Cobal -A Novel Design of CNN Basedgait Feature Extraction Using Bat-Elm for Human Tracking System

Abstract

Human gait recognition is one of the promising non-invasive biometric traits. Owing to its uniqueness, effectiveness and possession of rich discriminative features even in low resolution data, it is considered among the popular choicefor authentication purposes. The sensitivity of the model is the challenging attribute in gait recognition. Also, it is difficult to discriminate the view angle and motion of human gait in varying illumination conditions. Addressing these issues, a hybrid Convolutional Neural Network (CNN) adapted evolutionary Bat Optimized Extreme Learning Machine approach is proposed. This hybrid structure works in two folds, such that the novel spatiotemporal features including spatial and morphological features are extracted by the CNN structure. The output of the CNN is incorporated in to the Bat optimized learning scheme as a single feed forward loop to attain classification of gait movements for recognition. Extensive experiments shows reduced error rate, increasing the rate of recognition than most of the existing hybrid algorithms.