TY - GEN
T1 - A novel hybrid multibiometrics based on the fusion of dual iris, visible and thermal face images
AU - Wang, Ning
AU - Li, Qiong
AU - El-Latif, Ahmed A.Abd
AU - Yan, Xuehu
AU - Niu, Xiamu
PY - 2013
Y1 - 2013
N2 - Human identification via multibiometrics is a very promising approach to improve overall systems security and recognition performance. In this paper, a novel multibiometrics fusion strategy based on dual iris, visible and thermal face traits is proposed. Firstly, 1D Log-Gabor dual iris codes are fused into a serial feature vector to address the noisy problems of iris. Then, Complex Gabor Jet Descriptor (CGJD) is proposed to enhance the feature representation abilities for thermal and visible face images. Finally, a score level fusion algorithm based on Aczél-Alsina triangular norm (AA t-norm) is proposed to enlarge the distance of imposters and narrow the distance of genuine simultaneously. All the simulations are performed on a virtual multibiometrics database, which merges the challenging CASIA-Iris-Thousand database with dual iris and the NVIE face database with visible and thermal face images. The proposed fusion strategy achieves EER of 2.89*10(-4) and d of 8.87, which outperforms the state-of-theart methods.
AB - Human identification via multibiometrics is a very promising approach to improve overall systems security and recognition performance. In this paper, a novel multibiometrics fusion strategy based on dual iris, visible and thermal face traits is proposed. Firstly, 1D Log-Gabor dual iris codes are fused into a serial feature vector to address the noisy problems of iris. Then, Complex Gabor Jet Descriptor (CGJD) is proposed to enhance the feature representation abilities for thermal and visible face images. Finally, a score level fusion algorithm based on Aczél-Alsina triangular norm (AA t-norm) is proposed to enlarge the distance of imposters and narrow the distance of genuine simultaneously. All the simulations are performed on a virtual multibiometrics database, which merges the challenging CASIA-Iris-Thousand database with dual iris and the NVIE face database with visible and thermal face images. The proposed fusion strategy achieves EER of 2.89*10(-4) and d of 8.87, which outperforms the state-of-theart methods.
KW - Dual iris
KW - Multibiometrics
KW - Score level
KW - Triangular norm
KW - Visible and thermal Face
UR - https://www.scopus.com/pages/publications/84886028819
U2 - 10.1109/ISBAST.2013.38
DO - 10.1109/ISBAST.2013.38
M3 - 会议稿件
AN - SCOPUS:84886028819
SN - 9780769550107
T3 - Proceedings - 2013 International Symposium on Biometrics and Security Technologies, ISBAST 2013
SP - 217
EP - 223
BT - Proceedings - 2013 International Symposium on Biometrics and Security Technologies, ISBAST 2013
T2 - 2013 International Symposium on Biometrics and Security Technologies, ISBAST 2013
Y2 - 2 July 2013 through 5 July 2013
ER -