Improved gait recognition through gait energy image partitioning

Recently, human gait pattern has turned into an essential biometric feature to recognize an individual remotely. Gait as a feature becomes challenging owing to variation in appearance under different covariate conditions (eg, shoe, surface, haul, viewpoint and attire). The covariates may alter few fragment of gait while other fragment stay unaltered, leading to lower the probability of correct identification. To overcome such variation, an improved gait recognition strategy is proposed in this article by gait energy image partitioning and selection processing. Our method involves pre-processing of raw video for silhouette extraction, gait cycle detection, segmentation into different regions, and histogram of gradients feature extraction from selected segments. In this way, the specific features across complete gait cycles are extracted precisely. Finally, recognition is done by using K-NN. The proposed strategy has been assessed using the CASIA B gait database. Our outcomes shows a particular proposed strategy accomplishes high recognition rate and outperforms the advanced gait recognition mechanism.