PERSONAL AUTHENTICATION USING MULTIPLE PALMPRINT FEATURES

By
JEMSHEER AHMED P

A PROJECT REPORT Submitted to the DEPARTMENT OF INFORMATION TECHNOLOGY In partial fulfillment For the award of the degree of

MASTER OF ENGINEERING
IN

SOFTWARE ENGINEERING

NOORUL ISLAM CENTRE FOR HIGHER EDUCATION NOORUL ISLAM UNIVERSITY

Kumaracoil, Thuckalay, Kanyakumari District, Tamilnadu

November 2011

ii

DEPARTMENT OF INFORMATION TECHNOLOGY NOORUL ISLAM UNIVERSITY KUMARACOIL

BONAFIDE CERTIFICATE
Certified that this project report titled Personal Authentication Using Multiple Palmprint Features is the bonafide work of Mr P. JEMSHEER AHMED, Register No: 0110521011 who carried out the research under my supervision. Certified further, that to the best of my knowledge the work reported herein does not form part of any other project report or dissertation on the basis of which a degree or award was conferred on an earlier occasion on this or any other candidate.

SUPERVISOR Prof.S.Palanikumar, B.E.,M.E.(Ph.D) Department of IT Noorul Islam University Kumaracoil

HEAD OF THE DEPARTMENT Prof. R. Mathusoothana S. Kumar, B.E.,M.E.(Ph.D) Department of IT Noorul Islam University Kumaracoil

Submitted for the Project Viva-Voce Examination held on .

Internal Examiner

External Examiner

iii

ACKNOWLEDGEMENT

First and foremost I acknowledge the abiding presence and the abounding grace of OUR ALMIGHTY GOD for his unseen hand yet tangible guidance all through the formation of this project. I express my sincere gratitude to our Chairman Janab Dr. A.P.Majeed Khan for providing me all the support. I am extremely grateful to our Principal Prof. Dr. N. Chandrashekhar, B.E., Ph.D. (IIT Madras), for his inspiration to me in proceeding with this project. I sincerely thank Prof. Mathusoothana S.Kumar, B.E., M.E., (Ph.D), Head of the Department for his encouragement, valuable suggestions and advice for this project. I would like to express my heartfelt thanks to Prof.S.Palanikumar B.E., M.E.(Ph.D), my project guide, for her valuable guidance and care shown in aiding me consummate this project immaculately and impeccably and also, for her munificent support and intellectual guidance throughout the year. I express my gratitude for all the teaching and non-teaching staffs of our Information Technology Department who have helped me in one way or the other for the successful completion of this project. Finally, I appreciate the patience and solid support of my family and enthusiastic friends for their encouragement and moral support for this effort.

iv

ABSTRACT

In this project, a new approach for personal authentication using palm image is presented. Palmprint patterns are a very reliable biometric and require minimum co-operation from the user for extraction. Palmprint recognition uses the persons palm as a biometric for identifying or verifying who the person is. Based on the features of palm personal identification can be done. Features of different palms have great variety. No two palmprint are completely identical. Compared to fingerprint identification palmprint include much more information. Palm images may contain geometry features, principle line feature, wrinkle feature, datum point feature, delta point feature, minutiae feature. Multiple features can be utilized to uniquely identify a palm image rather than using single feature. For using multiple features there must be techniques to separately extract those features. The fusion of the extracted multiple features will obtain a unique score to represent a palm image. In this project three ensembles of matchers which employ different feature representation schemes of the palm images have designed. Discrete cosine coefficients; invariant local binary patterns; Gabor filters are the three schemes to represent features of palmprint. Each ensemble is obtained by varying the features used to train their matchers. Experimental results conrm that the three methods give complementary information which has been exploited by fusion rules. Finally, we combine our Palm based method system with other biometric characteristics that can be extracted from the hand obtaining a further improvement of the performance.

TABLE OF CONTENTS

CHAPTER NO

TITLE

PAGE NO IV VIII IX X

ABSTRACT LIST OF TABLES LIST OF FIGURES LIST OF ABBRIVIATIONS

INTRODUCTION 1.1 OBJECTIVE 1.2 PROBLEM STATEMENT 1.3 OVERVIEW 1 2 3

LITERATURE SURVEY 2.1 BASIC CONCEPTS 2.1.1 Image 2.1.2 Image Processing 2.1.3 Digital Image Processing 2.1.4 History of Digital Image Processing 2.1.5 Tasks of Image Processing 2.1.6 Digital Image Representation 2.1.7 Digital Images 2.1.8 Application of Digital Image Processing 2.2 PERSONAL AUTHENTICATION 2.3 BIOMETRICS 2.4 NEED OF BIOMETRICS 2.5 BASIC STEPS IN BIOMETRIC SYSTEM 2.5.1 Data Acquisition 4 4 5 6 6 7 7 7 8 8 8 10 11 11

vi 2.5.2 Preprocessing Module 2.5.3 Feature Extraction 2.5.4 Feature Matching 2.5.5 Decision Module 2.6 PERFORMANCE EVALUATION OF BIOMETRICS 2.7 PALM PRINTS 2.7.1 Principle Lines 2.7.2 Wrinkles 2.7.3 Ridges 2.8 PALM PRINT FEATURES 2.8.1 Geometry Features 2.8.2 Principal Line Features 2.8.3 Wrinkle Features 2.8.4 Datum Point Features 2.8.5 Delta point Features 2.8.6 Minutiae Features 2.9 APPLICATIONS OF PALM PRINT 2.9.1 Personal Identification 2.9.2 Fortune Telling 2.9.3 Palmprint In Diagnosis 2.10 ADVANTAGES OF PALM PRINT 11 11 11 11 12 12 13 13 14 14 14 14 14 14 15 15 15 15 15 15 15

EXISTING SYSTEMS 3.1 PALMPRINT FEATURE EXTRACTION USING 2-D GABOR FILTERS 3.2 PERSONAL AUTHENTICATION USING HAND IMAGES 3.3 FISHERPALMS RECOGNITION 3.4 PALMPRINT RECOGNITION USING EIGENPALMS FEATURES 24 BASED PALM PRINT 22 19 17

vii 3.5 PERSONAL AUTHENTICATION USING MULTIPLE PALMPRINT REPRESENTATION 26

PROPOSED SYSTEMS 4.1 INTRODUCTION 4.2 SYSTEM ARCHITECTURE 4.2.1 Feature Extraction : Discrete Cosine Transform 4.2.2 Feature Extraction : Invariant Local Binary Patterns 4.2.3 Feature Extraction : Gabor Filters 4.3 DATA FLOW DIAGRAM 33 33 34 29 30 33

CONCLUSION REFERENCES

36 37

viii

LIST OF TABLES

SL.NO

TABLE NAME

CONTENT

PAGE

1 2 3

2.1 2.2 4.1

Medium Grey Bright White Different Approaches in Palmprint Processing

5 5 29

ix

LIST OF FIGURES

SL.NO

FIGURE NAME

CONTENT

PAGE

1 2 3 4

2.1 2.2 4.1 4.2

Types of Biometrics Palm Prints Proposed System Architecture Data Flow Diagram

9 13 32 34

LIST OF ABBRIVIATIONS

ABBRIVIATION

EXPANSION

ROI ROC FAR FRR EER CMC DB PCA NN DCT FG LBP FAR

Region Of Interest Receiver Operating Characteristic Fault Acceptance Rate Fault Rejection Rate Equal Error Rate Cumulative Match Characteristic Database Principal Component Analysis Nearest Neighbor Discrete Cosine transform Gabor Filter Local Binary Pattern Fraudulent Access Rate