The Viterbi Algorithm and Sign Language Recognition

Abstract

This paper analyzes the Viterbi algorithm and its application to Sign Language Recognition. The Viterbi algorithm is used as a maximum a posteriori approach to solving the decoding problem of Hidden Markov Models (HMM). This paper discusses the attributes of the HMM with an example. The theoretical time complexity of the algorithm is compared to the results of experiments on a Python implementation. The more general field of Gesture Recognition is briefly mentioned as foundation for the type of system necessary to facilitate Sign Language Recognition. Both word and subunit models for American Sign Language are detailed.