The authors present results of the research on human recognition based on the video gait sequences from the CASIA Gait Database. Both linear (principal component analysis; PCA) and non-linear (isometric features mapping; Isomap and locally linear embedding; LLE) methods were applied in order to reduce data dimensionality, whereas a concept of hidden Markov model (HMM) was used for the purpose of data classification. The results of the conducted experiments formed the main subject of analysis of classification accuracy expressed by means of the Correct Classification Rate (CCR).
Feature Extraction and HMM-Based Classification of Gait Video Sequences for the Purpose of Human Identification
Studies Comp.Intelligence
2013-01-01
13 pages
Article/Chapter (Book)
Electronic Resource
English
A Vision-Based Feature Extraction Techniques for Recognizing Human Gait: A Review
Springer Verlag | 2023
|Gender Classification Based on Fusion of Multi-view Gait Sequences
Springer Verlag | 2007
|Statistical Feature Fusion for Gait-Based Human Recognition
British Library Conference Proceedings | 2004
|