基于聚类与遗传算法的Web图像检索  

Precise image retrieval on web with clustering and genetic algorithm

作　　者：李明[1] 王健琨[1] 

机构地区：[1]兰州理工大学计算机与通信学院,甘肃兰州730050

出　　处：《计算机工程与设计》2008年第15期3975-3979,共5页Computer Engineering and Design

基　　金：甘肃省教育厅科研基金项目(0603-10)

摘　　要：高效的Web图像检索对于用户来说是非常重要的,图像元搜索引擎作为一种有效的图像检索技术可以促进Web图像的检索质量和精度。提出一种基于改进的HACM(hierarchical agglomerative clustering methods)聚类算法和遗传算法的图像元搜索引擎模型,Web图像向量化表示之后运用HACM聚类技术进行分类,然后通过特殊设计的遗传算法对检索结果进行优化排序,最后将排序后的更精确的图像集提供给用户。实验结果表明,该系统可以在较短的时间内达到很高的检索精度。Effective image searching in WWW have become important to various users, and the image meta-search engine is an effective technique to improve the quality of retrieval results of web images on the Internet. The emphasis of the thesis is to propose a model of image-meta search engines, and a vectorization method is adopted to apply HACM （hierarchical agglomerative clustering methods）clustering techniques on images search that are then optimized by a specially designed genetic algorithm. The method provides a more significant and restricted set of images as the final result for a user＇ s search on an image-meta search engine. Some experiments have been run on to test the image-meta search engine. The method enables the image meta-search engine to handle a query term in a reasonably short time and return the results with high accuracy.

关 键 词：图像检索 搜索引擎 聚类算法 遗传算法 适应度函数 

分 类 号：TP393.09[自动化与计算机技术—计算机应用技术]