Recognition of a hand shape for application in a human interface

Abstract

This paper proposes a human interface where a novel input method is used to substitute conventional input devices. It overcomes the deficiencies of physical devices, as it is based on image processing techniques. A. Tomita, T. Ebina, and R. Ishii proposed an recognition algorithm (1995, 1998). Two kinds of hand shapes and rotation of hand are interpreted by their proposed algorithm. We modify their algorithm and prove that eight types of hand shapes and rotation of a hand can be interpreted by the modified algorithm. From experimental results, the processing time to interpret these types and rotation is 31.4 msec.