改进k-means聚类算法在图像检索中的应用研究

Application study of improved k-means clustering algorithm in image retrieval

为了从大规模图像数据库中快速而准确地检索到所需图像,提出了一种结合图像特征索引库和平均面积直方图的方法。通过图像特征索引库减少对图像数据库的访问次数和访问数据量,实现对图像的快速检索。使用平均面积直方图方法,增强算法区分空间差异的能力,使得检索结果与人的视觉感受更加吻合。实验结果亦表明,该方法提高了图像检索的速度和精度。

In order to quickly and correctly retrieve the desired image from a large image database,a method combining the image feature index library and the average area histogram is presented.Adopting the image feature index database,it can reduce the number of visiting to the image database,and achieve fast retrieval.Using the average size histogram,it enhances the ability of distinguishing the spatial differences,which makes the search results better matching the human visual experi-ence.The experimental results also show that the proposed method improves the speed and accuracy of image retrieval.