CN112507974A - Palm print identification method based on texture features - Google Patents

Palm print identification method based on texture features Download PDF

Info

Publication number
CN112507974A
CN112507974A CN202011588460.2A CN202011588460A CN112507974A CN 112507974 A CN112507974 A CN 112507974A CN 202011588460 A CN202011588460 A CN 202011588460A CN 112507974 A CN112507974 A CN 112507974A
Authority
CN
China
Prior art keywords
palm print
image
matched
main line
texture
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.)
Granted
Application number
CN202011588460.2A
Other languages
Chinese (zh)
Other versions
CN112507974B (en
Inventor
焦传佳
徐劲松
高云峰
曹雏清
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Wuhu Robot Technology Research Institute of Harbin Institute of Technology
Original Assignee
Wuhu Robot Technology Research Institute of Harbin Institute of Technology
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by Wuhu Robot Technology Research Institute of Harbin Institute of Technology filed Critical Wuhu Robot Technology Research Institute of Harbin Institute of Technology
Priority to CN202011588460.2A priority Critical patent/CN112507974B/en
Publication of CN112507974A publication Critical patent/CN112507974A/en
Application granted granted Critical
Publication of CN112507974B publication Critical patent/CN112507974B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

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
    • G06V40/12—Fingerprints or palmprints
    • G06V40/13—Sensors therefor
    • 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
    • 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
    • G06V40/12—Fingerprints or palmprints
    • G06V40/1347—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
    • G06V40/12—Fingerprints or palmprints
    • G06V40/1365—Matching; Classification
    • Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02D—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00—Energy efficient computing, e.g. low power processors, power management or thermal management

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • General Physics & Mathematics (AREA)
  • Multimedia (AREA)
  • Theoretical Computer Science (AREA)
  • Human Computer Interaction (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Image Analysis (AREA)
  • Collating Specific Patterns (AREA)

Abstract

The invention discloses a palm print identification method based on texture characteristics, which comprises the following steps: s1, collecting a palm print image of the palm print to be matched, and carrying out gray processing on the palm print image to form a gray image; s2, detecting a palm print main line in the gray level image, and acquiring a main line image of a palm print to be matched; s3, extracting texture detail features from the palm print dominant line image to be matched; s4, k palm print main line template images which are most matched with the palm print main line image to be matched are obtained in the matching library, the palm print main line template image which is matched with the texture detail features of the palm print to be matched is obtained from the k palm print main line template images, and the identification of the palm print to be matched is completed. The accuracy and the rapidity of palm print identification are improved, and the effect of identifying the identity information of people through the palm print characteristics is achieved.

