Classifying character shapes

Optical Character Recognition (OCR) is one of the oldest applicative problems of interest in Pattern Recognition. For its solution, a large number of statistical, structural and mixed methods have been proposed (reviews can be found in [1–3]). Although many OCR systems, suitable in a variety of applications, are today commercially available, nevertheless, the general problem of recognizing characters, no matter for the way they are produced and for the context in which they are embedded, still remains unsolved.

[1]  V. K. Govindan,et al.  Character recognition - A review , 1990, Pattern Recognit..

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

[3]  George Nagy,et al.  29 Optical character recognition - Theory and practice , 1982, Classification, Pattern Recognition and Reduction of Dimensionality.

[4]  K. M. Kulkarni,et al.  A high accuracy algorithm for recognition of handwritten numerals , 1988, Pattern Recognit..

[5]  Theodosios Pavlidis,et al.  On the Recognition of Printed Characters of Any Font and Size , 1987, IEEE Transactions on Pattern Analysis and Machine Intelligence.

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

[7]  Robert M. Haralick,et al.  Structural Descriptions and Inexact Matching , 1981, IEEE Transactions on Pattern Analysis and Machine Intelligence.