基于代表色不变矩的自适应匹配算法  

Adaptive matching algorithm based on representative color invariant moments

作　　者：马云飞 苏一飞 侯晰月 Ma Yunfei;Su Yifei;Hou Xiyue(Nanjing University of Science and Technology,Nanjing,Jiangsu 210094,China)

机构地区：[1]南京理工大学,江苏南京210094

出　　处：《计算机时代》2020年第9期1-3,6,共4页Computer Era

摘　　要：虽然Hu不变矩对于旋转等变换具有不变性,但其存在计算量过大、匹配速率慢等问题。文章介绍了一种首先搜索模板代表色,然后对代表色单独进行不变矩匹配的方法,并在匹配策略中引入变步长策略,进一步提高匹配效率。实验证明,所提出的算法不仅保持了不变矩的旋转不变性,而且相对于仅考虑灰度特征的不变矩匹配拥有更高的效率。Although Hu invariant moments are invariant to transformations such as rotation,problems exist such as large account of computation and low matching rate.This paper introduces a method of searching the representative colors of the template first and matching the representative colors individually with invariant moments.A variable step strategy is introduced into the matching strategy to further improve the matching efficiency.Experiments show that the algorithm proposed in this paper not only maintains the rotation invariance of invariant moments,but also has high efficiency compared with invariant moment matching which only considers gray scale features.

关 键 词：HU不变矩 HSV模型 图像匹配 变步长 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]