改进的特征点提取算法及其适应性评估  

Modified feature points extracting algorithm and it's adaptability evaluation

作　　者：李竹林[1,2] 赵红漫[3] 刘兴平[1] 赵宗涛[2] 

机构地区：[1]延安大学计算机学院,陕西延安716000 [2]第二炮兵工程学院402室,陕西西安710025 [3]北京二炮总医院,北京100084

出　　处：《计算机工程与设计》2009年第6期1441-1443,共3页Computer Engineering and Design

基　　金：国家自然科学基金项目(60272022)

摘　　要：改进了一种特征点提取算法[1]。提取图像的边缘轮廓线并以边缘线的几何重心为极点,对边缘极坐标化,形成幅角-极径曲线。再在该曲线上寻找局部最大与最小值点以得到特征点。改进后的算法既能获取曲线的凸点,也能获取其凹点,与原算法比较有了明显的改进。又分别在尺度、旋转及仿射变换情况下,对算法的适应性进行评估,实验结果表明,改进后的算法适应性较好,能达到79.1%。在实际应用中,二维边缘曲线实现基于特征点的自动输入及三维重建具有重要价值。A feature point extracting algorithm based onimage edge is modified. First, image edge outline is extracted. Second, geometric gravity center of edge outline is calculated. Third, argument-polar radius curve of polar coordinate system whose pole is geometric gravity is formed, and maximum and minimum value points are searched, they are feature points. Comparing the original algorithm, the modified algorithm can not only extract protruding points, but also concave points. In order to evaluate the quality of the algorithm, the stability of the algorithm in the case of scale transformation, rotation transformation and affine transformation is appraised. The result indicates that the algorithm is simple and its stability can reach 79.1%. In actual application, the algorithm has important value to auto-input of two-dimension curve based on feature points and three-dimension reconstruction.

关 键 词：特征点 几何重心 极坐标 适应性 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]