed are improved through the down sampling technology based on bicubic interpolation, and storage space of a characteristic template is saved; characteristic extraction is carried out through a multi-scale multi-directional filter, the influence of lighting changes on characteristic extraction is reduced, and the robustness of the system is improved; a characteristic matrix is coded through a hash table, and system matching speed is further improved; the recognition rate of the system is further improved through the unique fraction-level multi-spectral characteristic fusion method. The system has the advantages of being high in resolution ratio, high in recognition speed, good in stability and expansibility, resistant to counterfeit attack and the like.
Description
Technical field
The present invention relates to the technical field of living things feature recognition, particularly relate to low resolution multi-light spectrum palm print, the real-time personal identification method of vena metacarpea and system.
Background technology
Identification is the important component part of mankind's commercial production, business activity and daily life.Conventional means of identification comprises the traditional approachs such as key, smart card and password at present.Key and smartcard identification popularity are high, but easily lose and copy; Password is easy-to-use but be easy to forget and crack.Traditional identification mode cannot adapt to human being's production, living needs, and therefore, living things feature recognition method is arisen at the historic moment.
Living things feature recognition refers to that computing machine utilizes people's physiology or the technology that behavioural characteristic is carried out personal identification evaluation.People's research at present and the biometric discrimination method using mainly contain fingerprint recognition, recognition of face, iris recognition, palmmprint identification etc.
Fingerprint recognition is living things feature recognition method the earliest, and it is with a long history, easily realizes.The subject matter that fingerprint identification method exists is: fingerprint is the outer layer feature of health, easily copying and forging, damage.And fingerprint image region is little, the quantity of information comprising is few, causes its discrimination on the low side, and registration database is little, limits its large-scale application.In addition, finger overdrying, cross wet and foul etc. and easily cause fingerprint image fuzzy and cannot normally compare.
Face recognition application is extensive, its feature that can be used for identification comprises eye, nose, mouth, eyebrow, facial contour and position relationship etc., there is " non-infringement ", can be used for the active search of specific personage under public arena, also can be used as the important component part of multi-mode biometric feature identification.Its shortcoming is that accuracy of identification is low, and affected by environment large, practicality is not strong.
Due to iris feature abundant information, almost constant throughout one's life, so iris recognition is that in various living things feature recognition methods, error rate is minimum, it is the identity recognizing technology that high-end safety equipment adopt always.But compared with other biological recognition technology, its equipment complexity, costliness, and also identification time needs identified person to cooperate with on one's own initiative, and fixing face focusing pupil, its accessibility is the poorest.
Palmmprint identification is a kind of relatively new biometrics identification technology.Palmprint image comprises the abundant information characteristics such as palm main line, wrinkle, tiny texture, ridge tip, bifurcation, and these features are clear, stable.And less demanding to image resolution ratio when system identification, palm-print image capture is also relatively easy, convenient and swift, is a kind of non-offensive recognition methods, and user is more acceptant.But with respect to fingerprint image, palmprint image is much bigger, this brings many difficulties to image characteristics extraction, coupling and storage, can not guarantee recognition system requirement of real-time, and single spectrum Palm Print Recognition System can not prevent bogus attack.
Vena metacarpea belongs to the blood vessel feature of inside of human body, has good uniqueness, stability; The not problems affect such as vulnerable to pollution, wearing and tearing, aging, scar, vein image acquisition process is also very friendly, easily guarantees that identifying carries out smoothly; And vein belongs to people's internal feature, there is live body, therefore cannot copy and steal by technological means, there is good security.But also there are some shortcomings in vena metacarpea identification, as being positioned at because of vein under shallow-layer skin, image acquisition is compared with palmmprint difficulty, equipment is had to specific (special) requirements, and equipment relative complex, is difficult to miniaturization, manufacturing cost is relatively high, and image definition is not high, therefore needs more complicated image Processing Algorithm.
Identify shortcoming separately based on palmmprint, vena metacarpea, although the recognition methods of three-dimensional palm print palm shape can be used for solving some problem wherein, expensive and heavy device, makes it be difficult to be applied in practical application.One of scheme of dealing with problems is to adopt the imaging of multi-light spectrum palm print vena metacarpea, under multiple spectrum condition, catches image.Existing multispectral identification system imaging resolution is generally greater than 300DPI, has high-resolution image, but high-definition picture feature extraction can not meet again system real time requirement.
Summary of the invention
For overcoming the existing problem of prior art, the object of the present invention is to provide low resolution multi-light spectrum palm print, the real-time personal identification method of vena metacarpea and system, can meet identification requirement, when improving, accelerates recognition performance matching speed, the storage space of saving compressive features code also meets system real time function simultaneously.
The technical solution used in the present invention is:
Low resolution multi-light spectrum palm print, the real-time personal identification method of vena metacarpea, comprise registration phase and cognitive phase.