Description

Palm print identification method based on texture features
Technical Field
The invention belongs to the technical field of palm print recognition, and particularly relates to a palm print recognition method based on texture features.
Background
Biometric identification is widely applied in the fields of bank service, intelligent office buildings, intelligent security and the like, and an accurate biometric identification technology is a key technology for confirming the identity of a person. The biological characteristic identification method comprises a fingerprint identification method, a face identification method, a palm print identification method and the like, wherein the fingerprint identification method is used for matching and acquiring information of a person by detecting and identifying fingerprint characteristics, but the fingerprint texture characteristics are less, so that the problem of insufficient identification information is caused; the face recognition method determines the identity information of a person by recognizing the biological characteristics of the face, but the stability of the face is poor, and the face can change along with the age, so that the problem of reliability of recognition is caused; the palm print identification method based on the texture features is one of the current mature methods for identifying the biological features of human bodies, the skin surface texture of the palm print has stability and uniqueness, cannot be greatly changed along with the growth of age, has richer texture information compared with fingerprints, and is a more reliable biological feature identification technology.
The existing process for identifying the identity of a person based on a palm print outline and an edge texture feature comprises the following steps: collecting a palm print image, preprocessing the image, decomposing the palm print image into a main line contour and a main line edge texture by using mean filtering, respectively extracting features by using a gray histogram and a difference box, and finally matching by using a chi-square distance to finish identity recognition. This solution has the following problems: the mean filtering cannot well protect image details, and the detail part of the image is damaged while the image is denoised, so that the image becomes fuzzy, noise points cannot be well removed, and the segmentation processing of edge details is not facilitated.
Disclosure of Invention
The invention provides a palm print identification method based on texture features, aiming at improving the problems.
The invention is realized in such a way that a palm print identification method based on texture features specifically comprises the following steps:
s1, collecting a palm print image of the palm print to be matched, and carrying out gray processing on the palm print image to form a gray image;
s2, detecting a palm print main line in the gray level image, and acquiring a main line image of a palm print to be matched;
s3, extracting texture detail features from the palm print dominant line image to be matched;
s4, k palm print main line template images which are most matched with the palm print main line image to be matched are obtained in the matching library, the palm print main line template image which is matched with the texture detail features of the palm print to be matched is obtained from the k palm print main line template images, and the identification of the palm print to be matched is completed.
Further, the method for extracting the texture detail features specifically comprises the following steps:
s31, h image blocks are formed from the nxn matrix, and adjacent image blocks are overlapped;
s32, equally dividing the filtering angle into m intervals at 180 degrees, sampling the angle value in each angle interval as the filtering direction of the filtering function, forming a filtering image based on each filtering direction, accumulating the amplitude m (x, y) of each pixel point on all the filtering images, and forming an m-dimensional gradient amplitude accumulation histogram HC of each pixel point;
accumulating m-dimensional gradient amplitude accumulation histograms HC of all pixel points in an image block to form a histogram HB corresponding to the image block, and constructing a standardized histogram NHB of the image block;
the normalized histograms NHB of the h image blocks are integrated to form a line energy direction histogram feature HOLEGaborI.e. the texture detail feature of the palm print to be matched.
Further, the step S4 specifically includes the following steps:
s1, acquiring the overlapping area of the palm print main line template image and the palm print main line image to be matched, and calculating the matching characteristics S of the overlapping area relative to the palm print main line image to be matched and the palm print main line template image1、S2；
S2, calculating matching characteristics S1、S2And obtaining k palm print main line template images with the minimum distance Dist.
Further, matching the feature S1And S2The calculation formula of (a) is specifically as follows:
Figure BDA0002867849150000031
Figure BDA0002867849150000032
wherein L (x, y) and
Figure BDA0002867849150000033
pixel values of the x row and y column pixel points in the palm print main line image to be matched and the palm print main line template image are respectively, and N is the width and the height of the palm print main line image to be matched and the palm print main line template image.
According to the method, a Canny operator is used for palm print contour detection to obtain palm print main line characteristics, and then palm print detail characteristics are extracted according to a gray level image to obtain line energy direction histogram characteristics (HOLE)GaborThe method comprises the steps of performing hierarchical matching, namely performing coarse screening on a test image and database template image main line characteristics according to a defined matching degree method, extracting key line energy direction histogram characteristics respectively according to template images screened in the coarse matching process, matching the key line energy direction histogram characteristics with the test image line energy direction histogram characteristics, finding a template image with the closest matching degree, namely a final matching result, completing recognition, and improving the accuracy of palm print recognition; in addition, matching is carried out based on the main line characteristics, most images are screened out, and matching time is saved.
Drawings
Fig. 1 is a flowchart of a palm print recognition method based on texture features according to an embodiment of the present invention.
Detailed Description
The following detailed description of the embodiments of the present invention will be given in order to provide those skilled in the art with a more complete, accurate and thorough understanding of the inventive concept and technical solutions of the present invention.
The method uses Canny operator to carry out palm print contour detection, obtains palm print main line characteristics, and then carries out palm print contour detection according to a gray level diagramExtracting the detail features of the palmprint to obtain the line energy direction histogram feature HOLEGaborAnd then, carrying out hierarchical matching, namely, carrying out coarse screening on the test image and the database template image mainline characteristics according to a defined matching degree method, respectively extracting key line energy direction histogram characteristics according to the template image screened in the coarse matching process, matching the key line energy direction histogram characteristics with the test image line energy direction histogram characteristics, finding the template image with the closest matching degree, namely, a final matching result, completing the identification, improving the accuracy and rapidity of the palm print identification, and achieving the effect of identifying the identity information of a person through the palm print characteristics.
