HANDWRITTEN CHARACTER CLASSIFICATION USING THE HOTSPOT FEATURE EXTRACTION TECHNIQUE

Olarik Surinta, Lambert Schomaker, Marco Wiering

Abstract

Feature extraction techniques can be important in character recognition, because they can enhance the efficacy of recognition in comparison to featureless or pixel-based approaches. This study aims to investigate the novel feature extraction technique called the hotspot technique in order to use it for representing handwritten characters and digits. In the hotspot technique, the distance values between the closest black pixels and the hotspots in each direction are used as representation for a character. The hotspot technique is applied to three data sets including Thai handwritten characters (65 classes), Bangla numeric (10 classes), and MNIST (10 classes). The hotspot technique consists of two parameters including the number of hotspots and the number of chain code directions. The data sets are then classified by the k-Nearest Neighbors algorithm using the Euclidean distance as function for computing distances between data points. In this study, the classification rates obtained from the hotspot, mark direction, and direction of chain code techniques are compared. The results revealed that the hotspot technique provides the largest average classification rates.

References

  1. Bhowmik, T. K., Parui, S., Kar, M., and Roy, U. (2007). HMM parameter estimation with genetic algorithm for handwritten word recognition. In Ghosh, A., De, R., and Pal, S., editors, Pattern Recognition and Machine Intelligence, volume 4815 of Lecture Notes in Computer Science, pages 536-544. Springer Berlin / Heidelberg.
  2. Blumenstein, M., Verma, B., and Basli, H. (2003). A novel feature extraction technique for the recognition of segmented handwritten characters. Document Analysis and Recognition, International Conference on, 1:137.
  3. Ferdinando, H. (2001). Handwriting Digit Recognition With Fuzzy Logic. Jurnal Teknik Elektro, 1(1).
  4. Kawtrakul, A. and Waewsawangwong, P. (2000). Multifeature extraction for printed thai character recognition. In Natural Language Processing, 2000. SNLP 2000. 4th International Conference on.
  5. Lauer, F., Suen, C. Y., and Bloch, G. (2007). A trainable feature extractor for handwritten digit recognition. Pattern Recognition, 40(6):1816-1824.
  6. LeCun, Y. and Cortes, C. (1998). The MNIST database of handwritten digits.
  7. Pal, U., Sharma, N., Wakabayashi, T., and Kimura, F. (2008). Handwritten character recognition of popular south indian scripts. In Doermann, D. and Jaeger, S., editors, Arabic and Chinese Handwriting Recognition, volume 4768 of Lecture Notes in Computer Science, pages 251-264. Springer Berlin / Heidelberg.
  8. Rajashekararadhya, S. and Ranjan, P. (2009). Zone based feature extraction algorithm for handwritten numeral recognition of kannada script. In Advance Computing Conference, 2009. IACC 2009. IEEE International, pages 525-528.
  9. Sanossian, H. and Evans, D. (1998). Efficient feature extraction technique for english characters. International Journal of Computer Mathematics, 66(3- 4):257-265.
  10. Trier, Ø. D., Jain, A. K., and Taxt, T. (1996). Feature extraction methods for character recognition-a survey. Pattern Recognition, 29(4):641-662.
Download


Paper Citation


in Harvard Style

Surinta O., Schomaker L. and Wiering M. (2012). HANDWRITTEN CHARACTER CLASSIFICATION USING THE HOTSPOT FEATURE EXTRACTION TECHNIQUE . In Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM, ISBN 978-989-8425-98-0, pages 261-264. DOI: 10.5220/0003712002610264


in Bibtex Style

@conference{icpram12,
author={Olarik Surinta and Lambert Schomaker and Marco Wiering},
title={HANDWRITTEN CHARACTER CLASSIFICATION USING THE HOTSPOT FEATURE EXTRACTION TECHNIQUE},
booktitle={Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,},
year={2012},
pages={261-264},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0003712002610264},
isbn={978-989-8425-98-0},
}


in EndNote Style

TY - CONF
JO - Proceedings of the 1st International Conference on Pattern Recognition Applications and Methods - Volume 1: ICPRAM,
TI - HANDWRITTEN CHARACTER CLASSIFICATION USING THE HOTSPOT FEATURE EXTRACTION TECHNIQUE
SN - 978-989-8425-98-0
AU - Surinta O.
AU - Schomaker L.
AU - Wiering M.
PY - 2012
SP - 261
EP - 264
DO - 10.5220/0003712002610264