TY - GEN
T1 - An efficient iris texture analysis based on HAAR wavelet 2D Log Gabor and monogenic filter
AU - Tajouri, Imen
AU - Ghorbel, Ahmed
AU - Aydi, Walid
AU - Masmoudi, Nouri
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2017/6/16
Y1 - 2017/6/16
N2 - Human iris is a perfect part of the body for biometric identification. In fact, iris patterns are unique and stable that is why two people never occur to have the same iris texture even if they are twins. In this paper, we tried to improve the Rai's algorithm feature extraction method. On the one hand, we selected this algorithm thanks to its simplicity as compared to other algorithms that use complex techniques of segmentation such as snake. On the other hand, it has impressive results for some databases like CASIA V1.0 and CASIA V3.0. To enhance Rai's algorithm, we suggested using the HAAR wavelet, and the combined 2D Log Gabor filter along with the monogenic filter for feature extraction. Thus, our approach achieved a trade-off between the richness of the HAAR and Gabor features and the distinctiveness of the monogenic features. Daubechies wavelet and the Histogram of Oriented Gradient (HOG) were also tested. The experimental results on the CASIA iris database V3.0 show that the proposed method, using the HAAR wavelet, the combined monogenic filter and 2D Log Gabor filter yields a recognition rate of 94.45 %.
AB - Human iris is a perfect part of the body for biometric identification. In fact, iris patterns are unique and stable that is why two people never occur to have the same iris texture even if they are twins. In this paper, we tried to improve the Rai's algorithm feature extraction method. On the one hand, we selected this algorithm thanks to its simplicity as compared to other algorithms that use complex techniques of segmentation such as snake. On the other hand, it has impressive results for some databases like CASIA V1.0 and CASIA V3.0. To enhance Rai's algorithm, we suggested using the HAAR wavelet, and the combined 2D Log Gabor filter along with the monogenic filter for feature extraction. Thus, our approach achieved a trade-off between the richness of the HAAR and Gabor features and the distinctiveness of the monogenic features. Daubechies wavelet and the Histogram of Oriented Gradient (HOG) were also tested. The experimental results on the CASIA iris database V3.0 show that the proposed method, using the HAAR wavelet, the combined monogenic filter and 2D Log Gabor filter yields a recognition rate of 94.45 %.
KW - 2D Log Gabor filter
KW - feature extraction
KW - monogenic filter
KW - SVM
UR - http://www.scopus.com/inward/record.url?scp=85025127965&partnerID=8YFLogxK
U2 - 10.1109/STA.2016.7952108
DO - 10.1109/STA.2016.7952108
M3 - Conference contribution
AN - SCOPUS:85025127965
T3 - 2016 17th International Conference on Sciences and Techniques of Automatic Control and Computer Engineering, STA 2016 - Proceedings
SP - 153
EP - 157
BT - 2016 17th International Conference on Sciences and Techniques of Automatic Control and Computer Engineering, STA 2016 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 17th International Conference on Sciences and Techniques of Automatic Control and Computer Engineering, STA 2016
Y2 - 19 December 2016 through 21 December 2016
ER -