一种改进的SUSAN兴趣点检测算法  

An Improved SUSAN Interesting Point Detection

作　　者：郭峰[1] 韩溟[1] 王道平[1] 

机构地区：[1]第二炮兵工程学院,陕西西安710025

出　　处：《现代电子技术》2011年第10期5-7,共3页Modern Electronics Technique

基　　金：第二炮兵工程学院创新性探索研究基金(XY2009JJB07)

摘　　要：兴趣点是图像中重要的几何特征,兴趣点的准确检测对于图像处理具有重要意义。为了优化SUSAN算法,提高算法的有效性,对SUSAN兴趣点检测算法中阈值的确定提出了改进。在图像每个像素的SUSAN模板中首先计算阈值t的初值,在利用迭代法获得终值,使其在各种不同的对比度下仍能正确检测兴趣点。实验结果证明了该方法的有效性。Interesting point is an important geometrical feature of image. The exact interesting point detection is vital image processing. To improve efficiency and optimize SUSAN arithmetic, an improved way of determining the threshold SUSAN operator is proposed. The initial value of threshold was calculated in every single SUSAN template. The final value threshold was obtained using iterative segment. This way made it possible to pick up the right interesting point in all kinds gray contrast. The experimental result based on this method is proved to be feasible.

关 键 词：SUSAN算法 兴趣点检测 迭代 自适应 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]