用直方图面积法进行图像相似度计算

Image Similarity Computation by Using Histogram Method

颜色直方图图像检索方法是一种重要的基于颜色特征图像检索方法。本文从颜色直方图相似的本质出发,定义直方图之间灰阶概率的重合面积作为图像之间的相似度,相似度的取值范围介于[0,1],这样图像相似度的含义更为明确,并通过计算多组遥感影像之间的相似度印证该方法的有效性。试验结果表明,该方法比信息熵方法计算图像之间的相似度更加有效,具有更强的稳健性,是一个切实可行的图像相似度计算方法。

Color histogram image retrieval,which is based on the color character,is a very effective image retrieval method.In this paper,image similarity is defined as the intersectant area between two gray level probability histograms.It ranges from 0 to 1.This concept is more specific to describe the image similarity.Some groups of remotely sensed data's image similarities are computed to test whether this method is valid or not.The result shows that this method can discriminate the images from each other easily,which is more effective than the information entropy method to compute image similarity.As a whale,it is a feasible method.