No abstract

In this paper, the task of recognizing signs made by hearing impaired people at sentence level has been addressed. A novel method of detecting sign boundaries in a video of continuous signs has been proposed and extraction of spatial features to capture hand movements of a signer through fuzzy membership functions has been proposed. Frames of a given video of a sign are preprocessed to extract face and hand components of a signer. The centroids of the extracted components are exploited to extract spatial features. The concept of interval valued type symbolic data has been explored to capture variations in the same sign made by the different signers at different instances of time. A suitable symbolic similarity measure is studied to establish matching between reference and test signs and a simple nearest neighbor classifier is used to recognize an unknown sign as one among the known signs by specifying a desired level of threshold. An extensive experimentation is conducted on a significantly large corpus of Indian regional signs created by us during the course of our research work in order to evaluate the performance of the proposed system.

No abstract

No abstract

No abstract