Supervised Template Estimation for Document Image Decoding

An approach to supervised training of character templates from page images and unaligned transcriptions is proposed. The template training problem is formulated as one of constrained maximum likelihood parameter estimation within the document image decoding framework. This leads to a three-phase iterative training algorithm consisting of transcription alignment, aligned template estimation (ATE), and channel estimation steps. The maximum likelihood ATE problem is shown to be NP-complete and, thus, an approximate solution approach is developed. An evaluation of the training procedure in a document-specific decoding task, using the University of Washington UW-II database of scanned technical journal articles, is described.

[1]  Philip A. Chou,et al.  Document Image Decoding Using Markov Source Models , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[2]  Oscar E. Agazzi,et al.  Keyword Spotting in Poorly Printed Documents using Pseudo 2-D Hidden Markov Models , 1994, IEEE Trans. Pattern Anal. Mach. Intell..

[3]  Francine Chen,et al.  Spotting phrases in lines of imaged text , 1995, Electronic Imaging.

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

[5]  M. R. Rao,et al.  Combinatorial Optimization , 1992, NATO ASI Series.

[6]  Biing-Hwang Juang,et al.  Fundamentals of speech recognition , 1993, Prentice Hall signal processing series.

[7]  William J. Cook,et al.  Combinatorial optimization , 1997 .

[8]  Gary E. Kopec,et al.  Document Image Decoding by Heuristic Search , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[9]  Philip A. Chou,et al.  Automatic generation of custom document image decoders , 1993, Proceedings of 2nd International Conference on Document Analysis and Recognition (ICDAR '93).

[10]  Gary E. Kopec Document image decoding in the UC Berkeley Digital Library , 1996, Electronic Imaging.

[11]  Donald Ervin Knuth Digital typography , 1999, CSLI lecture notes series.

[12]  Jesse F Hull Recognition of mathematics using a two-dimensional trainable context-free grammar , 1996 .

[13]  Gary E. Kopec,et al.  Document image decoding in the Berkeley Digital Library , 1996, Proceedings of 3rd IEEE International Conference on Image Processing.

[14]  Gary E. Kopec,et al.  Document-specific character template estimation , 1996, Electronic imaging.

[15]  守屋 悦朗,et al.  J.E.Hopcroft, J.D. Ullman 著, "Introduction to Automata Theory, Languages, and Computation", Addison-Wesley, A5変形版, X+418, \6,670, 1979 , 1980 .

[16]  Postscript language reference manual, Second Edition , 1991 .

[17]  George Nagy,et al.  Self-correcting 100-font classifier , 1994, Electronic Imaging.

[18]  Gary E. Kopec,et al.  Multilevel character templates for document image decoding , 1997, Electronic Imaging.

[19]  Gary E. Kopec,et al.  Separable source models for document image decoding , 1995, Electronic Imaging.