ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술지 Fuzzy Difference-of-Gaussian-Based Iris Recognition Method for Noisy Iris Images
Cited 9 time in scopus Download 0 time Share share facebook twitter linkedin kakaostory
저자
강병준, 박강령, 유장희, 문기영
발행일
201006
출처
Optical Engineering, v.49 no.6, pp.1-10
ISSN
0091-3286
출판사
SPIE
DOI
https://dx.doi.org/10.1117/1.3447924
초록
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 SPIE.
키워드
difference of Gaussian, fuzzy theory, iris recognition
KSP 제안 키워드
Binary codes, Confidence Level, Degrees of freedom(DOF), Difference of Gaussian(DoG), DoG filter, Feature values, Frequency components, Fuzzy theory, Iris Recognition Accuracy, Iris feature, Iris patterns