尺度不变特征变换算子综述  

Summarization of the scale invariant feature transform

作　　者：刘立[1,2] 詹茵茵[1] 罗扬[1] 刘朝晖[1] 彭复员[2] 

机构地区：[1]南华大学计算机科学与技术学院,衡阳421001 [2]华中科技大学电信系,武汉430076

出　　处：《中国图象图形学报》2013年第8期885-892,共8页Journal of Image and Graphics

基　　金：国家自然科学基金项目(60475024;60872076);航天技术创新基金项目(2006AA09Z203);湖南省科技计划(2010GK3012)

摘　　要：随着计算机软件与硬件技术的发展,计算机视觉算法逐渐成为图像处理领域的研究热点。其中SIFT(scale invariant feature transform)算法是目前机器视觉领域应用最成功的算法之一。由于在尺度不变、旋转不变、光照不变等方面的独特优势,SIFT被广大视觉领域的研究者借鉴与学习。但是SIFT算法本身也存在一些问题,如仿射性能不太理想,计算复杂度过高等,因此针对它的多种改进算法不断出现。本文对SIFT的发展历史、SIFT算法的演变以及它不同领域的典型应用给出了一个比较全面的综述,比较了各类算法的优缺点。最后给出了该算法未来可能的发展方向,为视觉研究者提供参考。With the development of software and hardware technique, computer vision has become a hot research fields in image processing. Scale invariant feature transform （SIFT） is one of the most successful vision algorithm nowadays and it is widely studied by the computer vision community because of its unique features.SIFT is scale invariant, rotation invariant and illumination invariant. However, it also has some problems such as it is only part affine has a rather the high computation complexity. Many extended or modified algorithms of the SIFT are developed unceasingly. In this paper, we summarize the history, the evolved processing, and the application of the SIFT and compares those algorithm effects. At last, the paper discusses the feature direction and provides reference for computer vision researchers.

关 键 词：尺度不变 SIFT 计算机视觉 图像匹配 

分 类 号：TP301.6[自动化与计算机技术—计算机系统结构]