基于八方向Sobel算子的边缘检测算法

Edge Detection Algorithm Based on the Eight Directions Sobel Operator

针对传统图像边缘检测方法检测效果不理想的问题,提出一种基于八方向Sobel算子的边缘检测算法。采用0°、22.5°、45°、67.5°、90°、112.5°、135°、157.5°8个方向的模板进行检测,能较好地检测出不同方向的边缘。在检测过程中,考虑到邻域内像素到中心像素距离不同,对中心像素的贡献不同,算法根据该像素到中心像素欧氏距离对邻域内像素进行加权,使得距中心像素越近,其权值越大。实验表明,算法检测出的图像边缘较为完整,轮廓线清晰且连续性较好。

An edge detection algorithm based on eight directions sobel operator is proposed for the problem that traditional edge detection method＇ s result is not satisfactory. The algorithm based on eight templates of 0°, 22. 5°, 45°, 67. 5°, 90°, 112. 5°, 135° and 157.5° different directions is used to detect edges better in different directions. In the detection process, we take into account that the distance of neighborhood pixel to the center pixel is different, the contribution of the neighborhood pixel to the center pixel is different. This algorithm weights the neighborhood pixel according to the EueIidean of it to the center pixel. We let the pixel nearer to the center pixel has greater weight, The experimental results show that the new algorithm can detect the image edge relatively complete, with clear contours and better continuity.