A structural method for handprinted character recognition

A method for the recognition of handprinted characters, based on their structural description, is illustrated. Special importance is given to the procedure for decomposing characters into elementary components. The first aim, in fact, is to obtain descriptions as much as possible invariant with respect to the large shape variations existing among handprinted characters. The descriptions, given in terms of relational attributed graphs, are eventually matched against prototypes by using heuristic matching criteria that imply the contextual use of rules for transforming, with measurable costs, similar graphs into one another. Preliminary tests of performance have given stimulating results. Large scale experiments are now running.

[1]  Gabriella Sanniti di Baja,et al.  A Width-Independent Fast Thinning Algorithm , 1985, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[2]  W. A. Perkins,et al.  A Model-Based Vision System for Industrial Parts , 1978, IEEE Transactions on Computers.

[3]  V. K. Govindan,et al.  A pattern adaptive thinning algorithm , 1987, Pattern Recognit..

[4]  Theo Pavlidis,et al.  A vectorizer and feature extractor for document recognition , 1986 .

[5]  Kazuhiko Yamamoto,et al.  Research on Machine Recognition of Handprinted Characters , 1984, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[6]  Luigi P. Cordella,et al.  From Local Maxima to Connected Skeletons , 1981, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[7]  Theodosios Pavlidis,et al.  A Hierarchical Syntactic Shape Analyzer , 1979, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[8]  Keiji Kobayashi,et al.  Recognition of handprinted Kanji characters by the stroke matching method , 1983, Pattern Recognit. Lett..

[9]  King-Sun Fu,et al.  A graph distance measure for image analysis , 1984, IEEE Transactions on Systems, Man, and Cybernetics.

[10]  R. Narasimhan,et al.  A syntax-aided recognition scheme for handprinted english letters , 1971, Pattern Recognit..

[11]  Theodosios Pavlidis,et al.  Structural pattern recognition , 1977 .

[12]  King-Sun Fu,et al.  A distance measure between attributed relational graphs for pattern recognition , 1983, IEEE Transactions on Systems, Man, and Cybernetics.

[13]  Azriel Rosenfeld,et al.  Digital Picture Processing , 1976 .