Fuzzy difference-of-Gaussian-based iris recognition method for noisy iris images

Byung Jun Kang; Kang Ryoung Park; Jang-Hee Yoo; Kiyoung Moon

doi:10.1117/1.3447924

1 June 2010 Fuzzy difference-of-Gaussian-based iris recognition method for noisy iris images

Byung Jun Kang, Kang Ryoung Park, Jang-Hee Yoo, Kiyoung Moon

Author Affiliations +

Optical Engineering, Vol. 49, Issue 6, 067001 (June 2010). https://doi.org/10.1117/1.3447924

Abstract

Iris recognition is used for information security with a high confidence level because it shows outstanding recognition accuracy by using human iris patterns with high degrees of freedom. However, iris recognition accuracy can be reduced by noisy iris images with optical and motion blurring. We propose a new iris recognition method based on the fuzzy difference-of-Gaussian (DOG) for noisy iris images. This study is novel in three ways compared to previous works: (1) The proposed method extracts iris feature values using the DOG method, which is robust to local variations of illumination and shows fine texture information, including various frequency components. (2) When determining iris binary codes, image noises that cause the quantization error of the feature values are reduced with the fuzzy membership function. (3) The optimal parameters of the DOG filter and the fuzzy membership function are determined in terms of iris recognition accuracy. Experimental results showed that the performance of the proposed method was better than that of previous methods for noisy iris images.

©(2010) Society of Photo-Optical Instrumentation Engineers (SPIE)

Citation Download Citation

Byung Jun Kang, Kang Ryoung Park, Jang-Hee Yoo, and Kiyoung Moon "Fuzzy difference-of-Gaussian-based iris recognition method for noisy iris images," Optical Engineering 49(6), 067001 (1 June 2010). https://doi.org/10.1117/1.3447924

Published: 1 June 2010

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available