Efficient online handwritten Chinese character recognition system using a two-dimensional functional relationship model

Yun Fah Chang; Jia Chii Lee; Omar Mohd Rijal; Syed Abdul Rahman Syed Abu Bakar

International Journal of Applied Mathematics and Computer Science (2010)

  • Volume: 20, Issue: 4, page 727-738
  • ISSN: 1641-876X

Abstract

top
This paper presents novel feature extraction and classification methods for online handwritten Chinese character recognition (HCCR). The X-graph and Y-graph transformation is proposed for deriving a feature, which shows useful properties such as invariance to different writing styles. Central to the proposed method is the idea of capturing the geometrical and topological information from the trajectory of the handwritten character using the X-graph and the Y-graph. For feature size reduction, the Haar wavelet transformation was applied on the graphs. For classification, the coefficient of determination (R²ₚ) from the two-dimensional unreplicated linear functional relationship model is proposed as a similarity measure. The proposed methods show strong discrimination power when handling problems related to size, position and slant variation, stroke shape deformation, close resemblance of characters, and non-normalization. The proposed recognition system is applied to a database with 3000 frequently used Chinese characters, yielding a high recognition rate of 97.4% with reduced processing time of 75.31%, 73.05%, 58.27% and 40.69% when compared with recognition systems using the city block distance with deviation (CBDD), the minimum distance (MD), the compound Mahalanobis function (CMF) and the modified quadratic discriminant function (MQDF), respectively. High precision rates were also achieved.

How to cite

top

Yun Fah Chang, et al. "Efficient online handwritten Chinese character recognition system using a two-dimensional functional relationship model." International Journal of Applied Mathematics and Computer Science 20.4 (2010): 727-738. <http://eudml.org/doc/208021>.

@article{YunFahChang2010,
abstract = {This paper presents novel feature extraction and classification methods for online handwritten Chinese character recognition (HCCR). The X-graph and Y-graph transformation is proposed for deriving a feature, which shows useful properties such as invariance to different writing styles. Central to the proposed method is the idea of capturing the geometrical and topological information from the trajectory of the handwritten character using the X-graph and the Y-graph. For feature size reduction, the Haar wavelet transformation was applied on the graphs. For classification, the coefficient of determination (R²ₚ) from the two-dimensional unreplicated linear functional relationship model is proposed as a similarity measure. The proposed methods show strong discrimination power when handling problems related to size, position and slant variation, stroke shape deformation, close resemblance of characters, and non-normalization. The proposed recognition system is applied to a database with 3000 frequently used Chinese characters, yielding a high recognition rate of 97.4% with reduced processing time of 75.31%, 73.05%, 58.27% and 40.69% when compared with recognition systems using the city block distance with deviation (CBDD), the minimum distance (MD), the compound Mahalanobis function (CMF) and the modified quadratic discriminant function (MQDF), respectively. High precision rates were also achieved.},
author = {Yun Fah Chang, Jia Chii Lee, Omar Mohd Rijal, Syed Abdul Rahman Syed Abu Bakar},
journal = {International Journal of Applied Mathematics and Computer Science},
keywords = {2D functional classifier; coefficient of determination; handwritten Chinese character recognition; Haar wavelet; multidimensional functional relationship model},
language = {eng},
number = {4},
pages = {727-738},
title = {Efficient online handwritten Chinese character recognition system using a two-dimensional functional relationship model},
url = {http://eudml.org/doc/208021},
volume = {20},
year = {2010},
}

TY - JOUR
AU - Yun Fah Chang
AU - Jia Chii Lee
AU - Omar Mohd Rijal
AU - Syed Abdul Rahman Syed Abu Bakar
TI - Efficient online handwritten Chinese character recognition system using a two-dimensional functional relationship model
JO - International Journal of Applied Mathematics and Computer Science
PY - 2010
VL - 20
IS - 4
SP - 727
EP - 738
AB - This paper presents novel feature extraction and classification methods for online handwritten Chinese character recognition (HCCR). The X-graph and Y-graph transformation is proposed for deriving a feature, which shows useful properties such as invariance to different writing styles. Central to the proposed method is the idea of capturing the geometrical and topological information from the trajectory of the handwritten character using the X-graph and the Y-graph. For feature size reduction, the Haar wavelet transformation was applied on the graphs. For classification, the coefficient of determination (R²ₚ) from the two-dimensional unreplicated linear functional relationship model is proposed as a similarity measure. The proposed methods show strong discrimination power when handling problems related to size, position and slant variation, stroke shape deformation, close resemblance of characters, and non-normalization. The proposed recognition system is applied to a database with 3000 frequently used Chinese characters, yielding a high recognition rate of 97.4% with reduced processing time of 75.31%, 73.05%, 58.27% and 40.69% when compared with recognition systems using the city block distance with deviation (CBDD), the minimum distance (MD), the compound Mahalanobis function (CMF) and the modified quadratic discriminant function (MQDF), respectively. High precision rates were also achieved.
LA - eng
KW - 2D functional classifier; coefficient of determination; handwritten Chinese character recognition; Haar wavelet; multidimensional functional relationship model
UR - http://eudml.org/doc/208021
ER -

