Syntactic methodology of pruning large lexicons in cursive script recognition

Abstract In this paper, we present a holistic technique for pruning of large lexicons for recognition of off-line cursive script words. The technique involves extraction and representation of downward pen-strokes from the off-line cursive word to obtain a descriptor which provides a coarse characterization of word shape. Elastic matching is used to match the image descriptor with “ideal” descriptors corresponding to lexicon entries organized as a trie of stroke classes. On a set of 23,335 real cursive word images the reduction is about 70% with accuracy above 75%.

[1]  Azriel Rosenfeld,et al.  The Interpretation and Reconstruction of Interfering Strokes , 1993 .

[2]  Ellis Horowitz,et al.  Fundamentals of Data Structures , 1984 .

[3]  Giovanni Seni,et al.  An on-line cursive word recognition system , 1994, 1994 Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.

[4]  Venu Govindaraju,et al.  Serial classifier combination for handwritten word recognition , 1995, Proceedings of 3rd International Conference on Document Analysis and Recognition.

[5]  Venu Govindaraju,et al.  Contour-based image preprocessing for holistic handwritten word recognition , 1997, Proceedings of the Fourth International Conference on Document Analysis and Recognition.

[6]  Venu Govindaraju,et al.  Using tem-poral information in o-line word recognition , 1992 .