Date of Publication :18th April 2018

Abstract: Gait recognition is an effective biometric feature to identify persons from a distance by the way people walk or run. Gait recognition technology is not limited to security applications; researchers also envision medical applications for the technology. For example, recognizing changes in walking patterns early on can help to highlight biomechanical abnormalities such as Parkinson’s disease and multiple sclerosis in their earliest stages. The greatest turmoil in gait recognition is to identify an individual with cofactors and in sundry situations. View difference causes degradation of gait recognition accuracy, and so several solutions have been proposed to suppress this degradation. Thus gait identification of individuals with cofactors in multiple views becomes even more troublesome. In this paper we propose a method to descry cofactor affected probes in a stipulated range of views. Entire GEI Image is parted into three segments reckoning the occurrence of cofactor in it. The cofactor encompassed segment will be detected and eliminated. The segments are re-joined for final classification. The CASIA gait database is used here as a training and testing data. This is performed successfully for a given range of views with highly dynamic algorithms bringing forth a good accuracy rate and more adaptable than other prevalent methods.

Reference :