Registration phase comprises:
A. gather metacarpus image to be registered, described metacarpus image is included in the five width images that gather under white light, ruddiness, green glow, blue light, near infrared spectrum;
B. metacarpus image to be registered is carried out to ROI extraction, and adopt two cube interpolation to carry out down-sampling to the ROI image of gained;
C. adopt multiple dimensioned Multi-aspect filtering device to carry out feature extraction to the ROI image obtaining, obtain the eigenvector of five groups of corresponding different spectrum, and eigenvector is encoded, generating feature template is also stored in property data base;
Cognitive phase comprises:
A. gather metacarpus image to be identified, described metacarpus image is included in the five width images that gather under white light, ruddiness, green glow, blue light, near infrared spectrum;
B. metacarpus image to be identified is carried out to ROI extraction, and adopt two cube interpolation to carry out down-sampling to the ROI image of gained;
C. adopt multiple dimensioned Multi-aspect filtering device to carry out feature extraction to the ROI image obtaining, obtain the eigenvector of five groups of corresponding different spectrum, and eigenvector is encoded, generate input feature vector;
D. input feature vector and the feature templates being stored in property data base are carried out to single spectrum characteristic matching correspondingly, five coupling marks that obtain carry out mark level weight and merge, finally adopt nearest neighbor algorithm to carry out decision-making according to merging mark, obtain recognition result.
Further, described metacarpus image is carried out also comprising pre-service and reference frame location before ROI extraction, wherein said pre-service comprises binary conversion treatment and morphology processing, and described morphology processing comprises Image erosion, expansion, closed operation; Reference frame location comprises: from binary image, extract the contour curve of palm and finger, and determine the reference frame of image by Harris angular-point detection method.
Further, the described step that ROI image is carried out to feature extraction comprises: adopt the logical pyramid wave filter of non-lower sampling band and down-sampled images to carry out convolution, output response after convolution is carried out convolution to bank of filters from all directions with non-lower sampling again, finally in eight directions, adopts competitive way to carry out maximal value coding to wave filter output response and forms 0 or 1 binary features vector.
Further, described template characteristic is stored in property data base with Hash table form.
The present invention also provides low resolution multi-light spectrum palm print, the real-time identification system of vena metacarpea, comprising:
Image capture module, described image capture module comprises multispectral active light source, ccd image inductor, and the control module being connected with multispectral active light source;
Image pretreatment module, the input end of described image pretreatment module is connected with the output terminal of ccd image inductor, carries out pre-service, reference frame location, ROI extraction, down-sampling processing for the metacarpus image that ccd image inductor is collected;
Characteristic extracting module, the input end of described characteristic extracting module is connected with the output terminal of image pretreatment module, for the pretreated metacarpus image of process is carried out to feature extraction;
Memory module, described memory module is provided with property data base, is connected with the output terminal of characteristic extracting module, the template characteristic of obtaining for storing registration phase;
Recognition decision module, described recognition decision module is connected with characteristic extracting module, property data base, for input feature vector to be identified and template characteristic are carried out to single spectrum characteristic matching, and the matching result of different spectrum is carried out to the fusion of mark level weight, finally adopt nearest neighbor algorithm to carry out decision-making according to merging mark, and then obtain recognition result.
Further, described multispectral active light source comprises around ccd image inductor alternatively distributed white light source, red-light source, green-light source, blue light source, near infrared ray light source successively ringwise, and described control module is for controlling the bright dark in turn of each light source.
Low resolution multi-light spectrum palm print provided by the invention, the real-time personal identification method of vena metacarpea and system mainly have following beneficial effect:
(1) gather the metacarpus image under five kinds of spectrum, based on Multispectral Image Fusion Methods, make full use of multispectral image information, improve system recognition rate;
(2) adopt the down-sampling technology based on two cubes of interpolation, improve feature extraction speed, matching speed, save feature templates storage space, recognition speed is accelerated, guarantee system real time requirement, reduce system cost;
(3) adopt multiple dimensioned Multi-aspect filtering device to carry out feature extraction, reduce the impact of illumination variation on feature extraction;
(4) under near infrared light spectrum, collect the vena metacarpea information of palm, make system there is live body detectability, improve the anti-bogus attack ability of system.
Accompanying drawing explanation
Below in conjunction with accompanying drawing and example, the present invention will be further described.
Fig. 1 is low resolution multi-light spectrum palm print of the present invention, the real-time personal identification method of vena metacarpea and the main flow process of System Implementation;
Fig. 2 is the chief component module of low resolution multi-light spectrum palm print of the present invention, the real-time personal identification method of vena metacarpea and system;
Fig. 3 is the metacarpus image pretreatment process of low resolution multi-light spectrum palm print of the present invention, the real-time personal identification method of vena metacarpea and system;
Fig. 4 is the multiple dimensioned Multi-aspect filtering device stack features leaching process of low resolution multi-light spectrum palm print of the present invention, the real-time personal identification method of vena metacarpea and system;
Fig. 5 is the identifying detailed process of low resolution multi-light spectrum palm print of the present invention, the real-time personal identification method of vena metacarpea and system.
