Frame difference history image for gait recognition

• Published in: 2011 International Conference on Machine Learning and Cybernetics Vol. 4; pp. 1785 - 1788
• Main Authors: Chun-Chieh Lee, Chi-Hung Chuang, Jun-Wei Hsieh, Ming-Xuan Wu, Kuo-Chin Fan
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.07.2011
• Subjects: Biometrics; Computational modeling; Feature extraction; Gait recognition; Humans; Image recognition; Legged locomotion; Load modeling; PCA/LDA; Video Surveillance
• ISBN: 9781457703058; 145770305X
• ISSN: 2160-133X
• DOI: 10.1109/ICMLC.2011.6017007

In this paper, we propose a simple but effective human identification method based on gait features using frame difference history image (FDHI). Before constructing the FDHI feature, a sequence-based silhouette normalization scheme and an alignment pre-processing step are applied. After that, a post-processing step is devised for getting more representative gait signatures for human identification. Two types of FDHI templates are then extracted and represented more compactly by a dimensionality reduction technique, i.e., Principal Component Analysis (PCA) followed by Linear Discriminant Analysis (LDA). The transformed feature vectors are then respectively classified by individual K-Nearest Neighbor (KNN) classifiers. Lastly, the final classification decision is made by a fusion technique. Experimental results are provided to prove the superiority of the proposed method.