Comparing natural and synthetic training data for off-line cursive handwriting recognition

Proceedings - International Workshop on Frontiers in Handwriting Recognition, IWFHR

Volumn , Issue , 2004, Pages 221-225

  Varga, Tamás ^a   Bunke, Horst ^a  

^a UNIVERSITY OF BERN   (Switzerland)

Author keywords

Hidden Markov model (HMM); Off line cursive hanawriting recognition; Perturbation model; Synthetic training data; Training set expansion

Indexed keywords

HIDDEN MARKOV MODE (HMM); OFFLINE CURVASIVE HANDWRITING RECOGNITION; PERTURBATION MODEL; SYNTHETIC TRAINING DATA; TRAINING SET EXPANSION;

DATA ACQUISITION; FUNCTIONS; INTERPOLATION; MARKOV PROCESSES; MATHEMATICAL MODELS; NONLINEAR SYSTEMS; PERTURBATION TECHNIQUES;

CHARACTER RECOGNITION;

EID: 18044387170     PISSN: 15505235     EISSN: None     Source Type: Conference Proceeding    
DOI: 10.1109/IWFHR.2004.29     Document Type: Conference Paper

References (15)

1. H. Baird. The State of the Art of Document Image Degradation Modeling. In Proc. 4th IAPR Workshop on Document Analysis Systems (DAS 2000), Rio de Janeiro, Brasil, December 2000.
2. J. Cano, J. Pérez-Cortes, J. Arlandis, and R. Llobet. Training Set Expansion in Handwritten Character Recognition. In Proc. 9th SSPR / 4th SPR, pages 548-556, Windsor, Ontario, Canada, 2002.
3. H. Drucker, R. Schapire, and P. Simard. Improving Performance in Neural Networks Using a Boosting Algorithm. In S. Hanson et. al., editor, Advances in Neural Information Processing Systems 5, pages 42-49. Morgan Kaufmann, San Mateo CA, 1993.
4. I. Guyon. Handwriting synthesis from handwritten glyphs. In Proc. 5th Int. Workshop on Frontiers in Handwriting Recognition, pages 309-312, Essex, England, 1996.
5. J. Mao and K. Mohiuddin. Improving OCR performance using character degradation models and boosting algorithms. Pattern Recognition Letters, 18:1415-1419, 1997.
6. U.-V. Marti and H. Bunke. Using a statistical language model to improve the performance of an HMM-based cursive handwriting recognition system. Int. Journal of Pattern Recognition and Artifical Intelligence, 15(1):65-90, 2001.
7. U.-V. Marti and H. Bunke. The IAM-Database: an English Sentence Database for Off-line Handwriting Recognition. Int. Journal on Document Analysis and Recognition, 5(1):39-46, 2002.
8. M. Mon, A. Suzuki, A. Shio, and S. Ohtsuka. Generating new samples from handwritten numerals based on point correspondence. In Proc. 7th Int. Workshop on Frontiers in Handwriting Recognition, pages 281-290, Amsterdam, The Netherlands, 2000.
9. L. Rabiner and B.-H. Juang. Fundamentals of Speech Recognition. Prentice Hall, 1993.
10. H. Rowley, M. Goyal, and J. Bennett. The effect of large training set sizes on online Japanese Kanji and English cursive recognizers. In Proc. 8th Int. Workshop on Frontiers in Handwriting Recognition, pages 36-40, Niagara-on-the-Lake, Ontario, Canada, 2002.
11. S. Setlur and V. Govindaraju. Generating manifold samples from a handwritten word. Pattern Recognition Letters, 15:901-905, 1994.
12. P. Simard, Y. Cun, and J. Denker. Efficient pattern recognition using a new transformation distance. In S. Hanson et. al., editor, Advances in Neural Information Processing Systems 5, pages 50-58. Morgan Kaufmann, San Mateo CA, 1993.
13. T. Varga and H. Bunke. Generation of Synthetic Training Data for an HMM-based Handwriting Recognition System. In Proc. 7th Int. Conf. on Document Analysis and Recognition, pages 618-622, Edinburgh, Scotland, August 2003.
14. T. Varga and H. Bunke. Off-line Handwritten Textline Recognition Using a Mixture of Natural and Synthetic Training Data. In Proc. 17th International Conference on Pattern Recognition, Cambridge, United Kingdom, August 2004, to appear.
15. O. Velek and M. Nakagawa. The Impact of Large Training Sets on the Recognition Rate of Off-line Japanese Kanji Character Classifiers. In Proc. 5th Int. Workshop on Document Analysis Systems (DAS 2002), pages 106-109, August 2002.