基于伪Zernike色度分布矩的彩色图像检索方法  

Color image retrieval based on Pseudo-Zernike chromaticity distribution moments

作　　者：王向阳[1] 张贝贝[1] 杨红颖[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116081

出　　处：《辽宁师范大学学报（自然科学版）》2011年第3期300-305,共6页Journal of Liaoning Normal University:Natural Science Edition

基　　金：国家自然科学基金项目(60773031;60873222);信息安全国家重点实验室(中国科学院软件研究所)开放基金(04-06-1);辽宁省教育厅高等学校科研项目(L2010230)

摘　　要：颜色是图像的基本视觉属性,不仅与图像中的物体和场景密切相关,而且对图像本身尺寸、方向、视角的依赖性较小.颜色矩是一种简单有效的颜色特征,其数学基础在于图像的任何色彩分布均可用矩来表示.以伪Zernike矩理论为基础,提出了一种基于伪Zernike色度分布矩的彩色图像检索新方法.首先将彩色图像从三维RGB颜色空间转换到二维对立色度空间,以获得图像像素的色差度量值;然后结合伪Zernike矩相关知识,在二维色度空间中计算出各像素的伪Zernike色度分布矩,最后将伪Zernike色度分布矩作为图像颜色特征,并进行彩色图像检索.仿真实验表明,该算法能够准确和高效地查找出用户所需内容的彩色图像,并且具有较好的查准率和查全率.Color is one of the widely used visual features and is invariant to image size and orientation.Color moments is a very simple and effective color feature,and the mathematical foundation of color moments is that any probability distribution is uniquely characterized by its moments.According to the Pseudo-Zernike moments theory,a new color image retrieval using Pseudo-Zernike chromaticity distribution moments is proposed in this paper.Firstly,the image is transformed from RGB space to opponent chromaticity space.Then,the characteristics of the color contents of an image is captured by using Pseudo-Zernike chromaticity distribution moments directly from the chromaticity space.Finally,the similarity between color images is computed by using the Pseudo-Zernike chromaticity distribution moments.Experimental experiments,including comparisons with state-of-the-arts,show the effectiveness of our algorithm in improving the retrieval performance.

关 键 词：图像检索 伪ZERNIKE矩 对立色度空间 相似度 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]