Fourier Descriptor Based Static Sign Language Recognition

Yong HU, Wei-yan SHEN, Wei ZHENG

Sign language recognition is an important and challenging research area in the field of human-computer interaction. The work presented in this paper aims at developing a robust system for automatic translation of static gestures of alphabets. The proposed methods used the Support Vector Machine classifier and features extracted from a novel signature, Inner-Centroid Distance. In the experiments, a comparison between the proposed methods and Zernike moments is performed by using a public sign database. Experiments show that the proposed approach is effective and simple to implement.