SIFT算法特征点提取的改进  

Improved Feature Selection of SIFT Algorithm

作　　者：殷妍[1] YIN Yan （Institute of the Computer Science and Technology, R.enai College of Tianjin University, Tianjin 301636, China）

机构地区：[1]天津大学仁爱学院计算机科学与技术系,天津301636

出　　处：《电脑知识与技术》2012年第3期1609-1610,共2页Computer Knowledge and Technology

摘　　要：SIFT特征点匹配算法是目前图像特征匹配研究领域的一个热点。该匹配效率高，可以处理图像之间发生平移等的变化的匹配。对不同角度拍摄的图像也具备稳定的特征点匹配效率。因此通过参数的变化对SIFT算法的原理进行了研究以及改进，并用图片、运算时间等数据说明该算法的有效性。SIFT features matching algorithm is a hot issue in the field of computer science. It has a high efficiency to match that it can be dealt with the match when the images are in translation, for any angle shot images it still has a stable feature matching efficiency. Therefore the principle of SIFT algorithms has been studied and improved by changing the parameters. The pictures and data such as the running times are used to prove its efficiency.

关 键 词：图像配准 SIFT算法 MATLAB 

分 类 号：TP393[自动化与计算机技术—计算机应用技术;自动化与计算机技术—计算机科学与技术]