Embodiment
Below in conjunction with accompanying drawing and instantiation, the present invention is described in further details:
With reference to Fig. 1, the main flow process of low resolution multi-light spectrum palm print of the present invention, the real-time personal identification method of vena metacarpea and System Implementation comprises: (1) gathers the image that comprises palmmprint and vena metacarpea information under multispectral active light source; (2) binaryzation to metacarpus image, morphology processing, ROI extract and two cubes of interpolation down-samplings; (3) multiple spectrum image ROI is carried out to multiple dimensioned Multi-aspect filtering device group and carries out feature extraction, obtain respectively individual features, and with Hash table to extract feature encode; (4) respectively the feature obtaining under different spectrum pictures is mated, obtain mating mark, take mark level fusing method to merge; (5) according to merging mark, adopt arest neighbors decision-making technique to obtain recognition result.
Particularly, personal identification method of the present invention comprises registration phase and cognitive phase.
Wherein registration phase comprises:
A. gather metacarpus image to be registered, described metacarpus image is included in the five width images that gather under white light, ruddiness, green glow, blue light, near infrared spectrum;
B. metacarpus image to be registered is carried out to ROI extraction, and adopt two cube interpolation to carry out down-sampling to the ROI image of gained;
C. adopt multiple dimensioned Multi-aspect filtering device group to carry out feature extraction to the ROI image obtaining, obtain the eigenvector of five groups of corresponding different spectrum, and eigenvector is encoded, generating feature template is also stored in property data base;
Cognitive phase comprises:
A. gather metacarpus image to be identified, described metacarpus image is included in the five width images that gather under white light, ruddiness, green glow, blue light, near infrared spectrum;
B. metacarpus image to be identified is carried out to ROI extraction, and adopt two cube interpolation to carry out down-sampling to the ROI image of gained;
C. adopt multiple dimensioned Multi-aspect filtering device group to carry out feature extraction to the ROI image obtaining, obtain the eigenvector of five groups of corresponding different spectrum, and eigenvector is encoded, generate input feature vector;
D. input feature vector and the feature templates being stored in property data base are carried out to single spectrum characteristic matching correspondingly, five coupling marks that obtain carry out mark level weight and merge, finally adopt nearest neighbor algorithm to carry out decision-making according to merging mark, obtain recognition result.
With reference to accompanying drawing 2, system of the present invention is mainly made up of image capture module, image pretreatment module, characteristic extracting module, memory module, recognition decision module etc.
(1) image capture module
Described image capture module comprises multispectral active light source, ccd image inductor, and the control module being connected with multispectral active light source.Described multispectral active light source comprises blue light source (470nm), green-light source (525nm), red-light source (660nm), white light source and near infrared ray light source (850nm), and each light source is alternately distributed ringwise successively around ccd video camera.Due to the absorptivity difference of people's the skin spectrum to different wave length, that is to say under different spectrum and will obtain differentiated image; Simultaneously people's epidermis has certain thickness, thereby and some spectrum can penetrate people's epidermis and obtains hypodermic textural characteristics, and these features are to be difficult for forging, and can improve the anti-duplicity of recognition system.So the present invention has used five kinds of light sources, wherein comprise four kinds of visible light sources and a kind of near-infrared light source.Under irradiating, front four kinds of visible light sources obtain the metacarpus image that four width comprise palmmprint information; Adopt near-infrared light source irradiation can penetrate epidermis and obtain hypodermic textural characteristics, i.e. vein blood vessel feature, can obtain the metacarpus image that comprises vena metacarpea information thus.The metacarpus image acquisition special purpose device using in the present invention adopts the image inductor based on CCD, and the advantage of this acquisition mode is to obtain that speed image is fast, level of integrated system is high, real-time is good.The present invention adopts five kinds of LED array to be looped around ccd image inductor surrounding as light source, and before light source, adds optical filter to guarantee even and stable illumination condition.
(2) image pretreatment module
The input end of described image pretreatment module is connected with the output terminal of ccd image inductor, carries out pre-service, reference frame location, ROI extraction, down-sampling processing for the metacarpus image that ccd image inductor is collected.
Shown in 3, the image pre-treatment step in the present invention is as follows by reference to the accompanying drawings:
First carry out image binaryzation, and adopt the morphology operations such as burn into expansion to improve image binaryzation result.
Then the bianry image being drawn by upper step extracts the contour curve of palm and finger, then extracts 2 points by Harris angular-point detection method, the lowest point point P2 between the lowest point point P1 and the third finger and the little finger of toe of forefinger and middle interphalangeal.Implementation method is: get a window (5 × 5) centered by target pixel points, and window is moved up and down along impact point, calculate in moving process the grey scale change of window interior in 4 directions simultaneously, the angle point respective function value that is set as this target pixel points minimum in the difference of 4 grey scale change, in the time that this numerical value is greater than threshold value, just as angle point.So the line of P1 and P2 is defined as to Y-axis, using P1 to the mid point of P2 line segment and perpendicular to Y-axis straight line as X-axis, meanwhile because system completes five width metacarpus image acquisition within very short time, there is not image registration problem, so after under white light, metacarpus image reference coordinate system is determined, the metacarpus coordinate system under other four kinds of illumination is also corresponding to be determined.Image pre-service before this step is only carried out for white spectrum image, to improve image processing speed.
