基于分块图像颜色特征的图像排序算法  

Image Sorting Algorithm Based on Color Features of Segmented Images

作　　者：冷鹏飞 马晓珂 Leng Pengfei;Ma Xiaoke(School of Computer and Information Engineering, Henan University, Kaifeng Henan 475004, Chin)

机构地区：[1]河南大学计算机与信息工程学院,河南开封475004

出　　处：《信息与电脑》2018年第10期30-33,共4页Information & Computer

摘　　要：针对序列图像三维重建算法,在处理拍摄角度相差非常小的图像时,传统的基于图像颜色直方图的相似性度量方法计算不准确。对于以上问题,提出了基于分块图像颜色特征的图像排序算法。先将原始图像等分成若干块,接下来分别统计每块图像的颜色直方图特征,再计算各对应块颜色直方图距离,通过归一化算法得到整幅图像的相似度,最后根据相似度大小进行排序。实验结果表明,改进算法可以更好计算出图像的相似性并进行排序。For 3 D reconstruction of sequence images, the traditional method of similarity measurement based on color histogram is inaccurate when processing images with very small difference in shooting angle. For these problems, an image sorting algorithm based on color features of block images is proposed. First, the original image is divided into several blocks, then the color histogram features of each image are calculated respectively, then the color histogram distance of each corresponding block is calculated, and the similarity degree of the whole image is obtained by the normalization algorithm. Finally, the similarity is sorted according to the size of the similarity. Experimental results show that the improved algorithm can better calculate the similarity of images and sort them.

关 键 词：三维重建 颜色直方图 相似性度量 图像排序 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]