Gait Recognition Analysis for Human Identification Analysis-A Hybrid Deep Learning Process

Gait is an individual biometric behavior which can be detected based on distance has different submissions in social security, forensic detection and crime prevention. Hence, this paper, Advanced Deep Belief Neural Network with Black Widow Optimization (ADBNN-BWO) Algorithm developed to identify the human emotions by walking style images. This proposed methodology working four stages like pre-processing, feature extraction, selection classification. For contrast enhancement median filter used Hu Moments, GLCM, Fast Scale-invariant transform (F-SIFT), addition skeleton features are for extraction. To extract efficiently, extraction algorithm often very essential calculation. After that, performed. Then classification process done utilizing ADBNN-BWO Algorithm. Based method, gait recognition achieved utilized from style. The method validated using open source databases. implemented MATLAB platform their corresponding performances/outputs evaluated. Moreover, statistical measures of also determined compared existing as Artificial (ANN), Mayfly Particle Swarm (MA-PSO), Recurrent Network-PSO (RNN-PSO) Adaptive Neuro Fuzzy Inference System (ANFIS) respectively.