Analysis gait recognition performance based on the walking speed

• Main Author: Liu, Mengrui
• Other Authors: Ma Kai Kuang
• Format: Final Year Project
• Language: English
• Published: 2018
• Subjects: DRNTU::Engineering
• Online Access: http://hdl.handle.net/10356/75193
• Institution: Nanyang Technological University

This report proposes the gait recognition algorithm based on principal component analysis (PCA) for gait energy image (GEI) and analysts the impact of various walking speeds on the gait recognition. The gait energy image is obtained by preprocessing the original gait sequence. The eigenvalues ​​and the corresponding eigenvectors are extracted by the principal component analysis. After the principal components are obtained, they are projected to the low dimension space and classified using the k-nearest neighbor method. The algorithm is verified on the CASIA database. The experimental results show that the recognition performance can be effected by other factors except existing well-known factors.