IIAE CONFERENCE SYSTEM, The 1st IEEE/IIAE International Conference on Intelligent Systems and Image Processing 2013 (ICISIP2013)

Font Size: 
Multi-scale principal component analysis based gait recognition
Senapathi Rohith Sai, Rohan Ravi

Last modified: 2013-10-01


Gait recognition aims to identify individuals by the manner in which they walk. The prime innovation in this paper is a simple yet effective method of modelling the lower limbs using spline curves. To start with, we extract the binary silhouette from the monocular images. The gait cycle is extracted by exploiting the periodic variance of the width vector of the silhouette. Then, the novel gait feature area under the lower limbs, modelled using a cubic spline curve, is computed for each of the silhouettes in a cycle. Later Discrete cosine Transform is applied to the feature vector to create a feature matrix. The method of Multi-scale principal component analysis (MSPCA) was adopted for dimensional reduction of feature matrix containing the area signals. Finally Neuro-fuzzy and the K-NN classifiers are used to classify the final feature vectors. Experimental results on the CASIA datasets A, B show that the best accuracy achieved using Neuro-fuzzy and K-NN classifier is 95% and 97.1% respectively.


Image processing


(1)    J.E.Cutting and L.T. Kozlowski, “Recognition of Friends by Their Walk,” Bull.Of the Psychonomic Soc, vol. 9, pp. 353-356, 1977.

(2)    S.Niyogi and E.Adelson,“Analyzing Gait with Spatiotemporal Surfaces,” Proc. IEEE Workshop Non-Rigid Motion, pp. 24-29, 1994.

(3)    Y.Yam, M.S.Nixon, and J.N.Carter. Gait recognition by walking and running: A model-based approach, 2002. in Proceedings of 5th Asian Conference on Computer Vision.

(4)    D. Cunado, M. S. Nixon, and J. N. Carter. Using gait as a biometric,via phase-weighted magnitude spectra, 1997. in Proceedings of 1st International Conference on Audio-and Video-Based Biometric Person Authentication.

(5)    C. S. Lee and A. Elgammal. Gait tracking and recognition using person-dependent dynamic shape model,2006, in Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition.

(6)    J. Little and J. Boyd, “Recognizing People by Their Gait: The Shape of Motion,” Videre: J. Computer Vision Research, vol. 1, no. 2, pp. 232, 1998.

(7)    Y.Chai, Q.Wang, R.Zhao,and C.Wu. A new automatic gait recognition method based on the perceptual curve, 2005. IEEE International Conference on Intelligent Information Communication Technologies for Better Human Life.

(8)    R.Tanawongsuwan and A.Bobick. Gait recognition from time-normalized joint-angle trajectories in the walking plane,2001.In Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

(9)    yanmei chai, jinchang ren, rongchun zhao, jingpin jia, Automatic gait recognition using dynamic variance features, proceedings of 7th international conference on Face and Gesture Recognition(FGR’06).

(10)B. R. Bakshi,. “Multiscale PCA with application to multivariate statistical process monitoring,” AIChE J, vol. 44, no. 7, pp. 1596-1610, Jul. 1998.

(11)Su-li XU, Qian-jin ZHANG. Gait Recognition using Fuzzy Principal Component Analysis, 2010 IEEE.

(12)C. Chen, J. Liang, H. Zhao, H. Hu and J. Tian, “Frame di_erence energy image for gait recognition with incomplete silhouettes,” Pattern Recognition Letters, 30, 977–984 (2009).

Full Text: PDF