This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Direct Extraction of Topographic Features for Gray Scale Character Recognition
July 1995 (vol. 17 no. 7)
pp. 724-729

Abstract—Optical character recognition(OCR) traditionally applies to binary-valued imagery although text is always scanned and stored in gray scale. However, binarization of multivalued image may remove important topological information from characters and introduce noise to character background. In order to avoid this problem, it is indispensable to develop a method which can minimize the information loss due to binarization by extracting features directly from gray scale character images.

In this paper, we propose a new method for the direct extraction of topographic features from gray scale character images. By comparing the proposed method with Wang and Pavlidis’ method, we realized that the proposed method enhanced the performance of topographic feature extraction by computing the directions of principal curvature efficiently and prevented the extraction of unnecessary features. We also show that the proposed method is very effective for gray scale skeletonization compared to Levi and Montanari’s method.

[1] 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.
[2] T. Pavlidis and Wolberg,“An algorithm for the segmentation of bilevel images,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 570-575,Miami, June 1986.
[3] H. Murakami and B.V.K.V. Kumar,“Efficient calculation of primary images from a set of images,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 4, pp. 511-515, 1982.
[4] C.M. Leung,“A practical basis set for Chinese character recognition,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, pp. 532-537,San Francisco, June 1985.
[5] G. Levi and U. Montanari,“A gray-weighted skeleton,” Information and Control, vol. 17, pp. 62-91, 1970.
[6] S.W. Lam,A.C. Girardin,, and S.N. Srihari,“Gray scale character recognition using boundary features,” Proc. SPIE Conf. Machine Vision Applications in Character Recognition and Industrial Inspection, vol. 1,661, pp. 98-105,San Jose, 1992.
[7] T. Pavlidis,“Recognition of printed text under realistic conditions,” Proc. Second IPTP Conf., pp. 65-76,Tokyo, Jan. 1992.
[8] T. Pavlidis,L. Wang,J. Zhou,W.J. Sakoda,, and J. Rocha,“Recognition of poorly printed text by direct extraction of features from gray scale,” Proc. SPIE Conf. Machine Vision Applications in Character Recognition and Industrial Inspection, vol. 1,661, pp. 1-9,San Jose, Feb. 1992.
[9] L. Wang and T. Pavlidis,“A geometric approach to machine-printed character recognition,” Proc. IEEE Conf. Computer Vision and Pattern Recognition, vol. 2, pp. 665-668,Champaign, Ill., June 1992.
[10] R.M. Haralick,L.T. Watson,, and T.J. Laffey,“The topographic primal sketch,” Int’l J. Robotics Research, vol. 2, pp. 50-72, 1983.
[11] D.H. Kim,Y.S. Hwang,S.T. Park,E.J. Kim,S.H. Paek,, and S.Y. Bang,“Handwritten Korean character image database PE92,” Proc. Second Int’l Conf. Document Analysis and Recognition, pp. 470-473,Tsukuba Science City, Japan, Oct. 1993.
[12] L. Lam, S.W. Lee, and C.Y. Suen, “Thinning Methodologies: A Comprehensive Survey,” IEEE Trans. Pattern Analysis and Machine Intelligence, vol. 14, pp. 869-885, 1992.
[13] S.-W. Lee,L. Lam,, and C.Y. Suen,“A systematic evaluation of skeletonization algorithms,” Pattern Recognition and Artificial Intelligence, vol. 7, no. 5, pp. 1,203-1,225, 1993.

Index Terms:
Gray scale character recognition, principal curvature, principal orthogonal elements, topographic feature extraction.
Citation:
Seong-Whan Lee, Young Joon Kim, "Direct Extraction of Topographic Features for Gray Scale Character Recognition," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 17, no. 7, pp. 724-729, July 1995, doi:10.1109/34.391416
Usage of this product signifies your acceptance of the Terms of Use.