一种改进的六边形结构的Canny边缘检测算法  

An improved algorithm of Canny edge detection of a hexagonal structure

作　　者：李海华[1] 齐红敏[1] 万亮亮[1] 

机构地区：[1]华中科技大学文华学院,湖北武汉430074

出　　处：《光学仪器》2011年第1期19-23,共5页Optical Instruments

摘　　要：在图像处理过程中,为了获取更精确的边缘轮廓,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,经过这三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。To get the more accurate edge maps of an image in the course of image processing, a simple edge detection method with high efficiency has been presented with combining the linear interpolation algorithms with the hexagonal image structure. The edge detection approach goes through three steps： noise filtering using a Gaussian filter, edge detection using Sobel operator and edge refining using thresholds. Through the experiment, we have shown that hexagonal structure leads to more accurate and less noise edge maps compared with the Canny edge detector. And using of linear interpolation results in more efficient edge detection than nonlinear interpolation algorithms.

关 键 词：边缘检测 六边形结构 图像内插 高斯滤波器 

分 类 号：TN911.73[电子电信—通信与信息系统]