Then, respectively five width metacarpus images are carried out to ROI extraction according to definite reference frame, extract the central area of palm as area-of-interest (ROI), ROI region is square area, and its length of side is about palm width 70%.Because ROI image has comprised topmost feature and information in metacarpus image, the extraction of ROI has reduced noise, can improve again the arithmetic speed of system simultaneously.Because having used effective image pre-processing method in the present invention, reduce to extract due to ROI the interference of the real-time factor such as translation, rotation, improve the discrimination of system.
Finally the ROI metacarpus under five kinds of illumination is carried out respectively to two cube interpolation down-sampling processing.Two cubes of interpolation are utilized the gray-scale value cubic interpolation of 16 points, not only consider the gray scale impact of 4 direct neighbor points, and consider the impact of gray-value variation rate between 12 consecutive point, so the down-sampling pixel obtaining combines the information of pixel in 4 × 4 regions, both guaranteed accuracy of identification, more improved recognition speed.It is 4:1 that the present invention adopts down-sampling rate, and for example source images size is 128 × 128, and the image size after down-sampling is 32 × 32, and obviously image processing speed will improve 16 times.
(3) characteristic extracting module
The input end of described characteristic extracting module is connected with the output terminal of image pretreatment module, for the pretreated metacarpus image of process is carried out to feature extraction.
In conjunction with Fig. 4, the treatment step of feature extraction is as follows:
Multiple dimensioned Multi-aspect filtering device group allows to have different directions on each yardstick decomposes, and with dimensional variation, length breadth ratio presents " anisotropy " characteristic to its base support Interval, can realize the rarefaction representation to image.The feature extracting method using in the present invention is multiple dimensioned Multi-aspect filtering device group, its structure is divided into: without down-sampling pyramid (Non-subsampled Pyramid, NSP) decompose and without down-sampling anisotropic filter group (Non-subsampled Directional Filter Bank, NSDFB) decompose two parts, first utilize NSP to carry out multiple dimensioned decomposition to image, decompose and can effectively " catch " singular point in image by NSP; Then adopt NSDFB to decompose high fdrequency component travel direction, thereby obtain the sub-band images (coefficient) of different scale, different directions.Different from profile wave convert is in the decomposition and restructuring procedure of image, multiple dimensioned Multi-aspect filtering device group is not decomposed the up-sampling (interpolation) of filtered down-sampling (extraction) and synthesis filter to the component of signal after NSP and NSDFB decomposition, make it have multiple dimensioned, good spatial domain and frequency domain local characteristics and multi-direction characteristic.
Characteristic extraction procedure of the present invention is as follows: first adopt non-lower sampling band to lead to pyramid wave filter P
fwith down-sampled images I
x,ycarry out convolution, obtain the subimage f after bandpass filtering
x,y
f
x,y=I
x,y*P
f
P
fwave filter only allows the texture information with certain robust to remain so that subsequent characteristics is extracted; Then, the output response after convolution and non-lower sampling Multi-aspect filtering device group D
fconvolution, obtains multiple directions subimage
According to F
x,y, the present invention uses Hash table to encode to direction character.Metacarpus image under five kinds of spectrum that the present invention collects, after feature extraction, obtain five groups of direction characters, Hash table coding is that Orientation Features is stored with matrix form, and the index sequence that the array that is made up of row 0,1 of every group of direction character and the public pixel coordinate of four row and direction code form forms.Five width metacarpus Image Codings to be identified are the eigenvectors of five row by 0,1 composition.
(4) memory module
Described memory module is provided with property data base, is connected with the output terminal of characteristic extracting module, and the template characteristic of obtaining for storing registration phase.By reference to the accompanying drawings 2, the present invention's storage be metacarpus feature Hash table, piece image represents by five row binary values, five row represent respectively the eigenvector under different spectrum, due to the cause of down-sampling, required storage space dwindles greatly here.
(5) recognition decision module
Described recognition decision module is connected with characteristic extracting module, property data base, for input feature vector to be identified and template characteristic are carried out to single spectrum characteristic matching, and the matching result of different spectrum is carried out to the fusion of mark level weight, finally adopt nearest neighbor algorithm to carry out decision-making according to merging mark, and then obtain recognition result.
By reference to the accompanying drawings 5, in the present invention, gather from the metacarpus image under five kinds of spectrum, the image under every kind of illumination of metacarpus to be identified mates with the feature templates in database, will obtain the coupling mark of different meanings according to the mode difference of coupling.The present invention proposes two kinds of different feature matching methods, according to different matching process, will use different mark level fusing methods.When use with or when feature matching method, can by ask for five groups of coupling marks and as final decision mark
S
F=SUM(S
R,S
B,S
G,S
N,S
W)
Wherein S
r, S
b, S
g, S
n, S
wthe coupling mark that the matching process that represents respectively to seek common ground under single spectrum obtains, S
frepresent the mark after mark level merges; In the time using XOR matching process, can be by asking for five groups of maximal values of mating marks as final decision mark
S'
F=MAX(S'
R,S'
B,S'
G,S'
N,S'
W)
Experimental data shows, these two kinds of fusion methods all can obtain very high discrimination.