Fig. 1 is a flowchart of a palm print recognition method based on texture features according to an embodiment of the present invention, where the method specifically includes the following steps:
the identification of the palm print comprises a palm print extraction process and a palm print matching process, wherein the palm print extraction process specifically comprises the following steps:
s1, image preprocessing: firstly, carrying out weighted average on a palm print image to be matched, which is acquired by a camera, and converting the palm print image into a gray image, wherein a calculation formula of the weighted average is as follows:
Y＝0.3R+0.59G+0.11B
wherein, Y is the gray value of the pixel point in the gray image, and R, G, B represents the RGB values of the pixel point respectively. And removing the noise of the gray level image by using bilateral filtering on the acquired gray level image.
S2, detecting the main line edge of the palm print to be matched: the method comprises the following steps of performing dominant line contour detection on a palm print to be matched by using a Canny operator on a gray level image to obtain a palm print dominant line image of the palm print to be matched (the dominant line is also called flexor print and refers to the thickest lines on the palm. most people have three dominant lines which are generally called a life line, an emotional line and a smart line and are also called a first flexor print, a second flexor print and a third flexor print), and the calculation steps mainly comprise:
calculating an image gradient amplitude value Z and a gradient direction f of the gray level image, wherein the formula is as follows:
Figure BDA0002867849150000041
Figure BDA0002867849150000042
wherein f isx、fyTemplate matrix representing sobel operator, fxFor convolution arrays acting in the x-direction, fyFor arrays of convolutions acting in the direction of the y-axis, e.g.
Figure BDA0002867849150000051
And performing rough identification on a palm print main line based on the image gradient amplitude value Z and the gradient direction f, and then sequentially performing non-maximum suppression operation and high-low threshold connection edge on the palm print main line image to realize main line fine identification of the palm print to be matched, namely acquiring a main line image of the palm print to be matched, namely the main line image with the matched palm print, namely the image with the matched palm print main line image for short.
S4, extracting detail features of the palm print texture: extracting texture detail features of the palm print dominant line image to be matched, wherein the method for extracting the texture detail features comprises the following steps:
dividing the acquired gray level image into nxn matrix blocks, wherein each matrix block comprises axb pixels; h image blocks are formed from the nxn matrix, each image block is composed of cxd pixels, and adjacent image blocks are overlapped;
then, filtering the xth pixel point I (x, y) of the xth line of the image block by using a two-dimensional linear Gabor filter, wherein the Gabor filter has a definition formula as follows:
Figure BDA0002867849150000052
wherein θ is the direction of the filter function, μ is the frequency of the sine wave, δ is the standard deviation of the gaussian envelope, the fixed parameters μ and δ, and G (x, y, θ) is the pixel value of the pixel I (x, y) in the filter direction θ;
changing theta to obtain a group of filter banks in r directions, respectively convolving the image blocks to obtain r filtered images of the image blocks, wherein the value number of the directions of the k filtering function ranges from 1 to n, and the amplitude m (x, y) of the pixel points in each filtering image is known by a Gabor filter principle formula:
m(x,y)＝min(I(x,y)G(x,y,θk)),k＝1,2,...,n
then, equally dividing the filtering angle of 180 degrees into m intervals, sampling an angle value in each angle interval as a filtering direction of a filtering function, forming a filtering image based on each filtering direction, sampling the angle value based on a set angle step length, accumulating the amplitude m (x, y) of each pixel point on all the filtering images, and forming an m-dimensional gradient amplitude accumulation histogram HC of each pixel point;
accumulating m-dimensional gradient amplitude accumulation histograms HC of all pixel points in the image block to form a histogram HB corresponding to the image block, standardizing by using L2 norm to construct a standardized histogram NHB of the image block, and calculating a formula:
HBj＝{HC1,HC2,...,HCj，...，HCh}；
Figure BDA0002867849150000061
wherein, HBjHistograms HB, NHB representing the jth image BlockjThe normalized histogram NHB, e ≈ 1.732 representing the j-th image block.
The normalized histograms NHB of the h image blocks are integrated to form a line energy direction histogram feature HOLEGaborThen, the formula is expressed as: HOLEGabor＝{NHB1,NHB2,...,NHBkAnd finishing the extraction of detail features of the palm print main line and the main line texture of the gray level image.
S5, palm print matching and identifying process: finding out k palm print main line template images which are most matched with the palm print to be matched in a matching library based on the palm print main line, wherein the matching library is used for storing the palm print main line template images and corresponding identity information;
calculating the feature matching degree of the palm print main line template image and the palm print main line image to be matched in the matching library, wherein the calculation formula is as follows:
Figure BDA0002867849150000062
Figure BDA0002867849150000063
wherein L (x, y) and
Figure BDA0002867849150000064
respectively the pixel values of the x row and y column pixel points in the palm print mainline image to be matched and the palm print mainline template image, N is the width and height of the image, S1Matching characteristics of the image divided by the overlapping area of the palm print main line template image and the palm print main line image to be matched relative to the palm print main line image to be matched S2Obtaining the matching characteristic S for the matching characteristic of the image of the overlapping area of the palm print main line template image and the palm print main line image to be matched relative to the palm print main line template image1And matching feature S2Then, the distance between features Dist is defined as:
Figure BDA0002867849150000071
the smaller the distance Dist is, the larger the matching degree is, namely the closer the master palm print template image is, the k master palm print template images with the maximum matching degree are obtained, and the preliminary coarse matching is completed;
and extracting the key line energy direction histogram characteristics of the palm print main line template image, matching the key line energy direction histogram characteristics with the line energy direction histogram characteristics of the matched image, and finding the palm print main line template image with the closest matching degree to finish the identification.
The invention has been described above with reference to the accompanying drawings, it is obvious that the invention is not limited to the specific implementation in the above-described manner, and it is within the scope of the invention to apply the inventive concept and solution to other applications without substantial modification.

