Yan Ji-kun, Zhang Zhen, Zheng Hui. Application of Deformable Grid in Image Recognition[J]. Journal of Electronics & Information Technology, 2004, 26(8): 1183-1189.
Citation:
Yan Ji-kun, Zhang Zhen, Zheng Hui. Application of Deformable Grid in Image Recognition[J]. Journal of Electronics & Information Technology, 2004, 26(8): 1183-1189.
Yan Ji-kun, Zhang Zhen, Zheng Hui. Application of Deformable Grid in Image Recognition[J]. Journal of Electronics & Information Technology, 2004, 26(8): 1183-1189.
Citation:
Yan Ji-kun, Zhang Zhen, Zheng Hui. Application of Deformable Grid in Image Recognition[J]. Journal of Electronics & Information Technology, 2004, 26(8): 1183-1189.
Grid feature is a popular feature extraction scheme in image recognition, and usually higher performance could be obtained with the help of deformable template, espe-cially in such difficult image recognition tasks as character recognition, digit recognition, logo recognition etc. The critical shortcoming of deformable template is time-consuming. In this paper the method of deformable grid is proposed to compensate for the shortcoming of deformable template. Firstly certain grid must be superimposed on image, then unlike de-formable template where deformation is applied to image, various deformations are applied to grid. Because the number of grid is much less than that of pixels in image, the method is much more timesaving comparing to deformable template. The approximate equality of deformable template and deformable gird is also analyzed. The method is evaluated by two image recognition experiments, namely, logo recognition and off-line Chinese character recognition. The improvements in recognition rate by 7.3% in first experiment, and 5.8% in second one are obtained by the use of deformable grid.
Trier Q D,Jain A K,Taxt T.Feature extraction methods for character recognition-A survey[J].Pattern Recognition.1996,29(4):641-662[2]Zhang Dengsheng,Lu Guojun.A comparative study of three region shape descriptors,Digital Image Computing Techniques and Applications(DICTA2002).Melbourne,Australia,2002:21-22.[3]Yan Ji-Kun,Zheng Hui,Xi Jian-Min.Logo recognition in low quality document images.Proceedings of International Conference on Intelligent Information Technology(ICIIT2002).Beijing,China,2002:185-189.[4]Jain A K,Zongker D.Representation and recognition of handwritten digits using deformable templates.IEEE Trans.on Pattern Analysis and Machine Intelligence,1997,19(12):1365-1388.[5]Ha T M,Bunke H.Off-line handwritten numeral recognition by perturbation method[J].IEEE Trans.on Pattern Analysis and Machine Intelligence.1997,19(5):535-539[6]Jain A K,Vailaya A.Shape-based retrieval:A case study with trademark image databases[J].Pattern Recognition.1998,31(9):1369-1390[7]ftp://ftp.cfar.umd.edu/pub/documents/contrib/databases/UMDlogo-database.tar.[8]燕继坤,郑辉,张震.基于网格变形的脱机手写汉字识别.计算机研究与发展,2001,38(增刊):127-131.[9]李辉,史忠植,许卓群.运用文本领域的常识改善基于支撑向量机的文本分类器的性能.中文信息学报,2002,16(2):7-13.
DownLoad: