Ancient Books Chinese Characters Segmentation Based on Connected Domain and Chinese Characters Feature

Abstract:

During the processing of handwritten Chinese characters recognition, pretreatment and segmentation has great effect to the recognition. On the base of review upon the often-used algorithm, the article proposes the methods which get the connected domain of binary image use the non-recursion Marking algorithm, and design the algorithm to coherent noise and delete image frame line and segment the character. The article segment the character in the whole scope with the connected domain merging algorithm to overcame the difficult about the tilt; and segment the Chinese character in the part scope with the projection to overcome the difficult about conglutination. The fact proved that this algorithm solves the problem by using single method.

• Periodical: Advanced Materials Research (Volumes 143-144)
• Pages: 227-231
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.143-144.227
• Online since: October 2010
• Authors: Lei Zhu, Jing Yang
• Keywords: Chinese Character Segment, Connected Domain, Projection

References

[1] GAO Yangyu, YANG Yang. Survey of Unconstrained Handwritten Chinese Character Segmentation [J]. Computer Engineering, 2004, 30(5): 144-146.

[2] WANG Kai, JIN Jian-ming, SHI Guang-shun. Chinese Font Recognition Based on Feature Point [J]. Journal of Electronics & Information Technology, 2008, 30(2): 272-276.

DOI: 10.3724/sp.j.1146.2006.01129

[3] FU Qiang, DING Xiao-qing, JIANG Yan. Segmentation and Recognition Algorithm for Chinese Handwritten Address Character String [J]. Journal of Electronics & Information Technology, 2008, 30(12): 2916-2920.

DOI: 10.3724/sp.j.1146.2007.00961

[4] ZHANG Yu-Jin. Image Engineering(1). BeiJing: Tsinghua University Press, 1999: 205-206.

[5] GAO Hong-bo, WANG Wei-xing . New connected component labeling algorithm for binary image[J]. journal of Computer Applications, 2007, 27 (11): 2776-2777.

[6] XU Zheng-guang, BAO Dong-lai, ZHANG Li-xin . Pixel Labeled Algorithm Based on Recursive Method of Connecting Area in Binary Images[J]. Computer Engineering, 2006, 32(24): 186-188.

[7] GE GONG-YAN, XU JJ-JIE, Wang MING-HUA. On the study of image characters location, segmentation and pattern recognition using LS-SVM [C]/ The 6th World Congress on Intelligent Control and Automation, Mar 3-7, 2006. Dalian: Institute of Electrical and Electronics Engineers Inc, 2006: 9650-9654.

DOI: 10.1109/wcica.2006.1713875

[8] ZHU KAI, QI FANG, Jiang R, et al. Using boost to detect and segment characters from natural scenes. In: Proceedings of the first International Workshop on Camera-Based Document Analysis and recognition, Apr 24-27, 2005. Seoul, Korea: IEEE computer Society, 2005. 52-58.

[9] HU QING-MAO, QIAN GUO-YU, NOWINSKI, et al. Fast connected-component labeling in three-dimensional binary images based on iterative recursion [J]. Computer Vision and Image Understanding. 2005, 99(3): 414-434.

DOI: 10.1016/j.cviu.2005.04.001

[10] HE LI-FENG, CHAO YU-YAN, SUZKI. Fast connected- component labeling [J]. Pattern Recognition. 2009, 42(9): 1977-(1987).

DOI: 10.1016/j.patcog.2008.10.013

[11] ZHANG Xiu-jun, GUO Xia, JIN Xin-yu. The Pixel Label Algorithm with Label Rectified of Connecting Area in Binary Pictures[J]. Journal of Image and Graphics, 2003, 8(2): 198-202.