Recognition of Equations Using a Two-Dimensional Stochastic Context-Free Grammar

We propose using two-dimensional stochastic context-free grammars for image recognition, in a manner analogous to using hidden Markov models for speech recognition. The value of the approach is demonstrated in a system that recognizes printed, noisy equations. The system uses a two-dimensional probabilistic version of the Cocke-Younger-Kasami parsing algorithm to find the most likely parse of the observed image, and then traverses the corresponding parse tree in accordance with translation formats associated with each production rule, to produce eqn I troff commands for the imaged equation. In addition, it uses two-dimensional versions of the Inside/Outside and Baum re-estimation algorithms for learning the parameters of the grammar from a training set of examples. Parsing the image of a simple noisy equation currently takes about one second of cpu time on an Alliant FX/80.

[1]  L. R. Rabiner,et al.  An introduction to the application of the theory of probabilistic functions of a Markov process to automatic speech recognition , 1983, The Bell System Technical Journal.

[2]  Frederick Jelinek,et al.  Markov Source Modeling of Text Generation , 1985 .

[3]  Jr. G. Forney,et al.  The viterbi algorithm , 1973 .

[4]  James K. Baker,et al.  Stochastic modeling as a means of automatic speech recognition. , 1975 .

[5]  L. Rabiner,et al.  An introduction to hidden Markov models , 1986, IEEE ASSP Magazine.

[6]  L. Baum,et al.  A Maximization Technique Occurring in the Statistical Analysis of Probabilistic Functions of Markov Chains , 1970 .

[7]  S.E. Levinson,et al.  Structural methods in automatic speech recognition , 1985, Proceedings of the IEEE.

[8]  J. Baker,et al.  The DRAGON system--An overview , 1975 .

[9]  F. Jelinek,et al.  Continuous speech recognition by statistical methods , 1976, Proceedings of the IEEE.

[10]  R. H. Anderson,et al.  Two-Dimensional Mathematical Notation , 1977 .

[11]  Noam Chomsky,et al.  On Certain Formal Properties of Grammars , 1959, Inf. Control..

[12]  Brian W. Kernighan,et al.  A system for typesetting mathematics , 1975, Commun. ACM.

[13]  J. Baker.  Trainable grammars for speech recognition , 1979 .

[14]  Lalit R. Bahl,et al.  A Maximum Likelihood Approach to Continuous Speech Recognition , 1983, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[15]  L. Baum,et al.  An inequality with applications to statistical estimation for probabilistic functions of Markov processes and to a model for ecology , 1967 .

[16]  Lorinda L. Cherry,et al.  Typesetting mathematics—user's guide , 1990 .

[17]  L. Baum,et al.  Statistical Inference for Probabilistic Functions of Finite State Markov Chains , 1966 .

[18]  King-Sun Fu,et al.  Syntactic Pattern Recognition And Applications , 1968 .

[19]  D. Rubin,et al.  Maximum likelihood from incomplete data via the EM - algorithm plus discussions on the paper , 1977 .

[20]  Michael A. Harrison,et al.  Introduction to formal language theory , 1978 .

[21]  W. W. Stallings,et al.  Chinese Character Recognition , 1977 .

[22]  Jeffrey D. Ullman,et al.  Introduction to Automata Theory, Languages and Computation , 1979 .

[23]  L. R. Rabiner,et al.  On the application of vector quantization and hidden Markov models to speaker-independent, isolated word recognition , 1983, The Bell System Technical Journal.