Real-Time Hand Gesture Detection Using Convex Hull and Contour Edge Detection

Abstract

Hand gesture is a way of communicating through sign languages and presently it has been a hot research topic in the field of Artificial intelligence and Data Science. Contemporary methods for detecting the hand gesture uses optical/mechanical sensors, actuator & accelerometer attached with the glove. This paper proposes a novel method for gesture identification for various hand gestures without using additional equipment (such as sensors or gloves). The proposed method captures the image of the hand gesture then segments it. The real-time hand gesture is tracked down by the convex hull. Convolutional Neural Network is used to detect the area of hand gestures in real-time. The results of the experimental evaluation of the proposed method gave 80% accuracy.