ABSTRACT

Sign language is the most natural way of expression for the deaf community. The urge to support the integration of deaf people into the hearing society made the automatic sign language recognition, an area of interest for the researchers. Indian Sign Language (ISL) is a visual-spatial language which provides linguistic information using hands, arms, facial expressions, and head/body postures. In this paper we propose a novel vision-based recognition of Indian Sign Language Alphabets and Numerals using B-Spline Approximation. Gestures of ISL alphabets are complex since it involves the gestures of both the hands together. Our algorithm approximates the boundary extracted from the Region of Interest, to a B-Spline curve by taking the Maximum Curvature Points (MCPs) as the Control points. Then the B-Spline curve is subjected to iterations for smoothening resulting in the extraction of Key Maximum Curvature points (KMCPs), which are the key contributors of the gesture shape. Hence a translation & scale invariant feature vector is obtained from the spatial locations of the KMCPs in the 8 Octant Regions of the 2D Space which is given for classification.