边缘颜色匹配算法在计算机拼图中的应用  

Image matching algorithm based on edge color used in computer jigsaw puzzle

作　　者：支玲玲[1] 葛庆平[1] 姬照中[1] 

机构地区：[1]首都师范大学信息工程学院,北京100048

出　　处：《计算机工程与设计》2010年第16期3705-3707,3711,共4页Computer Engineering and Design

基　　金：国家自然科学基金项目(10603009);北京市教委基金项目(KM200710028018)

摘　　要：对于计算机自动拼图中的颜色匹配问题,由于全局直方图不包含颜色的空间分布信息,不同的图像可能具有相同的颜色直方图。为弥补该缺点,提出了应用图像的边缘颜色信息进行匹配的方法。该算法先进行边缘提取,然后以每个边缘点为中心,选取一个适当区域,计算直方图,利用直方图相交法进行特征的匹配。实验结果表明,与传统的直方图相交方法相比,在进行图像匹配时合理利用图像的边缘特征可有效的提高匹配性能。Aimed at the problem of color matching in automatic computer jigsaw puzzle,spatial distribution of color information is not included in global histogram,so different images may have the same histogram.To solve the problem,an algorithm combining the edge and color feature is introduced.Firstly,the extraction method of edge features is given,then select an appropriate regional around the edge point to calculate the histogram.Histogram intersection algorithm is used to match the pieces.Experiments show that the algorithm can match the puzzle pieces effectively,indicated that this algorithm is better than the traditional global histogram algorithm.And it can conclude that combining the edge and color feature properly improve the match performance.

关 键 词：计算机自动拼图 颜色直方图 图像匹配 边缘提取 HIS颜色空间 

分 类 号：TP391.4[自动化与计算机技术—计算机应用技术]