According to different feature matching methods, the coupling mark of different meanings will be obtained.In the time using same or characteristic matching and summation fusion method, using maximum coupling mark as recognition decision foundation
In the time using XOR characteristic matching and ask maximum fusion method, using smallest match mark as recognition decision foundation
The above; only for preferably embodiment of the present invention, but protection scope of the present invention is not limited to this, is anyly familiar with in technical scope that those skilled in the art disclose in the present invention; the variation that can expect easily or replacement, within all should being encompassed in protection scope of the present invention.
Claims (6)
1. low resolution multi-light spectrum palm print, the real-time personal identification method of vena metacarpea, mainly comprise registration phase and cognitive phase, it is characterized in that,
Registration phase comprises:
A. gather metacarpus image to be registered, described metacarpus image is included in the five width images that gather under white light, ruddiness, green glow, blue light, near infrared spectrum;
B. metacarpus image to be registered is carried out to ROI extraction, and adopt two cube interpolation to carry out down-sampling to the ROI image of gained;
C. adopt multiple dimensioned Multi-aspect filtering device group to carry out feature extraction to the ROI image obtaining, obtain the eigenvector of five groups of corresponding different spectrum, and eigenvector is encoded, generating feature template is also stored in property data base;
Cognitive phase comprises:
A. gather metacarpus image to be identified, described metacarpus image is included in the five width images that gather under white light, ruddiness, green glow, blue light, near infrared spectrum;
B. metacarpus image to be identified is carried out to ROI extraction, and adopt two cube interpolation to carry out down-sampling to the ROI image of gained;
C. adopt multiple dimensioned Multi-aspect filtering device group to carry out feature extraction to the ROI image obtaining, obtain the eigenvector of five groups of corresponding different spectrum, and eigenvector is encoded, generate input feature vector;
D. input feature vector and the feature templates being stored in property data base are carried out to single spectrum characteristic matching correspondingly, five coupling marks that obtain carry out mark level weight and merge, finally adopt nearest neighbor algorithm to carry out decision-making according to merging mark, obtain recognition result.
2. low resolution multi-light spectrum palm print according to claim 1, the real-time personal identification method of vena metacarpea, it is characterized in that, described metacarpus image is carried out also comprising before ROI extraction pre-service and reference frame location, wherein said pre-service comprises binary conversion treatment and morphology processing, and described morphology processing comprises Image erosion, expansion, closed operation;
Described reference frame location comprises: from binary image, extract the contour curve of palm and finger, and determine the reference frame of image by Harris angular-point detection method.
3. low resolution multi-light spectrum palm print according to claim 1, the real-time personal identification method of vena metacarpea and system, it is characterized in that, the described step that ROI image is carried out to feature extraction comprises: adopt the logical pyramid wave filter of non-lower sampling band and down-sampled images to carry out convolution, output response after convolution is carried out convolution to bank of filters from all directions with non-lower sampling again, finally in eight directions, adopts competitive way to carry out maximal value coding to wave filter output response and forms 0 or 1 binary features vector.
4. low resolution multi-light spectrum palm print according to claim 1, the real-time personal identification method of vena metacarpea, is characterized in that, described template characteristic is stored in metacarpus property data base with Hash table form.
5. low resolution multi-light spectrum palm print, the real-time identification system of vena metacarpea, is characterized in that, comprising:
Image capture module, described image capture module comprises multispectral active light source, ccd image inductor, and the control module being connected with multispectral active light source;
Image pretreatment module, the input end of described image pretreatment module is connected with the output terminal of ccd image inductor, carries out pre-service, reference frame location, ROI extraction, down-sampling processing for the metacarpus image that ccd image inductor is collected;
Characteristic extracting module, the input end of described characteristic extracting module is connected with the output terminal of image pretreatment module, for the pretreated metacarpus image of process is carried out to feature extraction;
Memory module, described memory module is provided with property data base, is connected with the output terminal of characteristic extracting module, the template characteristic of obtaining for storing registration phase;
Recognition decision module, described recognition decision module is connected with characteristic extracting module, property data base, for input feature vector to be identified and template characteristic are carried out to single spectrum characteristic matching, and the matching result of different spectrum is carried out to the fusion of mark level weight, finally adopt nearest neighbor algorithm to carry out decision-making according to merging mark, and then obtain recognition result.
