Segmentation of touching and fused Devanagari characters
作者： Veena Bansal , R.M.K. Sinha
DOI: 10.1016/S0031-3203(01)00081-4
关键词:
摘要: Devanagari script is a two dimensional composition of symbols. It highly cumbersome to treat each composite character as separate atomic symbol because such combinations are very large in number. This paper presents pass algorithm for the segmentation and decomposition characters/symbols into their constituent The proposed extensively uses structural properties script. In first pass, words segmented easily separable characters/composite characters. Statistical information about height width separated box used hypothesize whether composite. second hypothesized characters further segmented. A recognition rate 85 percent has been achieved on conjuncts. designed segment pair touching
elsevier.com
sci-hub.se 参考文章(13)
Structured Document Image Analysis Springer-Verlag New York, Inc.. ,(1992) , 10.1007/978-3-642-77281-8
R.M.K. Sinha, Rule based contextual post-processing for Devanagari text recognition Pattern Recognition. ,vol. 20, pp. 475- 485 ,(1987) , 10.1016/0031-3203(87)90075-6
Bidyut Baran Chaudhuri, U Pal, None, A complete printed Bangla OCR system Pattern Recognition. ,vol. 31, pp. 531- 549 ,(1998) , 10.1016/S0031-3203(97)00078-2
V. Bansal, R.M.K. Sinha, Partitioning and searching dictionary for correction of optically read Devanagari character strings international conference on document analysis and recognition. pp. 653- 656 ,(1999) , 10.1109/ICDAR.1999.791872
R.G. Casey, E. Lecolinet, A survey of methods and strategies in character segmentation IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 18, pp. 690- 706 ,(1996) , 10.1109/34.506792
Su Liang, M. Shridhar, M. Ahmadi, Segmentation of touching characters in printed document recognition Pattern Recognition. ,vol. 27, pp. 825- 840 ,(1994) , 10.1016/0031-3203(94)90167-8
R.M.K. Sinha, Birendra Prasada, Visual text recognition through contextual processing Pattern Recognition. ,vol. 21, pp. 463- 479 ,(1988) , 10.1016/0031-3203(88)90006-4
BB Chaudhuri, U Pal, None, Skew angle detection of digitized Indian script documents IEEE Transactions on Pattern Analysis and Machine Intelligence. ,vol. 19, pp. 182- 186 ,(1997) , 10.1109/34.574803
BB Chaudhuri, Umapada Pal, An OCR system to read two Indian language scripts: Bangla and Devnagari (Hindi) international conference on document analysis and recognition. ,vol. 2, pp. 1011- 1015 ,(1997) , 10.1109/ICDAR.1997.620662
R.M.K. Sinha, V. Bansal, On Devanagari document processing systems man and cybernetics. ,vol. 2, pp. 1621- 1626 ,(1995) , 10.1109/ICSMC.1995.538004