Abstract To segment machineprinted English characters of small font is a challenging problems. It is difficult to segment small font characters because of their small energies and the overlap by letters. In this paper, many kinds of overlaps caused by the serifs of letters are analyzed, and an algorithm to remove the serifs is proposed. Consequently, a method to segment machineprinted English characters of small fonts is designed. Experiments give encouraging segmentation results for not only small font characters but also large font characters.
[1] Jung M C, Shin Y C, Srihari S N. Machine Printed Character Segmentation Method Using Side Profiles // Proc of the IEEE International Conference on Systems, Man, and Cybernetics. Tokyo, Japan, 1999, Ⅵ: 863-867 [2] Lee S W, Kim W J. Direct Extraction of Topographic Features for Gray Scale Character Recognition. IEEE Trans on Pattern Analysis and Machine Intelligence, 1995, 17(7): 724-729 [3] Lee S W, Lee D J, Park H S. A New Methodology for Gray-Scale Character Segmentation and Recognition. IEEE Trans on Pattern Analysis and Machine Intelligence, 1996, 18(10): 1045-1050 [4] Li Zuo, Wang Shuhua, Cai Shijie. An Algorithm for Segmentation of Merged Characters Based on Forepart Prediction and Recognition. Journal of Computer Research and Development, 2001, 38(11): 1137-1344 (in Chinese) (李 佐, 王姝华, 蔡士杰. 一种基于前端预测识别的粘连字符分割方法. 计算机研究与发展, 2001, 38(11): 1137-1344) [5] Lu Da, Pu Wei, Xie Mingpei. Topographic Approach Recognizer for Merged Character Images Based on Skeletonization. Computer Engineering and Applications, 2000, 36(2): 65-66,161 (in Chinese) (卢 达, 浦 炜, 谢铭培. 基于骨架法形态分析的连体字符图像识别方法. 计算机工程与应用, 2000, 36(2): 65-66,161) [6] Blum H. A Transformation for Extracting New Descriptors of Shape // Watheen-Dunn W, ed. Models of the Perception of Speech and Visual Form. Cambridge, USA: MIT Press, 1967: 362-380 [7] Montanari U. Continuous Skeletons from Digitized Images. Journal of Association for Computing Machinery, 1969, 16(4): 534-549 [8] Jang B K, Chin R T. Analysis of Thinning Algorithms Using Mathematical Morphology. IEEE Trans on Pattern Analysis and Machine Intelligence, 1990, 12(6): 541-551 [9] Vincent L, Soille P. Watersheds in Digital Spaces: An Efficient Algorithm Based on Immersion Simulations. IEEE Trans on Pattern Analysis and Machine Intelligence, 1991, 13(6): 583-598 [10] Zou J J, Chang H H, Yan H. Shape Skeletonization by Identifying Discrete Local Symmetries. Pattern Recognition, 2001, 34(10): 1895-1905 [11] Zou Jujia, Yan Hong. Skeletonization of Ribbon-Like Shapes Based on Regularity and Singularity Analyses. IEEE Trans on Systems, Man, and Cybernetics, 2001, 31(3): 401-407 [12] Guo Jianxiong, Yang Lihua, Huang Daren. A Local Hough Transform-Based Algorithm for Automatic Location of Reference Baseline in Bank Cheques. Journal of Image and Graphics, 2003, 8(Z1): 55-85 (in Chinese) (郭剑雄, 杨力华, 黄达人. 基于局部Hough变换的银行支票参考基线自动定位算法. 中国图像图形学报, 2003, 8(Z1): 55-58) [13] Held A, Abe K. On the Decomposition of Binary Shapes into Meaningful Parts. Pattern Recognition, 1994, 27(5): 637-647 [14] Held A, Abe K. On Approximate Convexity. Pattern Recognition Letters, 1994, 15(6): 611-618 [15] Zimmer Y, Tepper R, Akselrod S. An Improved Method to Compute the Convex Hull of a Shape in a Binary Image. Pattern Recognition, 1997, 30(3): 397-402
2006, Vol. 19 
