基于ASIFT的医学图像配准算法  

Medical Image Registration Algorithm Based on ASIFT

作　　者：阚峻岭[1] 谷宗运[1] 殷云霞[1] 杜春敏[1] 

机构地区：[1]安徽中医学院医药信息工程学院,安徽合肥230031

出　　处：《安庆师范学院学报（自然科学版）》2013年第1期38-41,47,共5页Journal of Anqing Teachers College(Natural Science Edition)

基　　金：安徽省高等学校省级优秀青年人才基金项目(2012SQRL102)资助

摘　　要：对ASIFT算法的原理进行了分析,针对医学图像配准鲁棒性强、准确性高和低耗时率的要求,设计出基于ASIFT的医学图像配准算法。该算法首先通过ASIFT算法提取图像特征点,接着用欧式距离筛选出匹配的特征点,最后实现参考图像与浮动图像之间的配准。该算法较好地解决了其他同类型算法中存在的提取的特征点数量少、特征点匹配的精确度不高、不能对扭曲变形的仿射图像配准等问题。实验结果表明,该算法不仅提高了配准的精确度和准确性,也提高了配准的稳定性和可靠性。This paper analyzes the principle of ASIFT algorithm. For medical image registration of high robustness, high accuracy and low consumption rate, this paper proposes a medical image registration algorithm based on ASIFT. This algorithm extracts feature points from images by the ASIFT algorithm, then matches the feature points by the Euclidean distance, and achieves the medical image registration between two images at last. The algorithm effectively deals with the problems such as less feature points collected, inaccuracy matching appeared in feature points, being incapable to registration on distorted affine image, etc. , which exist in other algorithms. The experimental result verifies that the algorithm not only improves the registration accuracy and precision, but also enhances the stability and reliability of the registration.

关 键 词：医学图像配准 特征点 特征提取 特征匹配 ASIFT SIFT 

分 类 号：R319[医药卫生—基础医学] TP391.41[自动化与计算机技术—计算机应用技术]