Overview and synthesis of on-line cursive handwriting recognition techniques.
I. Guyon, M. Schenkel, and J. Denker.
In H. Bunke and Wang P.S.P., editors, Handbook on Optical Character Recognition and Document Image Analysis. World Scientific Publishing Company, in press.
In this chapter, we analyze several on-line cursive handwriting recognition systems. We find that virtually all such systems involve (a) a preprocessor, (b) a trainable classifier, and (c) a language modeling post-processor. Such architectures are described within the framework of Weighted Finite State Transductions, previously used in speech recognition by Pereira . We describe in some detail a recognition system built in our laboratory. It is a writer independent system which can handle a variety of writing styles including cursive script and handprint. The input to the system encodes the pen trajectory as a time-ordered sequence of feature vectors. A Time Delay Neural Network is used to estimate a posteriori probabilities for characters in a word. A Hidden Markov Model segments the word in a way which optimizes the global word score, taking a lexicon into account. The last part of the chapter is devoted to bibliographical notes.
Keywords: cursive, handwriting, recognition, on-line, character recognition, hidden Markov models, finite state automata, finite state transductions, neural networks, WFSA, WFST, HMM, graph, Viterbi, TDNN, grammar, UNIPEN, segmentation, product graph, INSEG, OUTSEG, script, handprint.
[ next paper ]