基于交互式遗传算法和粗糙集的图像检索方法  

Approach to image retrieval based on interactive genetic algorithm and rough set

作　　者：邹木春[1] 

机构地区：[1]江西省宜春学院数学与计算机学院,江西宜春336000

出　　处：《计算机工程与设计》2007年第9期2086-2088,共3页Computer Engineering and Design

摘　　要：针对如何在图像检索系统中客观地表达用户的感知,提出了一种基于粗糙集和遗传算法的相关反馈图像检索方法。采用粗糙集的方法求出图像的最简视觉特征子集,采用交互式遗传算法,对每一次反馈得到的候选图像集进行评价,利用遗传算子从图像库中选出接近用户需求的图像。实验表明该方法能有效的提高检索效率,是一种更为理想的检索方法。Aimed at presenting objectively the perspectives of users in the system of image retrieval, an image retrieval method of relevant feedback based on rough set and genetic algorithms is proposed. Firstly, the method of rough set is adopted to calculate the simplest visual feature subset of images, then interactive genetic algorithms is used to evaluate the candidate image sets which are gained by every feedback, finally, inheriting operator is used to select precisely the approximately qualified images from the library of images. Additionally, experiments explicitly manifest that the novel approach is a more ideal retrieve method and the speed of image retrieval greatly is enhanced.

关 键 词：图像检索 相关反馈 视觉特征 粗糙集 约简 交互式遗传算法 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]