Claims (4)

1. A palm print identification method based on texture features is characterized by specifically comprising the following steps:
s1, collecting a palm print image of the palm print to be matched, and carrying out gray processing on the palm print image to form a gray image;
s2, detecting a palm print main line in the gray level image, and acquiring a main line image of a palm print to be matched;
s3, extracting texture detail features from the palm print dominant line image to be matched;
s4, k palm print main line template images which are most matched with the palm print main line image to be matched are obtained in the matching library, the palm print main line template image which is matched with the texture detail features of the palm print to be matched is obtained from the k palm print main line template images, and the identification of the palm print to be matched is completed.
2. The palm print recognition method based on texture features as claimed in claim 1, wherein the extraction method of the texture detail features is as follows:
s31, h image blocks are formed in the main line image of the palm print to be matched, and adjacent image blocks are overlapped;
s32, equally dividing the filtering angle into m intervals at 180 degrees, sampling the angle value in each angle interval as the filtering direction of the filtering function, forming a filtering image based on each filtering direction, accumulating the amplitude m (x, y) of each pixel point on all the filtering images, and forming an m-dimensional gradient amplitude accumulation histogram HC of each pixel point;
accumulating m-dimensional gradient amplitude accumulation histograms HC of all pixel points in an image block to form a histogram HB corresponding to the image block, and constructing a standardized histogram NHB of the image block;
the normalized histograms NHB of the h image blocks are integrated to form a line energy direction histogram feature HOLEGaborI.e. the texture detail feature of the palm print to be matched.
3. The palm print recognition method based on texture features as claimed in claim 1, wherein the step S4 specifically comprises the steps of:
s1, acquiring the overlapping area of the palm print main line template image and the palm print main line image to be matchedCalculating the matching characteristic S of the overlapping area relative to the master line graph and master line template image of the palm print to be matched1、S2；
S2, calculating matching characteristics S1、S2And obtaining k palm print main line template images with the minimum distance Dist.
4. A palm print recognition method based on texture features as claimed in claim 3, characterized in that the matching features S1And S2The calculation formula of (a) is specifically as follows:
Figure FDA0002867849140000021
Figure FDA0002867849140000022
wherein L (x, y) and
Figure FDA0002867849140000023
pixel values of the x row and y column pixel points in the palm print main line image to be matched and the palm print main line template image are respectively, and N is the width and the height of the palm print main line image to be matched and the palm print main line template image.
CN202011588460.2A 2020-12-29 2020-12-29 Palm print identification method based on texture features Active CN112507974B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN202011588460.2A CN112507974B (en) 2020-12-29 2020-12-29 Palm print identification method based on texture features

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN202011588460.2A CN112507974B (en) 2020-12-29 2020-12-29 Palm print identification method based on texture features

Publications (2)

Publication Number Publication Date
CN112507974A true CN112507974A (en) 2021-03-16
CN112507974B CN112507974B (en) 2023-04-07

Family

ID=74951823

Family Applications (1)

Application Number Title Priority Date Filing Date
CN202011588460.2A Active CN112507974B (en) 2020-12-29 2020-12-29 Palm print identification method based on texture features

Country Status (1)

Country Link
CN (1) CN112507974B (en)

Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101604385A (en) * 2009-07-09 2009-12-16 深圳大学 A kind of palm grain identification method and palmmprint recognition device
CN102073843A (en) * 2010-11-05 2011-05-25 沈阳工业大学 Non-contact rapid hand multimodal information fusion identification method
US20120194662A1 (en) * 2011-01-28 2012-08-02 The Hong Kong Polytechnic University Method and system for multispectral palmprint verification
CN104636721A (en) * 2015-01-16 2015-05-20 青岛大学 Palm print identification method based on contour and edge texture feature fusion
US20180075282A1 (en) * 2016-09-09 2018-03-15 MorphoTrak, LLC Palm print image matching techniques
CN108171188A (en) * 2018-01-04 2018-06-15 天津大学 For the MCM methods of Rapid matching identification finger vena
CN108491802A (en) * 2018-03-26 2018-09-04 安徽大学 Palmmprint cross-matched recognition methods based on the excitation of joint weighted difference and double directions Gabor
CN109871779A (en) * 2019-01-23 2019-06-11 北京细推科技有限公司 The method and electronic equipment of personal recognition

