CIFO:针对显著对象的彩色图像检索方法  

CIFO:A Retrieval Method for Color Images with Salient Object

作　　者：许雪梅[1] 周立超[1] 杨兵初[1] 李梦平[1] 李丽娴[1] 尹林子[1] 丁一鹏[1] 

机构地区：[1]中南大学物理与电子学院,湖南长沙410083

出　　处：《武汉大学学报（信息科学版）》2015年第1期53-58,共6页Geomatics and Information Science of Wuhan University

基　　金：国家自然科学基金资助项目(61071025;61172047)~~

摘　　要：针对具有显著对象的彩色图像,尤其是事件和场景等语义简单的商标、地标图像,提出了一种组合特征的图像检索方法。在分析光谱能量结构模型的基础上,将颜色边界用于构建前景对象轮廓直方图,将颜色不变量用于提取对象的局部特征点,提出了一种结合对象轮廓与对象局部特征点的方法,称之为Freeman码与ORB特征综合法(color invariants to Freeman and ORB,CIFO)。应用CIFO对多组图像进行了实验,结果表明,对于检索具有显著对象的彩色图像,CIFO特征方法比目前基于特征检索的三种经典方法有明显优势。In order to retrieve color images of a salient object, especially for those images with simple events and scenes, such as trademark images and landmark images, a new image retrieval method with combinational features is proposed. On the basis of the analysis of spectral energy distribution model , the color boundary is used to build a histogram of contour and color invariants to extract a descriptor of key points, thus to present a kind of feature retrieval method combining contour and local features, called CIFO. Experiments on sets of images were carried out by applying CIFO. Experimental results show that, with regard to the retrieving of color images with salient object, the CIFO method has obvious advantages over the other three classical feature-based retrieval methods.

关 键 词：颜色不变量 光谱能量结构 特征点 轮廓特征 图像检索 

分 类 号：P237[天文地球—摄影测量与遥感] TP753[天文地球—测绘科学与技术]