基于向量相似度匹配准则的图像配准与拼接  

Image Registration and Mosaic Based on Vector Similarity Matching Principle

作　　者：秦佳[1,2] 杨建峰[1] 薛彬[1] 卜凡[1,2] 

机构地区：[1]中国科学院西安光学精密机械研究所光谱成像技术重点实验室,陕西西安710119 [2]中国科学院研究生院,北京100049

出　　处：《微电子学与计算机》2013年第6期22-25,共4页Microelectronics & Computer

基　　金：国家自然科学基金资助项目(60808028)

摘　　要：针对图像配准与拼接中存在的特征点误匹配问题,提出了基于向量相似度的特征匹配准则.首先在尺度空间检测SIFT(Scale Invariant Feature Transformation)特征点,生成包含特征点信息的SIFT向量.采用向量相似度方法进行特征点匹配,并通过互映射原理进一步筛选,删除误匹配点对.然后用随机抽样一致性算法计算初始投影变换矩阵,并用Levenberg-Marquardt(L-M)算法对矩阵求精.最后通过图像融合实现了图像拼接.实验结果表明该准则提高了特征点匹配精度,能处理存在投影变换的图像配准与拼接.To resolve the mismatching problem in image registration and image mosaic, this paper proposes animproved feature matching principle based on vector similarity. First, by detecting feature points in scale space, SIFT （Scale Invariant Feature Transformation） vectors, which represent local properties, are computed; the featurepoints are matched by using vector similarity method and mismatching point couples are further deleted with the application of mutual mapping theory. And then, the transform matrix is calculated by random sample consensus algorithm. Furthermore, it is optimized by Lenvenberg-Marquardt （L-M） algorithm. Finally, through imagefusion, image mosaic is realized. The experimental results indicate new principle improves the matching precision. The method can deal with image registration and mosaic with projective transformation.

关 键 词：图像拼接 特征匹配 尺度不变特征变换 向量相似度 互映射原理 

分 类 号：TP751[自动化与计算机技术—检测技术与自动化装置]