《计算机应用研究》|Application Research of Computers

一种快速旋转不变图像检索新方法

Novel Fast Rotation Invariant Image Retrieval Method

免费全文下载 (已被下载 次)  
获取PDF全文
作者 李杰,王磊,楚恒,朱维乐
机构 电子科技大学 1.电子工程学院;2.计算机科学与工程学院,四川 成都 610054
统计 摘要被查看 次,已被下载
文章编号 1001-3695(2007)04-0166-04
DOI 10.3969/j.issn.1001-3695.2007.04.048
摘要 提出了一种新型快速旋转不变图像检索新方法。该方法首先对图像进行傅里叶变换和功率谱分解,提取功率谱的扇形区域能量和环形区域能量参数,并将其均值和标准差作为图像纹理特征。然后,利用谱能量分布特征把纹理的主方向旋转到0°,提取旋转后图像的共生矩阵参数和小波分解各子带图像统计参数作为基本特征。利用所提出的特征提取方法在两组分别包含25类单色自然纹理的图像库上进行检索试验。结果表明,该方法获得了良好的检索效果。
关键词 像检索;谱分解;小波变换
基金项目 国家“863”发展计划资助项目(2005AA121520); 国家自然科学基金资助项目(60272014)
本文URL http://www.arocmag.com/article/1001-3695(2007)04-0166-04.html
英文标题 Novel Fast Rotation Invariant Image Retrieval Method
作者英文名 LI Jie, WANG Lei, CHU Heng, ZHU Wei-le
机构英文名 1. School of Electronic Engineering; 2. School of Computer Science & Engineering, University of Electronic Science & Technology of China, Chengdu Sichuan 610054, China
英文摘要 A novel fast rotation invariant image retrieval method was proposed. First, Fourier transform and Fourier spectrum decomposition were performed. Sector energy and ring energy of spectrum were extracted and their mean and standard deviation were calculated as texture features. Then, texture image was rotated to place its dominant direction at 0 degree according to the spectral energy distribution. Cooccurrence matrix based features and wavelet statistical features of the rotated image were calculated as basic texture features. Image retrieval using the proposed method showed a high performance conducted with two different texture databases both of which include 25 kinds of monochromatic natural textures.
英文关键词
参考文献 查看稿件参考文献
 
收稿日期
修回日期
页码 166-169
中图分类号
文献标志码 A