References

top
  1. Battaglia, G.J. (1996). Mean square error, AMP Journal of Technology 5(1): 31-36. 
  2. Casey, R.G. (1970). Moment normalization of handprinted character, IBM Journal of Research and Development 14(5): 548-557. Zbl0205.17904
  3. Chang, Y.F., Rijal, O.M. and Abu Bakar, S.A.R. (2010). Multidimensional unreplicated linear functional relationship model with single slope and its coefficient of determination, WSEAS Transactions on Mathematics 9(5): 295-C313. 
  4. Dan, J. (2004). Modern Chinese Character Frequency List, http://lingua.mtsu.edu/chinesecomputing/statistics/char/list.php?Which=MO. 
  5. Deepu, V., Sriganesh, M. and Ramakrishnan, A.G. (2004). Principal component analysis for online handwritten character recognition, Proceedings of the 17th International Conference on Pattern Recognition, Cambridge, UK, Vol. 2, pp. 327-330. 
  6. Dong, J.X., Krzyżak, A. and Suen, C.Y. (2005). An improved handwritten Chinese character recognition system using support vector machine, Pattern Recognition Letters 26(12): 1849-1856. 
  7. Fujarewicz, K. and Wiench, M. (2003). Selecting differentially expressed genes for colon tumor classification, International Journal of Applied Mathematics and Computer Science 13(3): 327-335. Zbl1035.92018
  8. Gao, T.F. and Liu, C.L. (2008). High accuracy handwritten Chinese character recognition using LDA-based compound distances, Pattern Recognition 41(11): 3442-3451. Zbl1167.68436
  9. Gao, X., Jin, L.W., Yin, J.X. and Huang, J.C. (2002). SVMbased handwritten Chinese character recognition, Chinese Journal of Electronics 30(5): 651-654. 
  10. Gonzalez, R.C. and Woods, R.E. (1993). Digital Image Processing, Addison-Wesley Publishing Co., New York, NJ, pp. 580-583. 
  11. Horiuchi, T., Haruki, R., Yamada, H. and Yamamoto, K. (1997). Two-dimensional extension of nonlinear normalization method using line density for character recognition, Proceedings of the 4th International Conference on Document Analysis and Recognition, Ulm, Germany, pp. 511-514. 
  12. Huang, L. and Huang, X. (2001). Multiresolution recognition of offline handwritten Chinese characters with wavelet transform, Proceedings of the 6th International Conference on Document Analysis and Recognition, Washington, DC, USA, pp. 631-634. 
  13. Kato, N., Suzuki, M., Omachi, S.I., Aso, H. and Nemoto, Y. (1999). A handwritten character recognition system using directional element feature and asymmetric Mahalanobis distance, IEEE Transactions on Pattern Analysis and Machine Intelligence 21(3): 258-262. 
  14. Kawamura, A., Yura, K., Hayama, T., Hidai, Y., Minamikawa, T., Tanaka, A. and Masuda, S. (1992). On-line recognition of freely handwritten Japanese characters using directional feature densities, Proceedings of the 11th International Conference on Pattern Recognition, The Hague, the Netherlands, Vol. 2, pp. 183-186. 
  15. Kimura, F., Takashina, K., Tsuruoka, S. and Miyake, Y. (1987). Modified quadratic discriminant functions and its application to Chinese character recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence 9(1): 149-153. 
  16. Kimura, F., Wakabayashi, T., Tsuruoka, S. and Mayake, Y. (1997). Improvement of handwritten Japanese character recognition using weighted direction code histogram, Pattern Recognition 30(8): 1329-1337. 
  17. Liu, C.L. and Marukawa, K. (2004). Global shape normalization for handwritten Chinese character recognition: A new method, Proceedings of the 9th International Workshop on Frontiers of Handwriting Recognition, Tokyo, Japan, pp. 300-305. 
  18. Liu, C.L. and Marukawa, K. (2005). Pseudo two-dimensional shape normalization methods for handwritten Chinese character recognition, Pattern Recognition 38(12): 2242-2255. 
  19. Liu, C.L., Jaeger, S. and Nakagawa, M. (2004). Online recognition of Chinese characters: The-state-of-the art, IEEE Transactions on Pattern Analysis and Machine Intelligence 26(2): 198-213. 
  20. Liu, C.L., Mine, R. and Koga, M. (2005). Building compact classifier for large character set recognition using discriminative feature extraction, Proceedings of the 8th ICDAR, Seoul, Korea, pp. 846-850. 
