Real Time Based Bare Hand Gesture Recognition

Gestures are a powerful means of communication among humans. Gesture recognition is the process of recognizing and interpreting a stream continuous sequential gesture from the given set of input data. Primary Concern in hand gesture recognition is that it could be possible for users to communicate with computerized equipment without need for external control devices. Another advantage is that the user not only can communicate from a distance, but need have no physical contact with the computer. According to survey almost 40% of all gestures are done with one hand and multiple hands at 20% and the rest are distributed between the other body parts. In this method bare hand gestures are recognizing using dynamic vision sensor (DVS) camera. DVS is different from conventional cameras. DVS cameras only respond to pixels with temporal luminance differences, which can greatly reduce the computational cost of comparing consecutive frames to track moving object. This method attempts to classify three different hand gestures made by a user which is called as Rock,Paper,Scissors. This is novel method detect the point where the user delivers a throw, to extract hand regions and to extract useful features for classification.