HAND GESTURE CONTROLLED DEVICE THROUGH MATLAB

Abstract

We propose a vision based Hand gesture Recognition system that recognizes hand gestures that is useful especially for physically challenged people, and provides recognized character or number as text and corresponding sound. A lot of work has been done towards developing intelligent and natural interfaces between human being and computer systems. Hand Gesture recognition is a fast developing area in the field of Human Computer Interaction. Present day system developers not only aim to develop the fully functional systems, but also aim for systems with more intuitive interfaces, allowing for easier user/system interaction. The gesture recognition is a process in which the gestures or postures of human body parts are identified and are used to control computer and other electronic appliances. The most contributing reason for the emerging gesture recognition is that they can create a simple communication path between human and computer called as HCI (Human Computer Interaction). This thesis is confined to a identification of hand postures to establish a manmachine interaction and to control a simple hardware wirelessly. The hand region in the image is detected and data regarding the detected image is stored in different groups. In this approach, the input which is an image or a frame from a video can be obtained from web camera or any other camera. Data consists of HOG (Histogram of an Oriented Graph) extracted features and different classification techniques have been used to classify the detected image from the trained groups. Skin detection system is more efficient as compare to converting color image into binary image. This is a simple yet efficient approach.