  21. Liu, C.L., Sako, H. and Fujisawa, H. (2003). Handwritten Chinese character recognition: Alternatives to nonlinear normalization, Proceedings of the 7th International Conference on Document Analysis and Recognition, Edinburgh, UK, pp. 524-528. 
  22. Liu, H. and Ding, X. (2005). Handwritten character recognition using gradient feature and quadratic classifiers with multiple discrimination schemes, Proceedings of the 8th ICDAR, Seoul, Korea, pp. 19-23. 
  23. Liu, J.Z., Cham, W.K. and Chang, M.M.Y. (1996). Online Chinese character recognition using attributed relational graph matching, IEE Proceedings: Vision, Image, Signal Processing 143(2): 125-131. 
  24. Long, T. and Jin, L.W. (2008). Building compact MQDF classifier for large character set recognition by subspace distribution sharing, Pattern Recognition 41(9): 2916-2925. Zbl1154.68491
  25. Michalak, K. and Kwaśnicka, H. (2006). Correlation-based feature selection strategy in classification problems, International Journal of Applied Mathematics and Computer Science 16(4): 503-511. Zbl1112.62059
  26. Miquelez, T., Bengoetxea, E. and Larranaga, P. (2004). Evolutionary computation based on Bayesian classifiers, International Journal of Applied Mathematics and Computer Science 14(3): 335-349. Zbl1084.90538
  27. Ritter, G.X. and Wilson, J.N. (2001). Handbook of Computer Vision Algorithms in Image Algebra, CRC Press LLC, Boca Raton, FL, pp. 225-228. Zbl0964.68145
  28. Romero, R., Berger, R., Thibadeau, R. and Touretsky, D. (1995). Neural network classifiers for optical Chinese character recognition, Proceedings of the 4th Annual Symposium on Document Analysis and Information Retrieval, Las Vegas, NV, USA, pp. 385-398. 
  29. Saeed, K. (2000). A projection approach for Arabic handwritten characters recognition, in P. Sincak and J. Vascak (Eds.), Quo Vadis Computational Intelligence? New Trends and Approaches in Computational Intelligence, Physica-Verlag, Berlin, pp. 106-111. 
  30. Shimodaira, H., Sudo, T., Nakai, M. and Sagayama, S. (2003). On-line overlaid-handwriting recognition based on substroke HMMs, Proceedings of the 7th International Conference on Document Analysis and Recognition, Edinburgh, UK, Vol. 2, p. 1043. 
  31. Shioyama, T., Wu, H.Y. and Nojima, T. (1998). Recognition algorithm based on wavelet transform for handprinted Chinese characters, Proceedings of the 14th International Conference on Pattern Recognition, Hong Kong, China, Vol. 1, pp. 229-232. 
  32. Suzuki, M., Ohmachi, S., Kato, N., Aso, H. and Nemoto, Y. (1997). A discrimination method of similar characters using compound Mahalanobis function, IEICE Transactions on Information and Systems J80-D(10): 2752-2760. 
  33. Świniarski, R.W. (2001). Rough sets methods in feature reduction and classification, International Journal of Applied Mathematics and Computer Science 11(3): 565-582. Zbl0990.68130
  34. Takahashi, K., Yasuda, H. and Matsumoto, T. (1997). A fast HMM algorithm for on-line handwritten character recognition, Proceedings of the 4th International Conference on Document Analysis and Recognition, Ulm, Germany, pp. 369-375. 
  35. Van der Weken, D., Nachtegael, M. and Kerre, E.E. (2002). Image quality evaluation, Proceedings of the 6th International Conference on Signal Processing, Beijing, China, Vol. 1, pp. 711-714. 
  36. Wang, Z., Bovik, A.C., Sheikh, H.R. and Simoncelli, E.P. (2004). Image quality assessment: From error visibility to structural similarity, IEEE Transactions on Image Processing 13(4): 600-612. 
  37. Zheng, J., Ding, X. and Wu, Y. (1997). Recognizing online handwritten Chinese character via FARG matching, Proceedings of the 4th International Conference on Document Analysis and Recognition, Ulm, Germany, Vol. 2, pp. 621-624. 

NotesEmbed ?

top

You must be logged in to post comments.

To embed these notes on your page include the following JavaScript code on your page where you want the notes to appear.

Only the controls for the widget will be shown in your chosen language. Notes will be shown in their authored language.

Tells the widget how many notes to show per page. You can cycle through additional notes using the next and previous controls.

    
                

                
Note: Best practice suggests putting the JavaScript code just before the closing </body> tag.