基于改进Canny算子的图像边缘检测方法

Image edge detection method based on improved Canny operator

针对传统Canny边缘检测算法采用高斯滤波处理图像不能有效消除椒盐噪声的问题,提出改进Canny算子用于检测图像边缘。首先利用双滤波设计-融合自适应模糊中值滤波和双边滤波去除图像椒盐噪声,降低图像噪声同时保证图像边缘。然后在研究过程中遇到边缘检测人工阈值选取自适应不足的问题,采用最大类间方差(Otsu)算法计算得到高低阈值,提高边缘检测的自适应,最后使用哈夫检测法增强边缘。通过对比实验发现,改进Canny算法滤波后的图像质量,与传统Canny算法相比提升10%~19%,并保持了传统Canny算法特性,具有自适应能力强、去除干扰点能力强的优点,提取边缘更完整。

In view of the problem of traditional Canny edge detection algorithm, such as using Gaussian Filter to process images cannot effectively eliminate salt and pepper noise, an improved Canny operator was proposed to detect image edges. Firstly, the algorithm replaced Gaussian Filter with Adaptive Fuzzy Median Filter and Bilateral Filter to remove the salt and pepper noise.Then in the research process, we encountered the problem of poor self-adaptability. The Otsu algorithm is employed to obtain the high and low thresholds to improve the self-adaptability of edge detection. Finally, the Huff transform detection is used to enhance the edge. The experimental results show that image quality after improved Canny algorithm filtering is 10%~19% higher than the traditional Canny algorithm. The improved algorithm not only maintains the excellent performance of traditional Canny edge detection algorithm, but also have the advantages of strong self-adaptability and good removal effect of disturbance points.