Resolving Ambiguities in Confused Online Tamil Characters with Post Processing Algorithms
This paper addresses the problem of resolving ambiguities in frequently confused online Tamil character pairs by employing script specific algorithms as a post classification step. Robust structural cues and temporal information of the preprocessed character are extensively utilized in the design of these algorithms. The methods are quite robust in automatically extracting the discriminative sub-strokes of confused characters for further analysis. Experimental validation on the IWFHR Database indicates error rates of less than 3 % for the confused characters. Thus, these post processing steps have a good potential to improve the performance of online Tamil handwritten character recognition.
KeywordsConfusion Pairs Sub stroke Extraction and analysis Fourier Descriptors Online handwritten character recognition
- 1.Joshi, N., Sita, G., Ramakrishnan, A.G., Madhavanath, S.: Comparison of Elastic Matching Algorithms for Online Tamil Handwritten Character Recognition. In: Proc. Intl. Workshop Frontiers Handwriting Recog., pp. 444–449 (2004)Google Scholar
- 2.Deepu, V., Madhavanath, S., Ramakrishnan., A.G.: Principal Component Analysis for Online Handwritten Character Recognition. In: Proc. Intl. Conf. Pattern Recog., vol. 2, pp. 327–330 (2004)Google Scholar
- 4.Prasad, S.: Online Handwriting Recognition for Tamil. Masters Thesis Report 2008. Indian Institute of Science, Bangalore, India (2008)Google Scholar
- 5.Sundaram, S., Ramakrishnan, A.G.: Improvement of Online Tamil Character Recognition Engine using Post Processing Methods. Accepted for publication in: Proc. Tenth Intl. Conf. on Doc. Anal. and Recog., ICDAR (2009)Google Scholar
- 6.HP Labs Isolated Handwritten Tamil Character Dataset, http://www.hpl.hp.com/india/research/penhw-interfaces-1linguistics.html#datasets