Segmentation-free printed character recognition by relaxed nearest neighbor learning of windowed operator

Segmentation is considered by many researchers as the key technology for a reliable optical character recognition (OCR) system. To accomplish sound segmentation, many alternative techniques have been recently proposed. This paper presents a new technique to recognize characters without explicit segmentation. It is based on the automatic construction of a windowed operator by relaxed nearest neighbor learning. It has been implemented, tested and yielded excellent recognition accuracy and computational performance.

[1]  Jesfis Peral,et al.  Heuristics -- intelligent search strategies for computer problem solving , 1984 .

[2]  Fabrizio Russo.  Nonlinear filtering of noisy images using neuro-fuzzy operators , 1997, Proceedings of International Conference on Image Processing.

[3]  H. Y. Kim,et al.  Technique for constructing grey-scale morphological operators using fuzzy expert system , 1997 .

[4]  Julian R. Ullmann,et al.  Experiments with the n-tuple Method of Pattern Recognition , 1969, IEEE Transactions on Computers.

[5]  Eric Lecolinet,et al.  A Survey of Methods and Strategies in Character Segmentation , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Mindy Bokser,et al.  Omnidocument technologies , 1992, Proc. IEEE.

[7]  Morton Nadler.  Document segmentation and coding techniques , 1984, Comput. Vis. Graph. Image Process..

[8]  Richard O. Duda,et al.  Pattern classification and scene analysis , 1974, A Wiley-Interscience publication.

[9]  George Nagy,et al.  N-Tuple Features for OCR Revisited , 1996, IEEE Trans. Pattern Anal. Mach. Intell..

[10]  Stephen Marshall,et al.  The use of genetic algorithms in morphological filter design , 1996, Signal Process. Image Commun..

[11]  Jon Louis Bentley,et al.  An Algorithm for Finding Best Matches in Logarithmic Expected Time , 1977, TOMS.

[12]  Yasuaki Nakano,et al.  Segmentation methods for character recognition: from segmentation to document structure analysis , 1992, Proc. IEEE.

[13]  H. Y. Kim.  Quick construction of efficient morphological operators by computational learning , 1997 .

[14]  Jon Louis Bentley,et al.  Multidimensional binary search trees used for associative searching , 1975, CACM.

[15]  Michael Ian Shamos,et al.  Computational geometry: an introduction , 1985 .

[16]  Edward R. Dougherty,et al.  Automatic programming of binary morphological machines by design of statistically optimal operators in the context of computational learning theory , 1997, J. Electronic Imaging.

[17]  Dave Elliman,et al.  A review of segmentation and contextual analysis techniques for text recognition , 1990, Pattern Recognit..

[18]  M Schmitt,et al.  Mathematical morphology and artificial intelligence: an automatic programming system , 1989 .

[19]  Hae Yong Kim,et al.  Automatic design of nonlinear filters by nearest neighbor learning , 1998, Proceedings 1998 International Conference on Image Processing. ICIP98 (Cat. No.98CB36269).

[20]  Ching Y. Suen,et al.  Historical review of OCR research and development , 1992, Proc. IEEE.