基于分块主色和形状特征的彩色图像检索  

Image retrieval based on main color and shape of image blocks

作　　者：孙君顶[1] 毋小省[1] 

机构地区：[1]河南理工大学计算机科学与技术学院,河南焦作454000

出　　处：《光电工程》2006年第12期85-90,共6页Opto-Electronic Engineering

基　　金：河南理工大学博士基金(B050901)

摘　　要：提出一种新的基于分块主色和形状特征的图像检索算法。图像首先被划分为不同分块,并提取分块主色,然后采用主色直方图作为图像的颜色特征。同时,提出采用平坦度和凹凸度来描述图像的形状特征,在分析平坦度和凹凸度统计特性的基础上,提出了新的量化的方法,并采用量化后的特征直方图作为图像的形状特征。试验结果表明,本文方法在图像的相似性检索时是很有效的,并具有较高的检索效率。A new image retrieval algorithm based on the main color and shape of image blocks was presented. Images were firstly partitioned into equal-sized sub-images. Then, the main color of each block was extracted and the main color histogram was computed as the image＇s color feature. In order to describe the shape feature, two new descriptors, flatness and roughness of the block were proposed. According to the statistical character of flatness and roughness, different quantized methods were discussed. In the end, shape histogram was accepted to represent the shape feature. Experiment results show that the new algorithm is more effective in image retrieval and it is better than three traditional algorithms in performance.

关 键 词：图像检索 主色 平坦度 凹凸度 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]