本文已被:浏览 1414次 下载 2767次
Received:October 25, 2012 Revised:December 07, 2012
Received:October 25, 2012 Revised:December 07, 2012
中文摘要: 小波变换具有良好的局部特性与多尺度特性, 能多尺度逼近边缘, 这使得它在图像奇异性检测和特征提取方面得到了广泛的应用. 通过三次样条二进小波变换模极大值法提取图像彩色边缘, 用彩色边缘的环形颜色直方图表示颜色特征, 用小波模极大值的环形直方图表示形状特征; 最后利用上述两种直方图计算图像间的相似度, 并进行彩色图像检索. 实验结果表明该算法不仅具有较好的查准率和查全率, 而且对图像中存在的光照变化和几何变化(尺度, 平移, 旋转等)具有较强的鲁棒性.
Abstract:Wavelet transform has good local characteristics and multi-scale characteristic, it can multi-scale edge approximation, this makes it wide range of applications in image singularity detection and feature extraction. In this paper color edge extracted by using dyadic wavelet transform modulus maxima,and then using annular color histogram express image color features, using wavelet modulus maxima annular histogram express shape feature. Finally, the similarity between color images is computed by using a combined feature index based on the above two histogram. experimental results show that the approach has a good retrieval performance, and strong robustness to the image illumination change and geometry change.
文章编号: 中图分类号: 文献标志码:
基金项目:新疆维吾尔自治区自然科学基金(200721104);国家自然科学基金(10661010,11261061);新疆师范大学2012年大学生课外学术科技作品项目(基于多特征的图像检索方法)
引用文本:
阿卜杜如苏力•奥斯曼,吐尔洪江•阿布都克力木,马丽亚木•阿布来孜.结合边缘颜色与形状特征的图像检索方法.计算机系统应用,2013,22(4):153-156,133
ABDURUSUL Osman,MARYAMGUL Abliz,TURGHUNJAN Abdukirim turki.Edge Based Image Retrieval Approach Combining Color Feature and Shape Feature.COMPUTER SYSTEMS APPLICATIONS,2013,22(4):153-156,133
阿卜杜如苏力•奥斯曼,吐尔洪江•阿布都克力木,马丽亚木•阿布来孜.结合边缘颜色与形状特征的图像检索方法.计算机系统应用,2013,22(4):153-156,133
ABDURUSUL Osman,MARYAMGUL Abliz,TURGHUNJAN Abdukirim turki.Edge Based Image Retrieval Approach Combining Color Feature and Shape Feature.COMPUTER SYSTEMS APPLICATIONS,2013,22(4):153-156,133