Real-Time Gesture Recognition System using CNN

Abstract

Hand gesture is the initial method for communication that was used by cave men. The verbal communication was developed by the more developed civilization. Hand gesture has been the oldest form of non-verbal communication. In current time, hand gesture is not only a way of communication between people who may or may not be physically challenged but also between humans and machines in diversified fields such as aviation, surveys, military simulation, medical training etc. It is the best way of interaction between man and machine as no peripheral devices are required and a wide range of gesture can be used for communication with high accuracy. For such human and machine interaction a real-time gesture recognition system is proposed. Detection of motion and skin is used for capturing region-of-interest. The region of interest is further processed by convolutional neural network in order to get a proper result.