【作者】 陈利军；

【导师】 吴成柯；

【作者基本信息】 西安电子科技大学 ， 通信与信息系统， 2005， 硕士

【摘要】 本文主要研究基于灰度图像的角点检测算法和图像的匹配算法。角点的信息含量很高，可以对视觉处理提供足够的约束，极大地提高运算速度，在图像之间进行可靠的匹配。这些特点使得角点检测在机器视觉和图像处理的许多方面都起着十分重要的作用。本文首先介绍了一些经典的自相关角点检测算法并分析了各算法的优缺点，并在最小亮度变化算法(MIC)的基础上提出了改进的MIC角点提取方法。实验结果证明该方法比改进前的MIC算法具有更好的效果。 计算机视觉和图像处理中另一个重要的研究内容是图像的匹配。它是许多计算机视觉应用的基础。本文对图像匹配算法进行了分类和比较，并详细介绍了一些经典的图像匹配方法，同时给出算法的匹配结果。更多还原

【Abstract】 Techniques on corner points detection based on gray-level image and image matching method are presented in this thesis.Corners are image points that show a strong intensity change. The detection of corner points in images is essential for many tasks such as machine vision , image processing. The reason that this approach is so popular that corner points have a rich content of information, provide a sufficient constraint to vision processing and a reliable match between images, have a greatly improvement on computation speed. This thesis describes some previous algorithms on auto-correlation corner points detection. Then the performance analysis of these algorithms are given. An improved approach is presented in this paper on the basis of MIC(Minimum Intensity Change) algorithm. Experimental results show that the proposed algorithm has a better performance than the original one.Image matching is another important content of computer vision and image processing. It has been applied to many computer vision tasks. This thesis has made a comparison and list of many image matching algorithms and introduced some classic image matching methods in a detail. Finally the results of image matching are given in a form of experiments.更多还原