A Retrieval Method of Ancient Chinese Character Images

Abstract:

Global and local image retrieval of ancient Chinese characters is a helpful means for character research work. Because of the characteristics of ancient Chinese characters such as complex structures and variant shapes, there exist many theoretical and technical problems in feature extraction, clustering and retrieval of these images. A retrieval method was established with the strategy of “clustering before matching” for the ancient Chinese character images by integrating the structural features of them. Firstly, preprocessed character image area was divided into elastic meshes and the directional elements were extracted to form the feature vectors. Then, K-means algorithm was employed to cluster the character images within global and local areas. Finally, the similar images within selected areas were searched in corresponding cluster and the obtained images were provided to users. The experimental results show that this method is helpful for the improvement of the efficiency of ancient Chinese character study.

• Periodical: Applied Mechanics and Materials (Volumes 462-463)
• Pages: 432-437
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.462-463.432
• Online since: November 2013
• Authors: Xue Dong Tian*, Xue Sha Jia, Fang Yang, Xin Fu Li, Xiu Fen Miao
• Keywords: Ancient Chinese Character, Directional Element, Elastic Mesh, Image Retrieval, K-Mean

References

[1] Yuan Zhang, Canping Li, Information Technology, 2011, p.38, In Chinese.

[2] K.C. Leung, C.H. Leung, Pattern Recognition, 2009, p.1.

[3] Tianlei Wu, Shaoping Ma, Proc. 7th Inter. Conf. on Document Analysis and Recognition, IEEE, Edinburgh, Scotland, 2003, p.529.

[4] Uday Pratap Singh, Sanjeev Jain, Gulfishan Firdose Ahmed, Inter. Journal of Computer Science and Information Security, Vol. 8( 2010), p.301.

[5] Zhuo Chen. SVM-based Active Feedback in Image Retrieval Using Clustering. Chongqing: Chongqing University, 2010, In Chinese.

[6] Guiyue Zhang. Research of Image Retrieva Technology Based on Salient Region and SVM Relevance Feedback. Xian: Xidian University, 2012, In Chinese.

[7] Xiangyang Wang, Ming Ji, Junfeng Wu, Proc. 2nd Inter. Congress on Image and Signal Processing, IEEE, Tianjin, China, 2009, p.1.

[8] Qizhou Li. Research of Image Retrieva Technology Based on Local Feature. Nanjing: Nanjing University of Information Science & Technology, 2011, In Chinese.

[9] Yan Zhu, Journal of National Library of China, 2004, p.91, In Chinese.

[10] Haiyang Li, Journal of Chifeng University(Soc. Sci), Vol. 32(2011), p.128, In Chinese.

[11] Guang Chen, Hongguang Zhang, Jun Guo, Pattern Recognition and Data Mining, Vol. 3686(2005), p.560.

[12] Xue Gao, Lianwen Jin, Junxun Yin, Pattern Recognition and Artificial Intelligence, Vol. 15(2002), p.351, In Chinese.

[13] Lianwen Jin, Xue Gao, Application Research of Computers, 2004, p.38, In Chinese.

[14] Ying Lin, Yue Lv, Computer Engineering, Vol. 35(2009), p.185, In Chinese.

[15] Ling Yang, Yifang Mao, Tianai Wu, Journal of Liaoning Provincial College of Communications, Vol. 10( 2008), p.38, In Chinese.

[16] Shigen Hu, Yiqin Lu, Computer Simulation, Vol. 27(2010), p.245, In Chinese.