The extraction and analysis of human gait characteristics using image sequences are currently an intense area of research. Identifying individuals using biometric methods has recently gained growing interest from computer vision researchers for security purposes at places like airport, banks etc. Gait recognition aims essentially to address this problem by identifying people at a distance based on the way they walk i.e., by tracking a number of feature points or gait signatures. We describe a new model-based feature extraction analysis is presented using Hough transform technique that helps to read the essential parameters used to generate gait signatures that automatically extracts and describes human gait for recognition. In the preprocessing steps, the picture frames taken from video sequences are given as input to Canny edge detection algorithm which helps to detect edges of the image by extracting foreground from background also it reduces the noise using Gaussian filter. The output from edge detection is given as input to the Hough transform. Using the Hough transform image, a clear line based model is designed to extract gait signatures. A major difficulty of the existing gait signature extraction methods are the good tracking the requisite feature points. In the proposed work, we have used five parameters to successfully extract the gait signatures. It is observed that when the camera is placed at 90 and 270 degrees, all the parameters used in the proposed work are clearly visible. The efficiency of the model is tested on a variety of body position and stride parameters recovered in different viewing conditions on a database consisting of 20 subjects walking at both an angled and frontal-parallel view with respect to the camera, both indoors and outdoors and find the method to be highly successful. The test results show good clarity rates, with a high level of confidence and it is suggested that the algorithm reported here could form the basis of a robust system for monitoring of gait.
展开▼
