Curvilinear tracing approach for recognition of Kannada sign language

Abstract

Sign languages are used as the main mode of communication for vocally disabled people; however, the diversity in sign symbol representation limits its usage to a particular region. There is a huge diversity in sign symbol representation from one country to another, one state to another. In India there are different sign languages observed for each state region. It is hence very difficult for one region individual to communicate to another using a significant symbol. This paper proposes a curvilinear tracing approach for shape representation and recognition of Kannada sign language to generate corresponding characters in Kannada language. To develop this approach, a dataset is created with all Swaragalu, Vyanjanagalu, and numbers in Kannada language. The dataset is formed by defining a vocabulary for different sign symbols used in common interfacing. In the representation of sign language for recognition, edge features of hand regions are considered to be an optimal feature representation of sign language.

Keyframe Extraction Algorithm for Continuous Sign-Language Videos Using Angular Displacement and Sequence Check Metrics

“…Te method is, therefore, inefective for CSL videos. Te research [22] identifes signifcant frames and treats each gesture as a separate, isolated gesture using a gradient-based key frame extraction technique. Te direction of motion continuity and minute motions are left unresolved.…”