This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
Segmentation of Single- or Multiple-Touching Handwritten Numeral String Using Background and Foreground Analysis
November 2000 (vol. 22 no. 11)
pp. 1304-1317

Abstract—A new approach of segmenting single- or multiple-touching handwritten numeral string (two-digits) is proposed. Most algorithms for segmenting connected digits mainly focus on the analysis of foreground pixels. Some concentrated on the analysis of background pixels only and others are based on a recognizer. In this paper, we combine background and foreground analysis to segment single- or multiple-touching handwritten numeral strings. Thinning of both foreground and background regions are first processed on the image of connected numeral strings and the feature points on foreground and background skeletons are extracted. Several possible segmentation paths are then constructed and useless strokes are removed. Finally, the parameters of geometric properties of each possible segmentation paths are determined and these parameters are analyzed by the mixture Gaussian probability function to decide the best segmentation path or reject it. Experimental results on NIST special database 19 (an update of NIST special database 3) and some other images collected by ourselves show that our algorithm can get a correct rate of 96 percent with rejection rate of 7.8 percent, which compares favorably with those reported in the literature.

[1] N.W. Strathy, C.Y. Suen, and A. Kryzyzak, ”Segmentation of Handwritten Digits Using Contour Features,” Proc. Second Int'l Conf. Document Analysis and Recognition, pp. 577-580, 1993.
[2] Z. Chi, M. Suters, and H. Yan, “Separation of Single- and Double Touching Handwritten Numeral Strings,” Optical Eng., vol. 34, pp. 1,159-1,165, 1995.
[3] Z. Shi, S.N. Shrihari, Y.-C. Shin, and V. Ramanaprasad, “A System for Segmentation and Recognition of Totally Unconstrained Handwritten Numeral Strings,” Proc. Int'l Conf. Document Analysis and Recognition, vol. 2, pp. 455-458, 1997.
[4] J. Hu, D. Yu, and H. Yan, “Algorithms for Partitioning Path Construction of Handwritten Numeral Strings,” Proc. Int'l Conf. Pattern Recognition, vol. 1, pp. 372-374, 1998.
[5] M. Cheriet, Y.S. Huang, and C.Y. Suen, "Background Region-Based Algorithm for the Segmentation of Connected Digits," Proc. 11th Int'l Conf. Pattern Recognition, vol. 2, p. 619, Sept. 1992.
[6] Z. Lu, Z. Chi, and P. Shi, “A Background-Thinning-Based Approach for Separating and Recognizing Connected Handwritten Digit Strings,” Pattern Recognition, vol. 32, no. 6, pp. 921-933, 1999.
[7] B. Zhao, H. Su, and S. Xia, “A New Method for Segmenting Unconstrained Handwritten Numeral String,” Proc. Int'l Conf. Document Analysis and Recognition, vol. 2, pp. 524-527, 1997.
[8] N. Arica and F.T. Yarman-Vural, “A New Scheme for Off-Line Handwritten Connected Digit Recognition,” Proc. Int'l Conf. Pattern Recognition, pp. 1127-1131, 1998.
[9] S.W. Lee and S.Y. Kim, “Integrated Segmentation and Recognition of Handwritten Numerals with Cascade Neural Networks,” IEEE Trans. Systems, Man, and Cybernetics, Part C: Applications and Reviews, vol. 29, no. 2, pp. 285-290, 1999.
[10] R.C. Gonzalez and R.E. Woods, Digital Image Processing, Addison-Wesley, New York, 1993.
[11] L.R. Rabiner and B.H. Juang, Fundamentals of Speech Recognition, Prentice Hall, Upper Saddle River, N.J., 1993.

Index Terms:
Thinning, multiple-touching, segmentation, mixture Gaussian probability.
Citation:
Yi-Kai Chen, Jhing-Fa Wang, "Segmentation of Single- or Multiple-Touching Handwritten Numeral String Using Background and Foreground Analysis," IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 22, no. 11, pp. 1304-1317, Nov. 2000, doi:10.1109/34.888715
Usage of this product signifies your acceptance of the Terms of Use.