基于快速鲁棒互相关算法的图像拼接系统  

Image Matching System Based on Fast Robust Correlation Method

作　　者：李馨迟[1] 马森[1] 陈芳民[1] 付明[1] 尚媛园[1] 

机构地区：[1]首都师范大学信息工程学院,北京100048

出　　处：《首都师范大学学报（自然科学版）》2009年第S1期7-10,共4页Journal of Capital Normal University：Natural Science Edition

摘　　要：本文介绍了一种全新、快速、顽健(鲁棒)、遍历的图像拼接算法——快速鲁棒互相关算法.该方法利用图像间的互相关性进行鲁棒配准.它利用快速傅里叶变换在频域范围内分析处理速度、时间耗费量等指标,因此具有运算迅捷的特点.特别是在匹配大尺寸图片时,快速鲁棒互相关算法的运算速度与传统互相关算法相比具有明显的优势,是直接鲁棒匹配算法运算速度的几千倍.A new,fast,robust,exhaustive,image-matching technique is presented: fast robust correlation.Fast robust correlation works by expressing a robust matching surface as a series of correlations.Speed is obtained by computing correlations in the frequency domain by FFT.Computational cost is analyzed and the method is shown to be fast.Speed is comparable to conventional correlation and,for large images,thousands of times faster than direct robust matching.

关 键 词：鲁棒 图像拼接 快速傅里叶变换 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]