SIGN LANGUAGE RECOGNITION BASED ON HMM/ANN/DP

摘要

In this paper, a system designed for helping the deaf to communicate with oth- ers is presented. Some useful new ideas are proposed in design and implementation. An algorithm based on geometrical analysis for the purpose of extracting invariant fea- Ture to signer position is presented. An ANN-DP combined approach is employed for Segmenting subswords automatically from the data stream of sign signals. To tackle the epenthesis movement problem, a DP-based method has been used to obtain the context- Dependent models.