Gait recognition based on outermost contour

Authors:
Lili Liu;Yilong Yin;Wei Qin
Affiliations:
School of Computer Science and Technology, Shandong University, Jinan, Shandong, China;School of Computer Science and Technology, Shandong University, Jinan, Shandong, China;School of Computer Science and Technology, Shandong University, Jinan, Shandong, China
Venue:
RSKT'10 Proceedings of the 5th international conference on Rough set and knowledge technology
Year:
2010

Citing 5
Cited 0

Eigenfaces vs. Fisherfaces: Recognition Using Class Specific Linear Projection

IEEE Transactions on Pattern Analysis and Machine Intelligence
Gait Analysis for Recognition and Classification

FGR '02 Proceedings of the Fifth IEEE International Conference on Automatic Face and Gesture Recognition
Silhouette Analysis-Based Gait Recognition for Human Identification

IEEE Transactions on Pattern Analysis and Machine Intelligence
Individual Recognition Using Gait Energy Image

IEEE Transactions on Pattern Analysis and Machine Intelligence
A Framework for Evaluating the Effect of View Angle, Clothing and Carrying Condition on Gait Recognition

ICPR '06 Proceedings of the 18th International Conference on Pattern Recognition - Volume 04

Quantified Score

Hi-index	0.00

Visualization

Abstract

Gait recognition aims to identify people by the way they walk. In this paper, a simple but effective gait recognition method based on Outermost Contour is proposed. For each gait image sequence, an adaptive silhouette extraction algorithm is firstly used to segment the images and a series of postprocessing is applied to the silhouette images to obtain the normalized silhouettes with less noise. Then a novel feature extraction method based on Outermost Contour is proposed. Principal Component Analysis (PCA) and Multiple Discriminant Analysis (MDA) are adopted to reduce the dimensionality of the feature vectors and to optimize the class separability of different gait image sequences simultaneously. Two simple pattern classification methods are used on the low-dimensional eigenspace for recognition. Experimental results on a gait database of 100 people show that the accuracy of our algorithm achieves 97.67%.