基于圆谐-傅里叶矩的彩色图像检索算法  

An image retrieval algorithm based on radial harmonic Fourier moments

作　　者：孙晋[1] 

机构地区：[1]辽宁师范大学计算机与信息技术学院,辽宁大连116029

出　　处：《微型机与应用》2014年第9期45-47,52,共4页Microcomputer & Its Applications

摘　　要：针对现有基于颜色信息的图像检索方法对图像描述能力不强、不能有效刻画色彩信息、对噪声敏感等问题,提出了一种基于圆谐-傅里叶矩的彩色图像检索算法。该算法首先将彩色图像从常见的RGB颜色空间转换到对立颜色空间;然后在对立颜色空间的基础上,结合圆谐-傅里叶矩的理论知识,构造出彩色图像的颜色特征,并进行图像检索。实验结果证明,该方法能够准确高效地提取图像中的颜色信息,并得到比较理想的检索结果。To solve the problems that existing methods can not illustrate the image thoroughly , depict the information of color and be sensitive to noise, a new image retrieval algorithm based on radial harmonic Fourier moments is presented. Firstly, it transforms the image from RGB space to opponent chromaticity space. Secondly, it extracts the features of color by using radial harmonic Fourier moments. Lastly, it computes the similarity between color images and gets the results of image retrieval. The experiment results show that this method can improve the accuracy of image retrieval effectively.

关 键 词：对立颜色空间 圆谐-傅里叶矩 基于内容的图像检索 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]