Hand gesture recognition approach for human computer interaction

Abstract

Gesture recognition is an interesting research area in the field of computer vision. Gesture recognition allow human user to interact non-verbally using different body parts like hand, face, finger, palm etc. The important steps involved in Hand Gesture Recognition are segmentation, feature extraction and hand gesture recognition. There are many factors which affect the result of feature extraction and gesture recognition. This report is a part of work in the field of Dynamic Hand Gesture Recognition. It highlights the important challenges faced in locating hand object in different environment and proposes a system to locate hand using Contour detection and Convex hull method. The proposed work may improve the accuracy in detection of object and recognition of gesture.