Authors: C. Nandini, C.N. Ravi Kumar
Addresses: Dept of CS&E, Vidya Vikas Institute of Engineering & Technology Mysore, India. ' Dept of CS&E, S.J. College of Engineering Mysore, India
Abstract: Human gait is a spatio-temporal phenomenon and typifies the motion characteristics of an individual. The gait of a person is easily recognisable when extracted from a side view of the person. Accordingly, gait-recognition algorithms work best when presented with images where the person walks parallel to the camera (i.e. the image plane). A set of stances or key frames that occur during the walk cycle of an individual is chosen. This paper presents a novel approach adopted in automatic gait recognition in which the silhouette extracted is represented using Shannon entropy and extracts the height of the subject and periodicity of the gait. To classify unknown gait, they need to match the nearest neighbour in the stored database of extracted gait features, and the proposed approach are tested on the data sets and is found to be quite satisfactory in natural walk conditions. In addition, the proposed decision fusion enables the performance improvement by integrating multiple ones with different confidence measures.
Keywords: gait recognition; Shannon entropy; edge based features; decision fusion; biometrics; comprehensive framework; silhouettes; gait stance; behavioural biometric; human gait; human height; gait periodicity; natural walk.
International Journal of Biometrics, 2008 Vol.1 No.1, pp.129 - 137
Published online: 04 Jun 2008 *Full-text access for editors Access for subscribers Purchase this article Comment on this article