DTW/ISODATA algorithm and multilayer architecture in sign language recognition with large vocabulary

Up to now, the major problem for large vocabulary sign language recognition lies in the huge search space due to a variety of recognition classes. Analytical methods such as Dynamic Time Wrapping (DTW) or Euclidian distance have been used for isolated word recognition, but the performance is not satisfactory enough because it is easily interfered by noise. Statistical methods, especially hidden Markov Models are commonly used for both continuous sign language and isolated words while the processing time becomes increasingly unacceptable with the expansion of vocabulary. A multilayer architecture of sign language recognition is proposed in this paper for the purpose of speeding up the search process. The gesture sequence to be recognized is first located at a set of words that are easy to be confused (confusion set) through a global cursory search with little computation cost and then the gesture is recognized through a local search. The generation of confusion set is realized by DTW/ISODATA algorithm. Experiment results indicate that it is an effective algorithm for sign language recognition with large vocabulary.