基于改进K-means算法的图像检索方法  

Novel image retrieval method based on improved K -means algorithm

作　　者：吕明磊[1] 刘冬梅[1] 曾智勇[1] 

机构地区：[1]福建师范大学软件学院,福州350108

出　　处：《计算机应用》2013年第A01期195-198,共4页journal of Computer Applications

基　　金：福建省自然科学基金资助项目(2011J01338)

摘　　要：分析了基于K-means聚类算法在图像检索中的缺点,提出了一种基于改进K-means算法的图像检索方法。它首先计算图像特征库里面所有颜色直方图之间的距离,把距离最大的两个特征向量作为前两个初始类心,在剩余的向量中查找到类心的距离之和最大的特征向量作为下一个初始类心,直到查找到全部初始类心,然后依据初始类心进行聚类,最后进行图像检索。实验结果表明,本算法具有较高的检索准确率。Having analyzed the drawbacks of image retrieval based on K -means algorithm, a novel image retrieval method based on improved K -means algorithm was presented in this paper. Firstly, computed the distance of every two color histograms of all color histograms in the image feature database. Then, took the two feature vectors which the distance between them is the maximum in the database, as the first two initial centroids, and found all correct initial centroids, and clustered according to the initial class centroids. Finally, started image retrieval. Experimental results demonstrate that the proposed method is efficient.

关 键 词：聚类 K-MEANS算法 颜色直方图 图像检索 特征提取 

分 类 号：TP391.413[自动化与计算机技术—计算机应用技术]