一种基于局部颜色特征的图像检索方法  

An Image Retrieval Algorithm Based on Local Color Features

作　　者：林丽惠[1] 杨升[1] 

机构地区：[1]武夷学院计算机科学与工程系,福建武夷山354300

出　　处：《重庆工学院学报（自然科学版）》2009年第7期142-145,共4页Journal of Chongqing Institute of Technology

基　　金：福建自然科学资助项目(S0750016);武夷学院科研基金资助项目(XLQ0805)

摘　　要：提出一种基于局部颜色特征的图像检索算法.该算法首先采用一种新的方法对图像进行分块,提取图像中心区域的主颜色和其他区域的平均颜色作为颜色特征,然后根据图像中心的重要性,对图像各个分块采用不同的加权系数,使局部图像的特征矢量被增强,从而提高了图像的检索精度.实验结果表明,这种基于局部颜色特征的图像检索算法适合于画面明显按分块变化的图像.An image retrieval algorithm based on local color features is proposed. Firstly, this paper splits the image into sub-blocks with a new method, and extracts dominant colors in central regions and the average colors in other sub - block as the characteristics of the color. Secondly, according to the importance of the image center, the different feature weights are adopted in the color features in each sub-block to enhance the feature vector of local image and improve the image retrieval accuracy. The experiments show that this image retrieval algorithm based on local color features can be adapted to sub-block image which obvious changes by screen, such as distinguishing image between the main screen and background screen.

关 键 词：图像检索 主色 颜色特征 加权系数 

分 类 号：TP91[自动化与计算机技术]