Japanese Sign Language Recognition System Using Image Processing

抄録

For people who are speech impaired and use Japanese sign language, it is helpful to develop an interactive Japanese sign language interface. Yamaguchi and Yoshihara etc. have proposed and realized a method for it. It uses only spatial motion features of different sign languages and doesn't think about the shape of hands. However, both spatial motion and shape of hands are important in sign language recognition. In this paper, we propose a method which employs skills of image processing to process and analyse simple shape of hands, and combine it with the method mentioned above. In our system, we also use Fuzzy Associative Memory Organizing Unit System(FAMOUS), which has property of robustness, to perform associative inference. Our system is person independent with high recognition rate.