6. low resolution multi-light spectrum palm print according to claim 1, the real-time identification system of vena metacarpea, it is characterized in that: described multispectral active light source comprises around ccd image inductor alternatively distributed white light source, red-light source, green-light source, blue light source, near infrared ray light source successively ringwise, described control module is for controlling the bright dark in turn of each light source.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410043629.4A CN103793692A (en) | 2014-01-29 | 2014-01-29 | Low-resolution multi-spectral palm print and palm vein real-time identity recognition method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201410043629.4A CN103793692A (en) | 2014-01-29 | 2014-01-29 | Low-resolution multi-spectral palm print and palm vein real-time identity recognition method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103793692A true CN103793692A (en) | 2014-05-14 |
Family
ID=50669337
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201410043629.4A Pending CN103793692A (en) | 2014-01-29 | 2014-01-29 | Low-resolution multi-spectral palm print and palm vein real-time identity recognition method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103793692A (en) |
Cited By (25)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104166842A (en) * | 2014-07-25 | 2014-11-26 | 同济大学 | Three-dimensional palm print identification method based on partitioning statistical characteristic and combined expression |
| CN104318213A (en) * | 2014-10-21 | 2015-01-28 | 沈阳大学 | Method for using human body palm biology information to identify identities |
| CN104615634A (en) * | 2014-11-10 | 2015-05-13 | 广东智冠信息技术股份有限公司 | Direction feature based palm vein guiding quick retrieval method |
| WO2015180461A1 (en) * | 2014-05-27 | 2015-12-03 | 常熟安智生物识别技术有限公司 | Palm vein recognition smart building video intercom system |
| CN105474234A (en) * | 2015-11-24 | 2016-04-06 | 厦门中控生物识别信息技术有限公司 | Method and apparatus for palm vein recognition |
| CN105811990A (en) * | 2014-12-31 | 2016-07-27 | 航天信息股份有限公司 | Decoding method and device for FM0 code, and ETC (electronic toll collection) system |
| CN107195124A (en) * | 2017-07-20 | 2017-09-22 | 长江大学 | The self-service book borrowing method in library and system based on palmmprint and vena metacarpea |
| CN107341473A (en) * | 2017-07-04 | 2017-11-10 | 深圳市利众信息科技有限公司 | Palm characteristic recognition method, palm characteristic identificating equipment and storage medium |
| CN107506688A (en) * | 2017-07-18 | 2017-12-22 | 西安电子科技大学 | Harris Corner Detection image pyramid palmmprint ROI recognition methods |
| CN108107049A (en) * | 2018-01-15 | 2018-06-01 | 江苏大学 | Combined harvester tanker seed percentage of impurity and percentage of damage real-time monitoring device and method |
| CN108596031A (en) * | 2018-03-20 | 2018-09-28 | 深圳大学 | A kind of multispectral three-dimensional fingerprint and refer to venous collection device |
| CN109271867A (en) * | 2018-08-20 | 2019-01-25 | 浙江荣亚工贸有限公司 | A kind of Strawberry ripening degree automatic judging method |
| CN109803450A (en) * | 2018-12-12 | 2019-05-24 | 平安科技（深圳）有限公司 | Wireless device and computer connection method, electronic device and storage medium |
| CN110751620A (en) * | 2019-08-28 | 2020-02-04 | 宁波海上鲜信息技术有限公司 | Method for estimating volume and weight, electronic device, and computer-readable storage medium |
| CN110897635A (en) * | 2019-12-31 | 2020-03-24 | 中国海洋大学 | Method for extracting and identifying electrocardiogram signal in real scene |
| WO2020082386A1 (en) * | 2018-10-26 | 2020-04-30 | 合刃科技（深圳）有限公司 | Character obtaining method and device |
| CN111104859A (en) * | 2019-11-19 | 2020-05-05 | 广州恒龙信息技术有限公司 | Authentication method and system based on multispectral identification |
| CN111553384A (en) * | 2020-04-03 | 2020-08-18 | 上海聚虹光电科技有限公司 | Matching method of multispectral image and single-spectral image |
| CN112052842A (en) * | 2020-10-14 | 2020-12-08 | 福建省海峡智汇科技有限公司 | Palm vein-based person identification method and device |
| CN112381042A (en) * | 2020-11-27 | 2021-02-19 | 程自昂 | Method for extracting palm vein features from palm vein image and palm vein identification method |
| CN113465505A (en) * | 2021-06-28 | 2021-10-01 | 七海测量技术（深圳）有限公司 | Visual detection positioning system and method |
| CN113591754A (en) * | 2018-11-16 | 2021-11-02 | 北京市商汤科技开发有限公司 | Key point detection method and device, electronic equipment and storage medium |
| CN113780122A (en) * | 2021-08-30 | 2021-12-10 | 沈阳大学 | Identification template generation method and device based on palm vein feature encryption |
