Stream State-tying for Sign Language Recognition
This work addresses sign language recognition for human-computer interaction, presenting an incremental improvement in accuracy and efficiency.
The paper tackles sign language recognition by proposing a state-tying approach across six data streams for hand gestures, achieving a real-time isolated recognition rate of 94.8% and a continuous word correct rate of 91.4% on 5177 Chinese signs.
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.