Perfomance Analysics of Human Gait Recognition Based on Principal Component

Sumitra Das¹ , Deepak Gupta²

Section:Research Paper, Product Type: Isroset-Journal
Vol.4 , Issue.5 , pp.12-15, Oct-2016

Online published on Oct 28, 2016

Copyright © Sumitra Das, Deepak Gupta . This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
 

View this paper at   Google Scholar | DPI Digital Library

XML View     PDF Download

How to Cite this Paper

Abstract :
This paper represents a method to recognize the human walking individuals by their gait using Principal Component Analysis (PCA). Human Gait is used as principal identifying feature to generate the unique gait sequence for each individual. Gait is an important biometric feature which delineates the way of locomotion. The generation of binary silhouette frames of walking subjects is the initial step in this method. Some distinguishable gait features, viz., centroid, aspect ratio, orientation, height and width are extracted from the silhouette frames to acquire feature vectors. Then, the PCA is employed over the generated feature vectors to condense the information contained and produces the principal components which are used as gait sequences or signatures to represent each walking individuals. Finally the generated gait sequences are recognized by using a minimum distance classifier based on eluclidean distance. A classification rate of 93% is achieved from the proposed human recognition method which is tested using CASIA dataset.

Key-Words / Index Term :
PCA, Gait, Silhouette, Feature Vector Human Recognition, CASIA dataset

References :
[1]. Sa-Mun KIM, Dae-Jong Lee, HO-Hyun Lee, Myung-Geun Chun, “Person Recognition Using Gait and Face features on thermal images”, The Transactions of Korean Institute of Electrical Engineering, vol. 65, Issue.2, pp. 130-135, 2016.
[2]. Amamoto and A. Fujii, “Detecting obstructions and tracking moving objectsby image processing technique”, Electronics and Communications in Japan, Part 3, vol. 82, no. 11, pp. 28–37, 1999.
[3]. E. J. Marey, Analysecin´ematique de la marche [chronophotograph]. C.R.S ´eances Acad. Sci. 98:1218- 1225, 1884
[4]. L. Lee and W.E.L. Grimson, “Gait analysis for recognition and classification”, Fifth IEEE Conference on Face and Gesture Recognition, 155-161, 2002.
[5]. L. Wang, W.M. Hu, and T.N. Tan, “Recent Developments in Human Motion Analysis” Pattern Recognition, vol. 36, no. 3, pp. 585-601, 2003.
[6]. Haritaoglu, D. Harwood, and L.S. Davis, “W4: real-time surveillance of people and their activities,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no. 8, pp. 809–830, Aug. 2000.
[7]. Troje, N. F. Decomposing biological motion: A framework for analysis and synthesis of Human gait patterns. Journal of Vision, 2, 2002.
[8]. C. Y. Yam and M.S. Nixon, “Model-based Gait Recognition”, Encyclopedia of Biometrics,, Vol.12, pp.1082-1088, 2009
[9]. G. Johansson, “Visual perception of biological motion and a model for its analysis”, Perception and Psychophysics, Vol. 14 (1973) 201–211
[10]. S. NiyogI and E. Adelson, “Analyzing and Recognizing Walking Figures in XYT”, IEEE Computer Society Conference on Computer Vision and Pattern Recognition, Seattle, Wash, USA, pp. 469-474, 1994.
[11]. Chiraz BenAbdelkader, Ross Cutler and Larry Davis, “View-Invariant Estimation of Height and Stride for Gait Recognition”, Biometric Authentication, European Conference on Computer Vision: International. Workshop, vol.4, pp. 155-167, 2002.
[12]. Jinyan Chen, Jiansheng Liu, ”Average Gait Differential Image Based Human Recognition”, The Scientific World Journal, vol.2014, pp. 1-8, 2014.
[13]. Murat Ekinci, “A New Attempt to Silhouette-Based Gait Recognition for Human Identification”, Computer Science Journals, vol. 4013, pp. 443-454, 2006.
[14]. Hu Ng, Hau-Lee Tong, Wooi-Haw Tan and Timothy TzenVun Yap, ”Human Identification Based on Extracted Gait Features”, International Journal on New Computer Architectures and Their Applications, vol. 1, pp. 358-370, 2011.
[15]. Bissacco, A. Chiuso, Y. Ma, S. Soatto, “ Recognition of human gaits”, in Computer Vision and Pattern Recognition, 2001, Volume II., Kauai, HI (2001) 52–57.