Based on image force field transformation, a novel algorithm was proposed to track the hand during hand over face occlusion in sign language video.First, the frames with a hand occluding the face and those with only a face were transformed to force field images.Then the force field images were partitioned into sub-images and the histograms of each sub-image were calculated.For each sub-image, the histogram of frame with only a face was subtracted from the frame with a hand occluding the face to get the difference histogram.Finally, for each sub-image the difference histogram was compared to threshold to get the position of the hand.Experimental results showed that the proposed algorithm is capable of real-time tracking of hand.
