International Journal of Computer Applications |
Foundation of Computer Science (FCS), NY, USA |
Volume 121 - Number 15 |
Year of Publication: 2015 |
Authors: Zankhana Purohit, Mukesh Sakle |
10.5120/21618-4897 |
Zankhana Purohit, Mukesh Sakle . A Novel Approach Proposed for Human Recognition using GAIT. International Journal of Computer Applications. 121, 15 ( July 2015), 34-38. DOI=10.5120/21618-4897
Gait recognition is used to recognize the human by his/her walking styles. It is used in biometric authentication system, the gait is the walking sequence of human and another type of spices. In the previous methodologies a change of viewing angle causes a significant challenge for gait recognition. Proposed methodology, formulate a framework to estimate the view angle of each probe gait sequence. In this method, each gait image is represented as a set of dual-tree complex wavelet transform (DTCWT) features derived from different scales and orientations together with the x-y coordinates. The proposed representation technique is capable of capturing variations. Features extraction is done using Hough Transform. Then using the similarity of features we can recognize the person details. For classification, SVM classifier is used.