An Implementation of OCR System Based on Skeleton Matching

This report gives a general review of the development of Optical Character Recognition (OCR), about its key problems and various of the techniques used. An implementation based on skeleton matching is introduced in detail, which is used mainly for printed character recognition and is insensitive to font style and size. This report emphasises on the implementation principles for text sectioning, preclassifier design, thinning algorithm, template database and matching strategy. An experiment is described to observe the system performance. Compared with conventional methods used, this implementation has included some new techniques, such as character dimension dependent broad classification method, AVP value used in fine classification and spelling check based post-processing method, in order to obtain a good performance.

[1]  J. Mantas,et al.  An overview of character recognition methodologies , 1986, Pattern Recognit..

[2]  Terry A. Welch,et al.  A Technique for High-Performance Data Compression , 1984, Computer.

[3]  Ching Y. Suen,et al.  The State of the Art in Online Handwriting Recognition , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Yun Xia,et al.  Skeletonization via the Realization of the Fire Front's Propagation and Extinction in Digital Binary Shapes , 1989, IEEE Trans. Pattern Anal. Mach. Intell..

[5]  Lindsay J. Evett,et al.  Fast dictionary look-up for contextual word recognition , 1990, Pattern Recognit..

[6]  Yung-Sheng Chen,et al.  A comparison of some one-pass parallel thinnings , 1990, Pattern Recognit. Lett..

[7]  R. Mahesh K. Sinha,et al.  On partitioning a dictionary for visual text recognition , 1990, Pattern Recognit..

[8]  Réjean Plamondon,et al.  On-line recognition of handprinted characters: Survey and beta tests , 1990, Pattern Recognit..

[9]  Wen-Hsiang Tsai,et al.  A new fast one-pass thinning algorithm and its parallel hardware implementation , 1990, Pattern Recognit. Lett..

[10]  John Collins.  On-line recognition of handprinted characters , 1984 .

[11]  William Stallings,et al.  Recognition of printed chinese characters by automatic pattern analysis , 1972, Comput. Graph. Image Process..

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

[13]  James L. Peterson,et al.  Computer programs for detecting and correcting spelling errors , 1980, CACM.

[14]  Nobuyasu Itoh,et al.  A spelling correction method and its application to an OCR system , 1990, Pattern Recognit..

[15]  Herbert A. Glucksman.  Multicategory Classification of Patterns Represented by High-Order Vectors of Multilevel Measurements , 1971, IEEE Transactions on Computers.

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

[17]  Carlo Arcelli,et al.  Pattern thinning by contour tracing , 1981 .

[18]  Nikolaos G. Bourbakis.  A parallel-symmetric thinning algorithm , 1989, Pattern Recognit..

[19]  R. Hecht-Nielsen,et al.  Neurocomputing: picking the human brain , 1988, IEEE Spectrum.

[20]  R.M. McElhaney,et al.  Algorithms for graphics and image processing , 1983, Proceedings of the IEEE.

[21]  King-Sun Fu,et al.  A Dynamic Programming Approach to Sequential Pattern Recognition , 1967, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[22]  Mary Elizabeth Stevens.  Introduction to the special issue on Optical Character Recognition (OCR) , 1970, Pattern Recognit..

[23]  Juan Humberto Sossa Azuela.  An improved parallel algorithm for thinning digital patterns , 1989, Pattern Recognit. Lett..