Patent Citations (8)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN101604385A (en) * 2009-07-09 2009-12-16 深圳大学 A kind of palm grain identification method and palmmprint recognition device
CN102073843A (en) * 2010-11-05 2011-05-25 沈阳工业大学 Non-contact rapid hand multimodal information fusion identification method
US20120194662A1 (en) * 2011-01-28 2012-08-02 The Hong Kong Polytechnic University Method and system for multispectral palmprint verification
CN104636721A (en) * 2015-01-16 2015-05-20 青岛大学 Palm print identification method based on contour and edge texture feature fusion
US20180075282A1 (en) * 2016-09-09 2018-03-15 MorphoTrak, LLC Palm print image matching techniques
CN108171188A (en) * 2018-01-04 2018-06-15 天津大学 For the MCM methods of Rapid matching identification finger vena
CN108491802A (en) * 2018-03-26 2018-09-04 安徽大学 Palmmprint cross-matched recognition methods based on the excitation of joint weighted difference and double directions Gabor
CN109871779A (en) * 2019-01-23 2019-06-11 北京细推科技有限公司 The method and electronic equipment of personal recognition

Non-Patent Citations (7)

* Cited by examiner, † Cited by third party
Title
WEI JIA等: ""Histogram of Oriented Line Energies for Palmprint Identification"", 《IEEE TRANSACTIONS ON SYSTEMS, MAN, AND CYBERNETICS: SYSTEMS》 *
WENXIN LI等: ""Texture-Based Palmprint Retrieval Using a Layered Search Scheme for Personal Identification"", 《IEEE TRANSACTIONS ON MULTIMEDIA》 *
刘富等: ""基于两层策略的掌纹识别新方法"", 《吉林大学学报（工学版）》 *
吴庆垚: ""基于线特征的双向匹配的掌纹识别研究"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *
接标: ""一种分层的基于多特征的在线掌纹识别研究"", 《中国优秀硕士学位论文全文数据库 信息科技辑》 *
胡戎翔: ""基于掌纹和手形的生物特征识别方法"", 《中国博士学位论文全文数据库 信息科技辑》 *
蒲东兵: ""生物识别技术及其嵌入式应用研究"", 《中国博士学位论文全文数据库 信息科技辑》 *

Also Published As

Publication number Publication date
CN112507974B (en) 2023-04-07

Similar Documents

Publication Publication Date Title
Zhang et al. Fingerprint classification based on extraction and analysis of singularities and pseudo ridges
CN110443128B (en) Finger vein identification method based on SURF feature point accurate matching
Afsar et al. Fingerprint identification and verification system using minutiae matching
CN107748877A (en) A kind of Fingerprint recognition method based on minutiae point and textural characteristics
US20020146178A1 (en) System and method for fingerprint image enchancement using partitioned least-squared filters
Lee et al. A Gabor filter-based approach to fingerprint recognition
Abhyankar et al. Towards integrating level-3 Features with perspiration pattern for robust fingerprint recognition
Murty et al. Iris recognition system using fractal dimensions of Haar patterns
Mali et al. Fingerprint recognition using global and local structures
CN112507974B (en) Palm print identification method based on texture features
Kumar et al. Finger vein based human identification and recognition using gabor filter
DR et al. Fingerprint verification based on fusion of minutiae and ridges using strength factors
Hsieh et al. An effective method of fingerprint classification combined with AFIS
Kuban et al. A NOVEL MODIFICATION OF SURF ALGORITHM FOR FINGERPRINT MATCHING.
Babatunde et al. A multi-level model for fingerprint image enhancement
Kanagalakshmi et al. Log-Gabor orientation with run-length code based fingerprint feature extraction approach
Tan et al. Minutiae-based offline palmprint identification system
Rani et al. Personal Identification using quality image resulting from binarization and thinning techniques
Ismail et al. Enhancement of finger vein patterns extracted by maximum curvature method
Patel et al. Improve fingerprint and recognition using both minutiae based and pattern based method
Murmu et al. Fingerprint Recognition
Patil et al. Fingerprint verification based on fixed length square finger code
Sengottuvelan et al. Analysis of Living and Dead Finger Impression Identification for Biometric Application
Zhang et al. A novel algorithm for fingerprint orientation extraction and image enhancement based on Gabor filters
Palanichamy et al. A novel image alignment and a fast efficient localized euclidean distance minutia matching algorithm for fingerprint recognition system.

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
GR01 Patent grant
GR01 Patent grant