摘要
将直线插补运算与六边形图像结构相结合,提出了一种简单高效的边缘检测方法.先用高斯滤波器对图像进行滤波,再使用Sobel算子进行边缘检测,最后按给定阈值对边缘进行精确提取,经过这3个步骤完成图像的边缘检测.通过实验验证了六边形图像结构的Canny边缘检测算法比常见的Canny边缘检测方法更精确、更能抑制噪声;而且直线插补运算在图像边缘检测中具有较快的计算速度,比非线性插补计算效率高.
A simple edge detection method with high efficiency was presented by using linear interpolation algorithms that combined with the hexagonal image structure achieved encouraging and promising edge detection performance.The edge detection approach went through three steps： noise filtering using a Gaussian filter,edge detection using Sobel operator and edge refining using thresholds.The result,show that hexagonal structure leads to more accurate and less noise edge maps compared with the Canny edge detector.And linear interpolation results in more efficient edge detection than bi-linear and tri-linear interpolation algorithms.
出处
《湖南科技大学学报（自然科学版）》
CAS
北大核心
2010年第4期47-50,共4页
Journal of Hunan University of Science And Technology：Natural Science Edition
基金
国家自然科学基金资助(60572048)
关键词
边缘检测
六边形结构
图像内插
高斯滤波器
edge detection
hexagonal structure
image interpolation
Gaussian filtering
