Accurate and fast hand-forearm segmentation algorithm based on silhouette

Segmentation of the hand from an image is a necessary step for many applications e.g. hand tracking, gesture recognition. One of the major problems is the hand-forearm segmentation. We propose mathematic model based on geometrical features of silhouette shape to address this problem. Then an accurate and effective approximation algorithm is proposed to obtain the solution of the model. Finally a complete hand segmentation algorithm is realized by using the Kinect sensor. The experiment result proves that our algorithm is accurate and fast.