Design and Implementation of Static Hand Gesture Recognition System for Device Control

Abstract

In order to create a system to recognize specific human gestures that can be used to convey information this paper presents a k-curvature algorithm. This paper aims at designing a static hand gesture recognition (HGR) system captured from a webcam in real-time. The system consists of different stages: image capturing, feature extraction, and hand gesture recognition. The input image of hand gestures is captured by digital camera in a fixed frame rate. The captured image is processed which helps for feature extraction. Features required for the recognition system are extracted from the image and a k-curvature algorithm is applied to recognize the hand gestures. The recognized gestures can be used to control devices.