Subunit modeling for Japanese sign language recognition based on stochastic model

点击翻译按钮获取中文摘要

In this study, an important issue for modeling sign is that how to determine the constituent element of sign (i.e., subunit) like "phoneme" in spoken language. We focused on special feature of sign language that Japanese sign language is composed of three types of phonological elements which is hand local information, position, and movement. In this paper, we propose an efficiently method of generating subunit using multi-stream HMM which is correspond to phonological elements. 100 and 307 isolated sign recognition experiment has confirmed the effectiveness of our proposed method.