%0 Journal Article
%T Illumination Invariant Recognition of Three-Dimensional Texture in Color Images
%A Jie Yang
%A Mohammed Al-Rawi
%A <br>Jie
%A Yang
%A and
%A Mohammed
%A Al-Rawi
%J 计算机科学技术学报
%D 2005
%I 
%X In this paper, illumination-affine invariant methods are presented based on affine moment normalization techniques, Zernike moments, and multiband correlation functions. The methods are suitable for the illumination invariant recognition of 3D color texture. Complex valued moments (i.e., Zernike moments) and affine moment normalization are used in the derivation of illumination affine invariants where the real valued affine moment invariants fail to provide affine invariants that are independent of illumination changes. Three different moment normalization methods have been used, two of which are based on affine moment normalization technique and the third is based on reducing the affine transformation to a Euclidian transform. It is shown that for a change of illumination and orientation, the affinely normalized Zernike moment matrices are related by a linear transform. Experimental results are obtained in two tests: the first is used with textures of outdoor scenes while the second is performed on the well-known CUReT texture database. Both tests show high recognition efficiency of the proposed recognition methods.Supported by the Sino-French Program of Advanced Research under Grant No.PRA SI 03-02 and the Key Project of Shanghai Science and Technology Committee under Grant No.045115001.Jie Yang received the Ph.D. degree from Department of Computer Science, Hamburg University, Germany in 1994. Currently, he is vice director of Institute of Image Processing & Pattern Recognition, Shanghai Jiaotong University, China. He has taken charge of many research projects (e.g., National Natural Science Foundation, 863 National High Tech. Program) and published one book in Germany and more than 100 journal papers. He has won several research prizes issued by Ministry of Education and Shanghai Municipality. He was elected as excellent young professor by Ministry of Education, China, in 2002. His major research interests are object detection and recognition, data fusion and data mining, intelligent system and applications, and medical image processing.Mohammed Al-Rawi received the Ph.D. degree in 2002, from Shanghai Jiaotong University, School of Electronics and Information, in pattern recognition and intelligent systems, B.Sc. and M.Sc. degrees from Baghdad University, College of Sciences in 1989 and 1993 respectively. From 2002 till now he has been working as an assistant professor in the computer science department, Jordan University. His interests range from fast computation of Zernike moments to image recognition applications. His current research position includes teaching and research in image processing and pattern recognition. His recent research interest is learning with generalization of context — sensitive languages by machines, such as neural networks as well as other machines.
%K 3D color texture recognition
%K illumination invariance
%K affine moment normalization
%K Zernike moment
%K affine invariant<br>三维结构辨别
%K 照度不变性
%K 仿射矩
%K 彩色图象
%U http://www.alljournals.cn/get_abstract_url.aspx?pcid=5B3AB970F71A803DEACDC0559115BFCF0A068CD97DD29835&cid=8240383F08CE46C8B05036380D75B607&jid=F57FEF5FAEE544283F43708D560ABF1B&aid=66C209EF02CBCC854AEE7C0BC7D40167&yid=2DD7160C83D0ACED&vid=A04140E723CB732E&iid=38B194292C032A66&sid=73648F51F187AC5E&eid=3BAAE0DA6093AC05&journal_id=1000-9000&journal_name=计算机科学技术学报&referenced_num=0&reference_num=32