一种基于颜色分块特征的自适应图象检索方法  

A Self- adaptive Approach to Combining Color Features of Partition with Genetic Algorithm in Image Retrieve

作　　者：王康[1] 王小铭[2] 

机构地区：[1]广东轻工职业技术学院计算机系,广州510000 [2]华南师范大学计算机系,广州510631

出　　处：《计算机工程与应用》2005年第32期77-79,共3页Computer Engineering and Applications

摘　　要：文章提出了一种基于颜色特征的,结合分块和遗传算法的图像检索方法。该方法充分利用了分块的特点,改善了颜色特征缺乏空间信息的缺点,同时利用遗传算法的自适应性,减少了在相关反馈的检索过程中,用户的选择操作。文章通过比较实验,证明了这种方法的有效性,并提出了进一步改进的方案。This paper discusses a image-retrieving method combined with color features of partition and genetic algorithm.This method amends the disadvantage of lacking spatial information of common color feature.The more important aspect is that this method cuts down the work of users＇ while using relevant feedback by using of the selfadaptive character of Genetic Algorithm. By comparative experiments,this paper proves the availability of this method, and the possible further improvements are also offered.

关 键 词：图象检索 颜色特征 分块 遗传算法 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]