Abstract
Human gait analysis is a novel topic in the field of computer vision with many famous applications like prediction of osteoarthritis and patient surveillance. In this application, the abnormal behavior like problems in walking style is detected of suspected patients. The suspected behavior means assessments in terms of knee joints and any other symptoms that directly affected patients’ walking style. Human gait analysis carries substantial importance in the medical domain, but the variability in patients’ clothes, viewing angle, and carrying conditions, may severely affect the performance of a system. Several deep learning techniques, specifically focusing on efficient feature selection, have been recently proposed for this purpose, unfortunately, their accuracy is rather constrained. To address this disparity, we propose an aggregation of robust deep learning features in Kernel Extreme Learning Machine. The proposed framework consists of a series of steps. First, two pre-trained Convolutional Neural Network models are retrained on public gait datasets using transfer learning, and features are extracted from the fully connected layers. Second, the most discriminant features are selected using a novel probabilistic approach named Euclidean Norm and Geometric Mean Maximization along with Conditional Entropy. Third, the aggregation of the robust features is performed using Canonical Correlation Analysis, and the aggregated features are subjected to various classifiers for final recognition. The evaluation of the proposed scheme is performed on a publicly available gait image dataset CASIA B. We demonstrate that the proposed feature aggregation methodology, once used with the Kernel Extreme Learning Machine, achieves accuracy beyond 96%, and outperforms the existing works and several other widely adopted classifiers.