| CN114241534A (en) * | 2021-12-01 | 2022-03-25 | 佛山市红狐物联网科技有限公司 | Rapid matching method and system for full-palmar venation data |
| CN117315833A (en) * | 2023-09-28 | 2023-12-29 | 杭州名光微电子科技有限公司 | Palm vein recognition module for intelligent door lock and method thereof |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101055618A (en) * | 2007-06-21 | 2007-10-17 | 中国科学院合肥物质科学研究院 | Palm grain identification method based on direction character |
| CN101604385A (en) * | 2009-07-09 | 2009-12-16 | 深圳大学 | A kind of palm grain identification method and palmmprint recognition device |
-
2014
- 2014-01-29 CN CN201410043629.4A patent/CN103793692A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101055618A (en) * | 2007-06-21 | 2007-10-17 | 中国科学院合肥物质科学研究院 | Palm grain identification method based on direction character |
| CN101604385A (en) * | 2009-07-09 | 2009-12-16 | 深圳大学 | A kind of palm grain identification method and palmmprint recognition device |
Non-Patent Citations (5)
| Title |
|---|
| DAVID ZHANG ET AL.: ""An Online System of Multispectral Palmprint Verification"", 《IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT》 * |
| DAVID ZHANG ET AL.: ""Online Palmprint Identification"", 《IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE》 * |
| YIBIN YU ET AL.: ""Multispectral Palmprint Recognition Using Score-Level Fusion"", 《IEEE INTERNATIONAL CONFERENCE ON GREEN COMPUTING AND COMMUNICATION》 * |
| ZOHAIB KHAN ET AL.: ""Contour Code: Robust and Efficient Multispectral Palmprint Encoding for Human Recognition"", 《IEEE INTERNATIONAL CONFERENCE ON COMPUTER VISION》 * |
| 苏晓生等: ""基于小波变换的掌纹特征提取"", 《清华大学学报（自然科学版）》 * |
Cited By (36)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2015180461A1 (en) * | 2014-05-27 | 2015-12-03 | 常熟安智生物识别技术有限公司 | Palm vein recognition smart building video intercom system |
| CN104166842B (en) * | 2014-07-25 | 2017-06-13 | 同济大学 | It is a kind of based on block statistics feature and combine represent three-dimensional palm print recognition methods |
| CN104166842A (en) * | 2014-07-25 | 2014-11-26 | 同济大学 | Three-dimensional palm print identification method based on partitioning statistical characteristic and combined expression |
| CN104318213A (en) * | 2014-10-21 | 2015-01-28 | 沈阳大学 | Method for using human body palm biology information to identify identities |
| CN104615634A (en) * | 2014-11-10 | 2015-05-13 | 广东智冠信息技术股份有限公司 | Direction feature based palm vein guiding quick retrieval method |
| CN105811990A (en) * | 2014-12-31 | 2016-07-27 | 航天信息股份有限公司 | Decoding method and device for FM0 code, and ETC (electronic toll collection) system |
| CN105474234B (en) * | 2015-11-24 | 2019-03-29 | 厦门中控智慧信息技术有限公司 | A kind of vena metacarpea knows method for distinguishing and vena metacarpea identification device |
| CN105474234A (en) * | 2015-11-24 | 2016-04-06 | 厦门中控生物识别信息技术有限公司 | Method and apparatus for palm vein recognition |
| CN107341473A (en) * | 2017-07-04 | 2017-11-10 | 深圳市利众信息科技有限公司 | Palm characteristic recognition method, palm characteristic identificating equipment and storage medium |
| CN107506688A (en) * | 2017-07-18 | 2017-12-22 | 西安电子科技大学 | Harris Corner Detection image pyramid palmmprint ROI recognition methods |
| CN107195124A (en) * | 2017-07-20 | 2017-09-22 | 长江大学 | The self-service book borrowing method in library and system based on palmmprint and vena metacarpea |
| CN108107049A (en) * | 2018-01-15 | 2018-06-01 | 江苏大学 | Combined harvester tanker seed percentage of impurity and percentage of damage real-time monitoring device and method |
| CN108596031A (en) * | 2018-03-20 | 2018-09-28 | 深圳大学 | A kind of multispectral three-dimensional fingerprint and refer to venous collection device |
| CN109271867A (en) * | 2018-08-20 | 2019-01-25 | 浙江荣亚工贸有限公司 | A kind of Strawberry ripening degree automatic judging method |
| CN109271867B (en) * | 2018-08-20 | 2021-11-02 | 浙江荣亚工贸有限公司 | Automatic judgment method for strawberry maturity |
| CN111357007A (en) * | 2018-10-26 | 2020-06-30 | 合刃科技（深圳）有限公司 | Character acquisition method and device |
| CN111357007B (en) * | 2018-10-26 | 2024-01-19 | 合刃科技（深圳）有限公司 | Character acquisition method and device |
| WO2020082386A1 (en) * | 2018-10-26 | 2020-04-30 | 合刃科技（深圳）有限公司 | Character obtaining method and device |
| CN113591754A (en) * | 2018-11-16 | 2021-11-02 | 北京市商汤科技开发有限公司 | Key point detection method and device, electronic equipment and storage medium |
| CN109803450A (en) * | 2018-12-12 | 2019-05-24 | 平安科技（深圳）有限公司 | Wireless device and computer connection method, electronic device and storage medium |
| CN110751620B (en) * | 2019-08-28 | 2021-03-16 | 宁波海上鲜信息技术有限公司 | Method for estimating volume and weight, electronic device, and computer-readable storage medium |
