Gait recognition by combining wavelets and geometrical features

Biometric system provides more reliable and efficient means of identity verification. Gait recognition is the process of identifying a person by the way they walk. It is one kind of biometric technology that can be used to monitor people without their co-operation and has been receiving wide attention in the computer vision community. In this paper, we propose a new approach for extracting human gait features from a walking subject based on wavelet coefficients and geometrical features of the silhouette. The proposed system is tested on CASIA dataset. The experimentation results indicate that the proposed system works efficiently by combining geometrical features and wavelet coefficients. The proposed decision fusion enables the performance improvement by integrating multiple ones with different confidence measures.

[1]  Mark S. Nixon,et al.  Gait recognition by dynamic cues , 2008, 2008 19th International Conference on Pattern Recognition.

[2]  Shi Chen,et al.  Wavelet moments for gait recognition represented by motion templates , 2010, 2010 Seventh International Conference on Fuzzy Systems and Knowledge Discovery.

[3]  Qiang Wu,et al.  Automatic Gait Recognition Using Weighted Binary Pattern on Video , 2009, 2009 Sixth IEEE International Conference on Advanced Video and Signal Based Surveillance.

[4]  Jiri Matas,et al.  On Combining Classifiers , 1998, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Qin Yang,et al.  Gait Extraction and Recognition Based on Lower Leg and Ankle , 2010, 2010 International Conference on Intelligent Computation Technology and Automation.

[6]  E. Kirubakaran,et al.  Image and Formula Based Gait Recognition Methods , 2010 .

[7]  Ryo Kurazume,et al.  Person identification from human walking sequences using affine moment invariants , 2009, 2009 IEEE International Conference on Robotics and Automation.

[8]  Saeid Rahati,et al.  Gait Recognition Using Wavelet Transform , 2008, Fifth International Conference on Information Technology: New Generations (itng 2008).

[9]  Larry S. Davis,et al.  Stride and cadence as a biometric in automatic person identification and verification , 2002, Proceedings of Fifth IEEE International Conference on Automatic Face Gesture Recognition.

[10]  Zhijing Liu,et al.  Gait Representation and Recognition Using Haar Wavelet and Radon Transform , 2009, 2009 WASE International Conference on Information Engineering.

[11]  Tieniu Tan,et al.  Orthogonal Diagonal Projections for Gait Recognition , 2007, 2007 IEEE International Conference on Image Processing.

[12]  Yong Hu,et al.  Novel gait recognition technique based on SVM fusion of PCA-processed contour projection and skeleton model features , 2009, 2009 IEEE International Conference on Computational Intelligence for Measurement Systems and Applications.

[13]  Haitao Liu,et al.  Automatic gait recognition from a distance , 2010, 2010 Chinese Control and Decision Conference.

[14]  Edward Guillen,et al.  Gait Recognition System: Bundle Rectangle Approach , 2009 .

[15]  Hu Ng,et al.  Extraction of human gait features from enhanced human silhouette images , 2009, 2009 IEEE International Conference on Signal and Image Processing Applications.