Stream State-tying for Sign Language Recognition

TL;DR

This paper introduces a novel state-tying method for sign language recognition that improves accuracy and efficiency by modeling six synchronized data streams, achieving high recognition rates in Chinese sign language.

Contribution

The paper presents a new state-tying approach for multi-stream sign language recognition, enhancing accuracy and computational efficiency over previous methods.

Findings

Real-time isolated recognition rate of 94.8%

Continuous sign recognition word correct rate of 91.4%

Effective modeling of six synchronized data streams

Abstract

In this paper, a novel approach to sign language recognition based on state tying in each of data streams is presented. In this framework, it is assumed that hand gesture signal is represented in terms of six synchronous data streams, i.e., the left/right hand position, left/right hand orientation and left/right handshape. This approach offers a very accurate representation of the sign space and keeps the number of parameters reasonably small in favor of a fast decoding. Experiments were carried out for 5177 Chinese signs. The real time isolated recognition rate is 94.8%. For continuous sign recognition, the word correct rate is 91.4%. Keywords: Sign language recognition; Automatic sign language translation; Hand gesture recognition; Hidden Markov models; State-tying; Multimodal user interface; Virtual reality; Man-machine systems.