Efficient Gait Recognition of Individuals by Utilizing Shape Features Using Particle Swarm Optimization

Gait is the manner in which a person walks and has gained much importance in the recent past in surveillance systems. This method uses the concept of extracting the features from the video sequence. which are used to identify the individual. In this work, along with the most effective parts and more informative less effective parts, which are extracted due to the effect of various cofactors, shape features are also considered for recognition. This work utilizes only the most informative movable parts with fixed movement as the shape of the parts tends to change with motion. The performance of this method is compared against gait recognition using PSO without utilizing the shape features. The experimental results shows that the proposed method of PSO utilizing shape features shows better performance metrics when compared to the recognition using PSO without considering the shape features.