TY - GEN
T1 - Modeling the individuality of iris pattern and the effectiveness of inconsistent bit masking strategy
AU - Li, Bin
AU - Yan, Zifei
AU - Zuo, Wangmeng
AU - Yue, Feng
N1 - Publisher Copyright:
© 2015 IEEE.
PY - 2015/6/16
Y1 - 2015/6/16
N2 - Iris recognition is one of the most accurate biometric technologies. The uniqueness of iris, also known as iris individuality, has been widely accepted as one foundation for iris recognition. Although a few iris individuality mod- els have been proposed, they are either incomplete or less accurate. In this paper, we investigate the iris individual- ity problem using Daugman's iriscode method. We divide the bits in an iriscode into two groups, i.e., consistent and inconsistent bits, and provide the individuality analysis by both FAR and FRR modeling. Numeric evaluation using re- al iris data shows its usefulness in predicting the empirical performance. Furthermore, till now it is just experimentally confirmed that the recognition accuracy could be improved by masking out inconsistent bits. In order to formally e- valuate the effectiveness of this strategy, we derive the iris individuality model after masking out the inconsistent bits. Comparison of the two models has demonstrated the im- proved accuracy of the masking strategy, and the drop of EER is up to about 80%.
AB - Iris recognition is one of the most accurate biometric technologies. The uniqueness of iris, also known as iris individuality, has been widely accepted as one foundation for iris recognition. Although a few iris individuality mod- els have been proposed, they are either incomplete or less accurate. In this paper, we investigate the iris individual- ity problem using Daugman's iriscode method. We divide the bits in an iriscode into two groups, i.e., consistent and inconsistent bits, and provide the individuality analysis by both FAR and FRR modeling. Numeric evaluation using re- al iris data shows its usefulness in predicting the empirical performance. Furthermore, till now it is just experimentally confirmed that the recognition accuracy could be improved by masking out inconsistent bits. In order to formally e- valuate the effectiveness of this strategy, we derive the iris individuality model after masking out the inconsistent bits. Comparison of the two models has demonstrated the im- proved accuracy of the masking strategy, and the drop of EER is up to about 80%.
UR - https://www.scopus.com/pages/publications/84942540532
U2 - 10.1109/ISBA.2015.7126351
DO - 10.1109/ISBA.2015.7126351
M3 - 会议稿件
AN - SCOPUS:84942540532
T3 - 2015 IEEE International Conference on Identity, Security and Behavior Analysis, ISBA 2015
BT - 2015 IEEE International Conference on Identity, Security and Behavior Analysis, ISBA 2015
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2015 IEEE International Conference on Identity, Security and Behavior Analysis, ISBA 2015
Y2 - 23 March 2015 through 25 March 2015
ER -