Augmenting the Discrimination Power of HMM by NN for On-Line Cursive Script Recognition

For on-line handwriting recognition, a hybrid approach that combines the discrimination power of neural networks with the temporal structure of hidden Markov models is presented. Initially, all plausible letter components of an input pattern are detected by using a letter spotting technique based on hidden Markov models. A word hypothesis lattice is generated as a result of the letter spotting. All letter hypotheses in the lattice are evaluated by a neural network character recognizer in order to reinforce letter discrimination power. Then, as a new technique, an island-driven lattice search algorithm is performed to find the optimal path on the word hypothesis lattice which corresponds to the most probable word among the dictionary words. The results of this experiment suggest that the proposed framework works effectively in recognizing English cursive words. In a word recognition test, on average 88.5% word accuracy was obtained.

[1]  Ching Y. Suen,et al.  Extraction of key letters for cursive script recognition , 1993, Pattern Recognit. Lett..

[2]  George Zavaliagkos,et al.  A Hybrid Continuous Speech Recognition System Using Segmental Neural Nets with Hidden Markov Models , 1993, Int. J. Pattern Recognit. Artif. Intell..

[3]  Jin Hyung Kim,et al.  Recognition of Unconstrained Handwritten English Words with Character and Ligature Modeling , 1995, Int. J. Pattern Recognit. Artif. Intell..

[4]  Ching Y. Suen,et al.  Building a perception based model for reading cursive script , 1995, Proceedings of 3rd International Conference on Document Analysis and Recognition.

[5]  Giorgio Satta,et al.  Computation of Probabilities for an Island-Driven Parser , 1991, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Hermann Ney.  A Comparative Study of Two Search Strategies for Connected Word Recognition: Dynamic Programming and Heuristic Search , 1992, IEEE Trans. Pattern Anal. Mach. Intell..

[7]  E. Lecolinet,et al.  Strategies in character segmentation: a survey , 1995, Proceedings of 3rd International Conference on Document Analysis and Recognition.

[8]  Nasser Sherkat,et al.  Recognizer characterisation for combining handwriting recognition results at word level , 1995, Proceedings of 3rd International Conference on Document Analysis and Recognition.

[9]  Isabelle Guyon,et al.  Recognition-based segmentation of on-line run-on handprinted words: Input vs. output segmentation , 1994, Pattern Recognit..

[10]  Lambertus Schomaker,et al.  A Handwriting Recognition System based on the Properties and Architectures of the Human Motor System , 1990 .

[11]  Ching Y. Suen,et al.  Combination of multiple classifiers with measurement values , 1993, Proceedings of 2nd International Conference on Document Analysis and Recognition (ICDAR '93).

[12]  Dan S. Bloomberg,et al.  Word spotting in scanned images using hidden Markov models , 1993, 1993 IEEE International Conference on Acoustics, Speech, and Signal Processing.

[13]  Michel Gilloux,et al.  A hybrid radial basis function network/hidden Markov model handwritten word recognition system , 1995, Proceedings of 3rd International Conference on Document Analysis and Recognition.

[14]  Jian Zhou,et al.  Off-Line Handwritten Word Recognition Using a Hidden Markov Model Type Stochastic Network , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  Beatrice Santorini,et al.  Building a Large Annotated Corpus of English: The Penn Treebank , 1993, CL.

[16]  Hervé Bourlard,et al.  Hybrid Neural Network/Hidden Markov Model Systems for Continuous Speech Recognition , 1993, Int. J. Pattern Recognit. Artif. Intell..