A Novel Recognition Technique for Chinese Sign Language

摘要

Sign language is the language used by the deaf, which is a comparatively steadier expressive system composed of signs corresponding to postures and motions assisted by facial expression. The objective of sign language recognition research is to "see" the language of deaf. The integration of sign language recognition and sign language synthesis jointly comprise a "human-computer sign language interpreter", which facilitates the interaction between deaf and their surroundings. According to the characteristics of Chinese sign language(CSL), a novel clustering algorithm, the greedy clustering algorithm along the rime axis(GLATA) is proposed in this paper and training and recognizing algorithm basing on the algorithm are used respectively to train the template corresponding to each word and can recognize 1067 words randomly selected from CSL with the accuracy of 93.1% .