Please use this identifier to cite or link to this item: https://idr.l2.nitk.ac.in/jspui/handle/123456789/8604
Title: On Human Identification Using Running Patterns: A Straightforward Approach
Authors: Anusha, R.
Jaidhar, C.D.
Issue Date: 2020
Citation: Advances in Intelligent Systems and Computing, 2020, Vol.941, , pp.322-331
Abstract: Gait is a promising biometric for which various methods have been developed to recognize individuals by the pattern of their walking. Nevertheless, the possibility of identifying individuals by using their running video remains largely unexplored. This paper proposes a new and simple method that extends the feature based approach to recognize people by the way they run. In this work, 12 features were extracted from each image of a gait cycle. These are statistical, texture based and area based features. The Relief feature selection method is employed to select the most relevant features. These selected features are classified using k-NN (k-Nearest Neighbor) classifier. The experiments are carried out on KTH and Weizmann database. The obtained experimental results demonstrate the efficiency of the proposed method. � 2020, Springer Nature Switzerland AG.
URI: http://idr.nitk.ac.in/jspui/handle/123456789/8604
Appears in Collections:2. Conference Papers

Files in This Item:
There are no files associated with this item.


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.