ADAPTIVE SKIN COLOUR MODELING FOR DETECTION OF VARYING SKIN COLOUR

摘要

A real time skin colour segmentation is prime consern in posture / hand gesture based sign language recognition. The developed method separate posture / hand gesture without any marker on any background by taking into account forground skin colour. The invention is segmenting dynamic posture / hand gesture done in front of camera or from images or video database. The values of YCgCr are determined in real time and in run time adaptive YCgCr bound values are used to segment foreground skin colour from skin / non-skin colour background. The algorithm is deployed on embedded image processing hardware platform and any varying skin colour / tone it can adapot to segment face/ hand gestures.