This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Structure Extraction from Decorated Characters Using Multiscale Images
March 2001 (vol. 23 no. 3)
pp. 315-322

Abstract—Decorated characters are widely used in various documents. Practical optical character reader is required to deal with not only common fonts but also complex designed fonts. However, since the appearances of decorated characters are complicated, most general character recognition systems cannot give good performances on decorated characters. In this paper, an algorithm that can extract character's essential structure from a decorated character is proposed. This algorithm is applied in preprocessing of character recognition. The proposed algorithm consists of three procedures: global structure extraction, interpolation of structure, and smoothing. By using multiscale images, topographical features, such as ridges and ravines are detected for structure extraction. Ridges are used for extracting global structure and ravines are used for interpolation. Experimental results show character structures are clearly extracted from very complex decorated characters.

[1] S. Mori, K. Yamamoto, and M. Yasuda, “Research on Machine Recognition of Handprinted Characters,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 6, no. 4, pp. 386-405, July 1984.
[2] S. Impedovo, L. Ottaviano, and S. Occhinegro, “Optical Character Recognition—A Survey,” Int'l J. Pattern Recognition and Artificial Intelligence, vol. 5, nos. 1 and 2, pp. 1-24, 1991.
[3] T.W. Hildebrandt and W. Liu, “Optical Recognition of Handwritten Chinese Characters: Advances since 1980,” Pattern Recognition, vol. 26, no. 2, pp. 205-225, 1993.
[4] K. Yamamoto, “Recognition of Handprinted KANJI Characters by Relaxation Matching,” Trans. IEICE, vol. J65-D, no. 9, pp. 1167-1174, Sept. 1982. (in Japanese).
[5] F.H. Cheng, “Multi-Stroke Relaxation Matching Method for Handwritten Chinese Character Recognition,” Pattern Recognition, vol. 31, no. 4, pp. 401-410, 1998.
[6] H. Nishida, “Automatic Construction of Structural Models Incorporating Discontinuous Transformations,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 18, no. 4, pp. 400-411, Apr. 1996.
[7] J. Rocha and T. Pavlidis, "A Shape Analysis Model With Applications to a Character Recognition System," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 16, pp. 393-404, 1994.
[8] Y.Y. Tang et al., “Offline Recognition of Chinese Handwriting by Multifeature and Multilevel Classification,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, no. 5, pp. 556-561, May 1998.
[9] N. Kato, M. Suzuki, S. Omachi, H. Aso, and Y. Nemoto, “A Handwritten Character Recognition System Using Directional Element Feature and Asymmetric Mahalanobis Distance,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 21, no. 3, pp. 258-262, Mar. 1999.
[10] T. Wakahara, "Shape Matching Using LAT and Its Application to Handwritten Numeral Recognition," IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 16, no. 6, pp. 618-629, June 1994.
[11] M. Revow, C.K.I. Williams, and G.E. Hinton, “Using Generative Models for Handwritten Digit Recognition,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 18, no. 6, pp. 592-606, June 1996.
[12] R.M. Haralick, L.T. Watson, and T.J. Laffey, “The Topographic Primal Sketch,” Int'l J. Robotics Research, vol. 2, no. 1, pp. 50-72, 1983.
[13] L. Wang and T. Pavlidis,“Direct gray scale extraction of features for character recognition,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 15, no. 10, pp. 1,053-1,067, Oct. 1993.
[14] T. Lindeberg, “Edge Detection and Ridge Detection with Automatic Scale Selection,” Proc. IEEE Conf. Computer Vision and Pattern Recognition (CVPR '96), pp. 465-470, 1996.
[15] H. Hontani and K. Deguchi, “Multi-Scale Image Analysis for Detection of Characteristic Component Figure Shapes and Sizes,” Proc. 14th Int'l Conf. Pattern Recognition (ICPR '98), pp. 1470-1472, Aug. 1998.
[16] H. Ozawa and T. Nakagawa, "A Character Image Enhancement Method From Characters With Various Background Images," Proc. Second Int'l Conf. Document Analysis and Recognition, pp. 58-61,Tsukuba, Japan, Oct. 1993.
[17] S. Liang and M. Ahmadi, “A Morphological Approach to Text String Extraction from Regular Periodic Overlapping Text/Background Images,” Graphical Models and Image Processing, vol. 56, no. 5, pp. 402-413, Sept. 1994.
[18] M. Sawaki and N. Hagita, “Text-Line Extraction and Character Recognition of Document Headlines with Graphical Designs Using Complementary Similarity Measures,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 20, no. 10, pp. 1,103-1,108, Oct. 1998.
[19] J.D. Hobby and T.K. Ho, “Enhancing Degraded Document Images via Bitmap Clustering and Averaging,” Proc. Fourth Int'l Conf. Document Analysis and Recognition (ICDAR '97), pp. 394-400, Aug. 1997.
[20] C. Rodríguez, J. Muguerza, M. Navarro, A. Zárate, J.I. Martín, and J.M. Pérez, “A Two-Stage Classifier for Broken and Blurred Digits in Forms,” Proc. 14th Int'l Conf. Pattern Recognition (ICPR '98), pp. 1,101-1,105, Aug. 1998.
[21] T.R. Chou and F. Chang, “Optical Chinese Character Recognition for Low-Quality Document Images,” Proc. Fourth Int'l Conf. Document Analysis and Recognition (ICDAR '97), pp. 608-611, Aug. 1997.
[22] J. Schürmann, Pattern Classification. John Wiley&Sons, 1996.
[23] T. Lindeberg, Scale-Space Theory in Computer Vision. Kluwer Academic, 1994.
[24] S. Omachi, M. Inoue, and H. Aso, “Structure Extraction from Various Kinds of Decorated Characters Using Multi-Scale Images,” Proc. 15th Int'l Conf. Pattern Recognition (ICPR 2000), vol. 4, pp. 455-458, Sept. 2000.

Index Terms:
Character recognition, OCR, decorated character, structure extraction.
Citation:
Shin'ichiro Omachi, Masaki Inoue, Hirotomo Aso, "Structure Extraction from Decorated Characters Using Multiscale Images," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 23, no. 3, pp. 315-322, March 2001, doi:10.1109/34.910884
Usage of this product signifies your acceptance of the Terms of Use.