HAND POSTURE RECOGNITION USING SKIN, TEXTURE AND SALIENCY MAP

Abstract

Hand Gesture Recognition (HGR) systems are paying more attention in the present scenario due to a wide range of application in real life. These systems are based on the processing of an incoming digital image. In this thesis, the first task is to separate the hand from rest of the image. This can be achieved in several ways and depends on whether the image includes only a hand against a background or the entire person. All the techniques proposed have some limitations. Their performance is affected by the illumination or lighting conditions and complex backgrounds of the hand images. To overcome the above mentioned limitations, a new technique is proposed for Hand Posture Recognition using Skin, Texture and Saliency map which involve classification of hand gesture. It efficiently makes the use of different color spaces, skin detection, saliency map and texture of an image. To recognize the hand gesture classes the features are extracted using the proposed methodology. These features are used for the classification purpose. Finally the application of multi-class SVM classifier is employed to recognize the hand gesture class. The experiments show that the proposed model has stable performance for a wide range of images.