Abstract
This paper deals with a continuous recognition method for finger signs used to express some numerals in Japanese sign language by image processing technology. There have been some reports about recognition methods for finger letters; however, these were concerned with the finger letters which could be recognized from only the hand shape. Some finger letters are expressed by both hand shape and motion; therefore, it is necessary to use sequential hand images to recognize such finger letters. We propose a new continuous recognition method for sequential hand images and their contour curves. First, we define some properties of the hand image with its contour curve. Next, we determine a judgement rule for discrimination of the hand shapes based on the above properties. Finally, we describe a recognition rule to apply the judgement rule to some sequential hand images, and show some examples to demonstrate the feasibility of the continuous recognition method.
