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.
出处
《微电子学与计算机》
CSCD
北大核心
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)
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
image mosaic
feature matching
scale invariant feature transformation
vector similarity~ mutualmapping theory
