GVIP Journal    

GVIP
 VOLUME={08}, ISSUE = {2} ICGST
Efficient Iris Recognition through Improvement in Iris Segmentation Algorithm
 
*.S. Uma Maheswari, P. Anbalagan,  T.Priya
Department of Electrical and Electronics Engineering,
Coimbatore Institute of Technology, Coimbatore-641 014, Tamil Nadu, INDIA.
Tel: +91 422 2574071-72, Extn.331

Abstract

Human recognition technology research projects promises new life to many security consulting firms and personal identification system manufacturers. Iris recognition is considered to be the most reliable biometric authentication system. This paper suggests a novel segmentation algorithm to localize the iris region from the eye image in an iris recognition system based on Daugman’s Algorithm. The localized iris image is normalized to eliminate dimensional inconsistencies between iris regions using Daugman’s rubber sheet model. Next the  features of the iris region is encoded by convolving the normalized iris region with 2D Gabor filter and phase quantizing the output in order to produce a bitwise biometric template. After projecting onto Gabor filters, phase information is extracted and stored as a bit code. Hamming distance measurement is done to match the iris code and authenticate the users. The two iris codes are found to match if the hamming distance is below 0.35. The iris recognition system based on Integro-differential operator segmentation method was also developed for comparative analysis. The systems suggested in this paper are written in Matlab. Digitized grayscale eye images of Chinese Academy of Sciences – Institute of Automation (CASIA) has been used for determining the performance of the proposed system.

 Keywords: Biometric authentication, Iris Recognition, Segmentation, Hamming Distance.

(P1150820002, 748 KB)

Biographies:

Mrs. S. Uma Maheswari received her B.E Degree in Electronics and Communication Engineering from Government College of Technology, Coimbatore  in the year 1985 and M.E (Applied Electronics) from Bharathiar University in 1991. Currently she is pursuing Ph.D research work in the area of Image Processing under the guidance of Dr.P.Anbalagan. She is a Selection Grade Lecturer of EEE department in Coimbatore Institute of Technology.  She is having 20 years of teaching experience. She has published 17 technical papers in national /international conferences. She is a Member of IE (India), Life Member in Indian Society for Technical Education (India), Life Member in Systems Society of India, and Life Member in Council of Engineers (India). Her special fields of interest are Digital Image Processing and Digital Signal Processing.

Dr. P. Anbalagan received his B.E. Degree in Electrical and Electronics Engineering from Government College of Technology in the year 1973 and M.Sc (Engg.)   from     Madras University   in   1977. He obtained his Ph.D Degree from   Bharathiar University in the   area of   Digital Protection   of Power Systems in the year 1994. He is having a teaching experience of 31 years. He is currently Professor and Head of EEE department in Coimbatore Institute of Technology, Coimbatore. He has published 112 technical papers in National  / International Conferences and Journals. He is a     Fellow Member IE (India) and Senior    Member of IEEE. Life Member in Indian Society for Technical Education (India), Life Member in Systems Society of India, and Life Member in Council of Engineers (India). His special fields of interest are Digital Protection of power systems and Embedded Systems

Ms T. Priya  received her B.E Degree in Electronics and Instrumentation Engineering from  Thiagarajar College of  Engineering, Madurai  in the year 2006  and  Currently pursuing M.E Applied Electronics) from Coimbatore  Institute of Tech.  

BibTex:

@ARTICLE{P1150820002,

AUTHOR = {S. Uma Maheswari and P. Anbalagan and  T.Priya},

TITLE = {Efficient Iris Recognition through Improvement in Iris Segmentation Algorithm},

JOURNAL ={ICGST International Journal on Graphics, Vision and Image Processing, GVIP},

YEAR = {2008},

VOLUME = {08},

ISSUE ={II},

PAGES={29--35}

}

(P1150820002, 748 KB)