摘要
主要研究了采用一种新的基于局部反射变换原理来对图像进行配准处理。针对传统的图像配准算法效率和精度较低,提出了一种新的快速简便的图形局部放射变换不变性特性的关键点筛选和配准算法。算法首先利用尺度不变特征转换算法(SIFT)提取图像中的关键点,然后在关键点附近区域构造三角形区域,并根据仿射不变性原理,计算各三角形区域相对面积;以此相对面积的比例来确定最终的关键点并对其进行配准操作,方法简单高效。实验结果表明,提出的方法能快速地筛选图像中的关键点,并在保证准确性的前提下,获得尽可能多的关键点,充分保证了最终图像配准操作的准确性。
This paper presented a method to classify tentative feature matches as inliers or outliers to a transformation model. It was well known that ratios of areas of corresponding shapes were affine invariants. This algorithm used consistency of ratios of areas in pairs of images to classify matches as inliers or outliers. The method selected four matches within a region, and generated all possible corresponding triangles. It classified all matches as inliers or outliers based on the variance among the ratio of areas of the triangles. Used the selected inliers to compute a homography transformation. Experimental results show significant improvements over the baseline RANSAC algorithm for pairs of images in the database.
出处
《计算机应用研究》
CSCD
北大核心
2012年第3期1198-1200,共3页
Application Research of Computers
基金
国家自然科学基金资助项目(61063046)
关键词
形状匹配
局部反射
关键点提取
尺度不变特征转换
shape matching
local reflex
key point extract
scale invariant feature transform
