Handwritten character recognition has received extensive attention in academic and production fields. The recognition system can be either online or off-line. There is a large demand for handwritten text recognition and hand written documents. This paper describes an effective approach for the offline recognition of handwritten Kannada texts. Under the general integrated segmentation-and-recognition benchmark with character over-segmentation and Recognizes the handwritten Kannada text, whenever there is multiple contexts in the text pattern and it is independent of size, slant, orientation, and translation, this approach investigates three important issues: candidate path evaluation, path search, and parameter estimation. In the path evaluation method, we integrate multiple contexts of the text (character recognition scores, geometric and linguistic contexts) from the Bayesian decision view, and convert the classifier outputs to posterior probabilities using confidence transformation. In path search, refined beam search algorithm is used to improve the search efficiency and use a candidate character augmentation mechanism to improve the recognition accuracy. The combining weights of the path evaluation function are optimized by supervised learning using a Maximum Character Accuracy criterion. This method evaluates the recognition performance on Kannada handwritten text images, which contains Kannada letters, words and sentences. The experimented result shows that confidence transformation and combining multiple contexts improve the text line recognition performance, efficiency and throughput significantly.

1. Statistical Texture Features based Handwritten and Printed Text Classification in South Indian Documents Mallikarjun Hangargea, K. C. Santosh, Srikanth Doddamania, Rajmohan Pardeshi
2. Divide and Conquer Technique in Online Handwritten Kannada Character Recognition M. Mahadeva Prasad Dept. of Electronics Mysore University P. G. Centre Hassan, INDIA. prasada9@gmail. com M. Sukumar Dept. of Instrumentation Technology S. J. College of Engineering Mysore, INDIA. m_sukumar@rediffmail. com A. G. Ramakrishnan Dept. of Electrical Engineering Indian Institute of Science Bangalore, INDIA. ramkiag@ee. iisc. ernet. in
3. Recognition of isolated handwritten Kannada vowels Sangame S. K. 1, Ramteke R. J. 1, Rajkumar Benne2.
4. K. Kuhnke, L. Simoncini, Z. M. Kovacs-V, A system for machine-written and hand-written character distinction, in: Proceedings of International Conference on Document Analysis and Recognition, 1995, pp. 811 – 814.
5. T. N. Tan, "Written language recognition based on Texture Analysis", Proc. of ICIP 96, Lausanne, Switz, vol. 2, pp. 185-188, 1996.
6. B. V. Dhandra, Mallikarjun Hangarge, Gururaj Mukarambi, "Spatial Features for Handwritten Kannada and English Character Recognition System", Special Issue on RTIPPR-10, International Journal of Computer Applications (IJCA).
7. R. -W. Dai, C. -L. Liu and B. -H. Xiao, "Kannada Character Recognition: History, Status and Prospects," Frontiers of Computer Science in China, vol. 1, no. 2, pp. 126-136, 2007
8. M. Wuthrich, M. Liwicki, A. Fischer, E. Indermuhle, H. Bunke, G. Viehhauser, and M. Stolz, "Language Model Integration for the Recognition of Handwritten Medieval Documents," Proc. 10th Int'l Conf. Document Analysis and Recognition, pp. 211-215, July 2009.
9. M. -Y. Chen, A. Kundu, and S. N. Srihari, "Variable Duration Hidden Markov Model and Morphological Segmentation for Handwritten Word Recognition," IEEE Trans. Image Processing, vol. 4, no. 12, pp. 1675-1688, Dec. 1995.
10. C. -L. Liu, F. Yin, D. -H. Wang, and Q. -F. Wang, "Online and Offline Handwritten Kannada Character Recognition: Benchmarking on New Databases," Proc. Second CJK Joint Workshop Pattern Recognition, Oct. 2010.
