Adaptive Fusion of Multi-Biometrics for Human Identification in Video

Abstract:

The purpose of multiple biometric fusion is to improve the recognition performance by utilizing their complementary. In this paper, the feature fusion recognition method of multi-view face and gait in video is studied, and a adaptive decision fusion method is proposed. The results showed that the adaptive fusion features carry the most discriminating power compared to any individual biometric and other static fusion rules like Max and Sum.

• Periodical: Applied Mechanics and Materials (Volumes 719-720)
• Pages: 1013-1018
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.719-720.1013
• Online since: January 2015
• Authors: Ying Hui Kong, Pei Yao Chen*
• Keywords: Adaptive, Face, Fusion, Gait, Video

References

[1] Koichiro Niinuma, Unsang Park, and Anil K. Jain. Soft Biometric Traits for Continuous User Authentication [J]. Information Forensics and Security, 5(4): 771–780, (2004).

DOI: 10.1109/tifs.2010.2075927

[2] Xiaoli Zhou and Bir Bhanu. Integrating Face and Gait for Human Recognition at a Distance in Video [J]. IEEE Transactions on System, man, and Cybernetics, 37(5): 1119–1137, (2007).

DOI: 10.1109/tsmcb.2006.889612

[3] Li Yi, Ming Dong. Gait and face profile fusion based human identification at a distance in video [J]. Journal of Scientific Instrument, 2011, 32(2): 264—270.

[4] Xin Geng, Liang Wang, MingLi, QiangWu, and Kate Smith-Miles. Adaptive Fusion of Gait and Face for Human Identification in Video [J]. Applications of Computer Vision, 7(9): 1–6, (2008).

DOI: 10.1109/wacv.2008.4544006

[5] Ling linben, Chen Chaoying. Optimal Weight Distribution Principle Used in the Fusion of Multi-sensor Data, 2006: 37–39.

[6] Theekhanont. P, Miguet. S, Kurutach.W. Gait Recognition using GEl and Pattern Trace Transform [J]. Information Technology in Medicine and Education, 3(5): 936-940, (2012).

DOI: 10.1109/itime.2012.6291457

[7] Guo Lei, Wang Qiuguang. Research of Face Detection Based on Ad boost Algorithm and OpenCV Implementation [J]. Journal of Harbin University of Science and Technology, 2009, 14(5): 123–126.

[8] Yu-Xiong Wang, Yu-Jin Zhang. Nonnegative Matrix Factorization: A Comprehensive Review [J]. IEEE Transaction on knowledge and data engineering, 25(6): 1337-1351, (2013).

[9] Chengjun Liu. Learning the Uncorrelated, Independent, and Discriminating Color Spaces for Face Recognition [J]. Information Forensics and Security, 3(2): 213-222, (2008).

DOI: 10.1109/tifs.2008.923824

[10] Zhou Bin, Lin Xirong. Optimal weight of the score level multiple biometric feature fusion [J]. J T singhua Univ(Sci&Tech), 2008, 48(2): 192–195.