Fusion of Complementary Online and Offline Strategies for Recognition of Handwritten Kannada Characters
作者： Angarai Ganesan Ramakrishnan , Rakesh Rampalli
DOI:
关键词:
摘要: This work describes an online handwritten character recognition system working in combination with offline system. The input data is also converted into image, and parallely recognized by both strategies. Features are proposed for a disambiguation step employed the samples which confidence level of classifier low. outputs then combined probabilistically resulting out-performing individual systems. Experiments performed Kannada, South Indian Language, over database 295 classes. accuracy recognizer improves 11% when used.
参考文章(5)
A. Vinciarelli, M. Perone, Combining online and offline handwriting recognition international conference on document analysis and recognition. pp. 844- 848 ,(2003) , 10.1109/ICDAR.2003.1227781
M. Mahadeva Prasad, M. Sukumar, A. G. Ramakrishnan, Divide and conquer technique in online handwritten Kannada character recognition Proceedings of the International Workshop on Multilingual OCR - MOCR '09. pp. 11- ,(2009) , 10.1145/1577802.1577815
Il-Seok Oh, Ching Y. Suen, Distance features for neural network-based recognition of handwritten characters International Journal on Document Analysis and Recognition. ,vol. 1, pp. 73- 88 ,(1998) , 10.1007/S100320050008
S. Uchida, H. Sakoe, A handwritten character recognition method based on unconstrained elastic matching and eigen-deformations international conference on frontiers in handwriting recognition. pp. 72- 77 ,(2002) , 10.1109/IWFHR.2002.1030887
Rituraj Kunwar, Shashikiran K., A.G. Ramakrishnan, Online Handwritten Kannada Word Recognizer with Unrestricted Vocabulary international conference on frontiers in handwriting recognition. pp. 611- 616 ,(2010) , 10.1109/ICFHR.2010.100