| CN110751620A (en) * | 2019-08-28 | 2020-02-04 | 宁波海上鲜信息技术有限公司 | Method for estimating volume and weight, electronic device, and computer-readable storage medium |
| CN111104859A (en) * | 2019-11-19 | 2020-05-05 | 广州恒龙信息技术有限公司 | Authentication method and system based on multispectral identification |
| CN110897635A (en) * | 2019-12-31 | 2020-03-24 | 中国海洋大学 | Method for extracting and identifying electrocardiogram signal in real scene |
| CN110897635B (en) * | 2019-12-31 | 2021-01-15 | 中国海洋大学 | Method for extracting and identifying electrocardiogram signal in real scene |
| CN111553384A (en) * | 2020-04-03 | 2020-08-18 | 上海聚虹光电科技有限公司 | Matching method of multispectral image and single-spectral image |
| CN112052842B (en) * | 2020-10-14 | 2023-12-19 | 福建省海峡智汇科技有限公司 | Palm vein-based personnel identification method and device |
| CN112052842A (en) * | 2020-10-14 | 2020-12-08 | 福建省海峡智汇科技有限公司 | Palm vein-based person identification method and device |
| CN112381042A (en) * | 2020-11-27 | 2021-02-19 | 程自昂 | Method for extracting palm vein features from palm vein image and palm vein identification method |
| CN113465505A (en) * | 2021-06-28 | 2021-10-01 | 七海测量技术（深圳）有限公司 | Visual detection positioning system and method |
| CN113465505B (en) * | 2021-06-28 | 2024-03-22 | 七海测量技术（深圳）有限公司 | Visual detection positioning system and method |
| CN113780122A (en) * | 2021-08-30 | 2021-12-10 | 沈阳大学 | Identification template generation method and device based on palm vein feature encryption |
| CN113780122B (en) * | 2021-08-30 | 2023-12-05 | 沈阳大学 | Palm vein feature encryption-based recognition template generation method and device |
| CN114241534A (en) * | 2021-12-01 | 2022-03-25 | 佛山市红狐物联网科技有限公司 | Rapid matching method and system for full-palmar venation data |
| CN117315833A (en) * | 2023-09-28 | 2023-12-29 | 杭州名光微电子科技有限公司 | Palm vein recognition module for intelligent door lock and method thereof |
| CN117315833B (en) * | 2023-09-28 | 2024-06-04 | 杭州名光微电子科技有限公司 | Palm vein recognition module for intelligent door lock and method thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103793692A (en) | Low-resolution multi-spectral palm print and palm vein real-time identity recognition method and system | |
| Han et al. | Palm vein recognition using adaptive Gabor filter | |
| CN101359365B (en) | Iris positioning method based on maximum between-class variance and gray scale information | |
| CN100492400C (en) | Matching identification method by extracting characters of vein from finger | |
| CN101251889B (en) | Personal identification method and near-infrared image forming apparatus based on palm vena and palm print | |
| US8917914B2 (en) | Face recognition system and method using face pattern words and face pattern bytes | |
| Das et al. | Sclera recognition using dense-SIFT | |
| Das et al. | A new efficient and adaptive sclera recognition system | |
| Yang et al. | Finger-vein segmentation based on multi-channel even-symmetric Gabor filters | |
| Banerjee et al. | ARTeM: A new system for human authentication using finger vein images | |
| Yang et al. | A novel finger-vein recognition method with feature combination | |
| Kang et al. | The biometric recognition on contactless multi-spectrum finger images | |
| Trabelsi et al. | A new multimodal biometric system based on finger vein and hand vein recognition | |
| Das et al. | A new method for sclera vessel recognition using OLBP | |
| CN111178130A (en) | Face recognition method, system and readable storage medium based on deep learning | |
| Fairuz et al. | Convolutional neural network-based finger vein recognition using near infrared images | |
| CN108288040A (en) | Multi-parameter face identification system based on face contour | |
| Agarwal et al. | A review on vein biometric recognition using geometric pattern matching techniques | |
| Malutan et al. | Dorsal hand vein recognition based on Riesz Wavelet Transform and Local Line Binary Pattern | |
| Kumar et al. | Finger Vein based Human Identification and Recognition using Gabor Filter | |
| Fatt et al. | Fingerprint and face recognition: Application to multimodal biometrics system | |
| Thenmozhi et al. | Comparative analysis of finger vein pattern feature extraction techniques: An overview | |
| Alam et al. | Fingerprint detection applying discrete wavelet transform on ROI | |
| Lian et al. | Partial occlusion face recognition method based on acupoints locating through infrared thermal imaging | |
| Kalaimathi et al. | Extraction and authentication of biometric finger vein using gradient boosted feature algorithm |
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: 20140514 |
|
| RJ01 | Rejection of invention patent application after publication |