基于融合图像特征的角点提取方法

基于图像边缘的角点提取往往对噪音敏感,提取精度较高但运算量大,而基于图像灰度的角点提取易于实现但提取效果不佳.因此提出一种融合图像边缘特征和图像灰度特征的角点检测方法.首先在一较低尺度用Canny算法求出所有边缘点,然后求出每一边缘点的曲率值并求出初始角点集,利用Harris算法通过实验在一较优尺度下对初始角点进行筛选并确定最终的角点集合.所提方法融合图像角点提取的两大特征,可以有效改进在单一特征提取下的不足.通过对比实验,该算法明显地提高了图像角点检测性能.

Corner Detection Based on Integrating Image Feature

Corner detection based on edge is often sensitive to noise.It has high precision,but complicated computation.The corner detection based on pray-level is easy to be carried out,but the obtained results are lower-qulified.This paper presents an algorithm,in which edge feature and gray-level feature are combined for corner detection.Canny is used to find out all the edge points at a low scale,then to find the value of the curvature of each edge point,and finally to derive the initial set of corner points.Harris is used to test corner points of initial and determine the final set of corners.Intergrating two image features,the algorithm proposed in this paper can effectively avoid the drawbacks under a single feature detection.Compared with Harris algorithm,the presented algorithm is more efficient in detecting the corners with accurate location.