Simulation of Real Time Hand Gesture recognition for Physically Impaired

Abstract: We propose a vision based Hand gesture Recognition system that recognizes hand gesture in midair, especially for physically challenged people, and provides recognized character or number as text and corresponding sound. This system also detects face of the gesture requesting person, so as to satisfy the needs of the person. This system provides a convenient and easy to use human computer interaction (HCI) system for especially visually or physically challenged people. The system does not demand on sensors or markers attached to the users and allow unrestricted character and symbol input from any position. It is the result of combining hand gesture recognition based on Centroids with real time 3D hand tracking and face recognition using PCA. We evaluated the system for both quantitative and qualitative aspects. The system achieves recognition rates of 86:15% for character and 97:54% for symbol recognition. Limitations are due to slow and lower resolution cameras or physical strain of training dataset. Overall, the proposed hand gesture recognition system provides an easy to use and accurate text input modality without placing restrictions on the users.

Category: User Interfaces: Image Processing HCI,

Keywords: PCA, Hand gesture, Real time motion tracking, face detection.