Connected Component Algorithm for Gestures Recognition

Abstract

This paper presents head and hand gestures recognition system for Human Computer Interaction (HCI). Head and Hand gestures are an important modality for human computer interaction. Vision based recognition system can give computers the capability of understanding and responding to the hand and head gestures. The aim of this paper is the proposal of real time vision system for its application within a multimedia interaction environment. This recognition system consists of four modules, i.e. capturing the image, image extraction, pattern matching and command determination. If hand and head gestures are shown in front of the camera, hardware will perform respective action. Gestures are matched with the stored database of gestures using pattern matching. Corresponding to matched gesture, the hardware is moved in left, right, forward and backward directions. An algorithm for optimizing connected component in gesture recognition is proposed, which makes use of segmentation in two images. Connected component algorithm scans an image and group its pixels into component based on pixel connectivity i.e. all pixels in connected component share similar pixel intensity values and are in some way connected with each other. Once all groups have been determined, each pixel is labeled with a color according to component it was assigned to.

Clustering of Human Gestures Images Using 3D Cellular Automata and N-Gram Pixels with a Visualisation aspect

“…The authors in (Hasan, 2012) said that the robots should communicate with human, using the Fuzzy C-Means (FCM) for recognizing the hand gestures. Also in (Chhabria, 2011), a system for recognition of hand gestures was proposed. We can see, the idea proposed in (Lyons, 1999), with a method for the classification of the images facial.…”