11. H. -S. Tang, E. Augustin, C. Y. Suen, O. Baret, and M. Cheriet, "Spiral Recognition Methodology and Its Application for Recognition of Kannada Bank Checks," Proc. Ninth Int'l Workshop Frontiers in Handwriting Recognition, pp. 263-268, Oct. 2004
12. S. Quiniou, M. Cheriet, and E. Anquetil, "Handling Out-of- Vocabulary Words and Recognition Errors Based on Word Linguistic Context for Handwritten Sentence Recognition," Proc. 10th Int'l Conf. Document Analysis and Recognition, pp. 466-470, July 2009.
13. M. Cheriet, N. Kharma, C. -L. Liu, and C. Y. Suen, Character Recognition Systems: A Guide for Students and Practitioners. John Wiley & Sons, Inc. , 2007.
14. H. Murase, "Online Recognition of Free-Format Japanese Handwritings," Proc. Ninth Int'l Conf. Pattern Recognition, pp. 1143-1147.
15. X. -D. Zhou, C. -L. Liu, and M. Nakagawa, "Online Handwritten Japanese Character String Recognition Using Conditional Random Fields," Proc. 10th Int'l Conf. Document Analysis and Recognition, pp. 521-525, July 2009.
16. L. Y. Tseng and R. C. Chen, "Segmenting Handwritten Kannada Characters Based on Heuristic Merging of Stroke Bounding Boxes and Dynamic Programming," Pattern Recognition Letters, vol. 19, no. 10, pp. 963-973, Aug. 1998.
17. Z. Liang and P. Shi, "A Metasynthetic Approach for Segmenting Handwritten Kannada Character Strings," Pattern Recognition Letters, vol. 26, no. 10, pp. 1498-1511, July 2005.
18. C. -L. Liu, "Handwritten Kannada Character Recognition: Effects of Shape Normalization and Feature Extraction," Proc. Conf. Arabic and Kannada Handwriting Recognition, S. Jaeger and D. Doermann, eds. , pp. 104-128, 2008.
19. F. Kimura, K. Takashina, S. Tsuruoka, and Y. Miyake, "Modified Quadratic Discriminant Functions and the Application to Kannada Character Recognition," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 9, no. 1, pp. 149-153, Jan. 1987.
20. C. -L. Liu and M. Nakagawa, "Evaluation of Prototype Learning Algorithms for Nearest Neighbor Classifier in Application to Handwritten Character Recognition," Pattern Recognition, vol. 34, no. 3, pp. 601-615, Mar. 2001. 1480 IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 34, http://ieeexploreprojects. blogspot. com
21. Y. Jiang, X. Ding, Q. Fu, and Z. Ren, "Context Driven Kannada String Segmentation and Recognition," Proc. Structural, Syntactic, and Statistical Pattern Recognition: Joint IAPR Int'l Workshops, pp. 127- 135, 2006.
22. Y. X. Li, C. L. Tan, and X. Q. Ding, "A Hybrid Post-Processing System for Offline Handwritten Kannada Script Recognition,"Pattern Analysis and Applications, vol. 8, no. 3, pp. 272-286, 2005
23. Q. -F. Wang, F. Yin, and C. -L. Liu, "Integrating Language Model in Handwritten Kannada Text Recognition," Proc. 10th Int'l Conf. Document Analysis and Recognition, pp. 1036-1040, July 2009.
24. M. Nakagawa, B. Zhu, and M. Onuma, "A Model of On-Line Handwritten Japanese Text Recognition Free from Line Direction and Writing Format Constraints," IEICE Trans. Information and Systems, vol. 88, no. 8, pp. 1815-1822, Aug. 2005. .
25. L. Y. Tseng and R. C. Chen, "Segmenting Handwritten Kannada Characters Based on Heuristic Merging of Stroke Bounding Boxes and Dynamic Programming," Pattern Recognition Letters, vol. 19, no. 10, pp. 963-973, Aug. 1998.
26. Qiu-Feng Wang, Fei Yin, and Cheng-Lin Liu, "Handwritten Kannada Text Recognition by Integrating Multiple Contexts", IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, VOL. 34, NO. 8, AUGUST 2012.

Handwritten Kannada Text Recognition Bayesian Decision View Kannada Letters And Words Refined Beam Search Algorithm Over Segmentation Candidate Character Augmentation.