|
|
Statistics of the Number of Seals Based on Multi-directional Projection |
SONG Yun-cen1,CHEN Zhen-long1,LUO Ying1,LIU Lin1,YE Yu-tang1,CHEN Wei1,2,LIU Shao-zhuang1,2 |
1. Lab of MOEMIL, University of Electronic Science and Technology of China, Chengdu,Sichuan 610054, China;
2. Chengdu HOLDTECS Co. Ltd., Chengdu,Sichuan 610054, China |
|
|
Abstract A multidirectional projection method which can count the number of seals on bundled banknotes automatically and quickly is introduced. The fundamental principle of this method is that, based on the theory of image processing, converting bundled banknotes image from RGB space to LUV space in the first, processing it by using cluster analysis algorithm, then a binary image of the tied note can be gained. Using thought of multidirectional projection, projection transformation in the vertical direction and the horizontal direction then be applied to in turn. Finally the number of the seals can be counted. Theoretical analysis and the experimental results show that, this method can remove the impact of background noise effectively, do not depend on the quality of seals sigil, and improve the efficiency and accuracy of the automatical number statistics of the seals.
|
|
|
|
|
[1]Wang S, Siskind J M. Image segmentation with ratio cut[J]. IEEE Trans on Pattern Analysis and Machine Intelligence.2008,25(6):675-690.
[2]Tao W B, Jin H, Zhang Y M. Color image segmentation based on mean shift and normalized cuts[J]. IEEE Trans on Systems.2007,37(5):1382-1389.
[3]Vadiveloo M, Abdullah R, Rajeswari M, et al. Image segmentation with cyclic load balanced parallel Fuzzy C-Means cluster analysis[C]//2011 IEEE International Conference on Imaging Systems and Techniques(IST).Guilin,China,2011:124-129.
[4]Hong H Y, Guo X Y, Zhang X H. An Improved Segmentation Algorithm of Color Image in Complex Background Based on Graph Cuts[C]//2011 IEEE International Conference on Computer Science and Automation Engineering(CSAE).Guilin,China,2011:642-645.
[5]曹卫. 基于二分法的字符垂直投影分割算法[J].软件导刊.2010,30(10):71-72.
[6]曾锐. 印章特征提取算法研究[D].杭州:浙江大学, 2007.
[7]Lee W C, Chen C H. A Fast Template Matching Method for Rotation Invariance Using Two-Stage Process[C]//IH-MSOP '09. Fifth International Conference on Intelligent Information Hiding and Multimedia Signal Processing,Kyoto,Japan,2009:9-12.
[8]Zeng Y C, Chen J F. Adaptive template-matching method for recognition of low-resolution license number[C]//2010 International Computer Symposium(ICS).Tainan,China,2010:228-233.
[9]Li Z H,Liu C Y,Cui J G, et al. Improved rotation invariant template matching method using relative orientation codes[C]//The 30th Chinese Control Conference(CCC 2011),Yantai,China,2011:3119-3123.
[10]Sibiryakov A. Fast and high-performance template matching method[C]//2011 IEEE Conference on Computer Vision and Pattern Recognition(CVPR),Colorado Springs,USA,2011:1417-1424.
[11]姜志高.基于二值化处理与模板匹配的图像识别[J].才智.2011,(26):72-73.
[12]何新鹏,黄英,刘奇,等.基于投影的快速模板匹配算法[J].自动化技术与应用.2011,25(7):72-75.
[13]迟晓君,孟庆春.基于投影特征值的车牌字符分割算法[J].计算机应用研究,2006,1(7):256-257.
[14]Yu S,Yu K,Tresp V,et al.Multi-Output Regularized Feature Projection [J].IEEE Transactions on Knowledge and Data Engineering,2011,18(12):1600-1613.
[15]Qong M.An unsupervised classification method for polarimetric SAR images with a projection approach[J].IEEE International Geoscience and Remote Sensing Symposium,2003,7:4471-4473. |
|
|
|