“Human gait recognition by CPNN”

This paper proposed a new method for recognizing human by their gait using CPNN. In the modified CPN model, there was no need of training parameters because it is not an iterative method like back propagation architecture which took a long time for learning. The model based approach is chosen so that the effect of exterior factors like clothing, shoes, briefcase and environmental context is minimized. The approach is to first extract the gate features from the image sequences for constructing a locomotion human model. We employed here a Model based technique by combining 2D and 3D feature by plotting different circle into gait portion and get a sequential set of 2D stick figure. A 3D model is used for gait sequences to get arbitrary view angles. Artificial neural networks which is one of the widely used automated techniques having high accuracy, most of the neural networks are computationally heavy due to their iterative nature. Hence, there is a significant requirement for a neural classifier which is computationally efficient and highly accurate. To this effect, Counter Propagation Neural Network (CPN) is employed in this work with 2D and 3D, which proves to be faster than the conventional BP.