针对传统Canny算子在进行边缘检测时存在抗噪声干扰能力较差、假边缘较多以及边缘模糊等问题,提出了一种基于Canny算子的改进型图像边缘提取算法,弥补了传统算法在边缘检测中的不足.该算法采用双边滤波代替高斯滤波,能够减少边缘丢失;增加2个方向的梯度幅值,能够保留更多的真实边缘;对图像进行Curvelet变换,可增强图像的细节.试验结果表明,该算法检测出的边缘更加真实和清晰,同时抗干扰能力较强,与传统Canny算子相比具有明显的优势.%In view of the problems of poor anti-noise ability, more false and blurred edge when the traditional Canny operator is used in image edge detection, an improved image edge extraction algorithm based on Canny operator is proposed, which makes up for the shortcomings of the traditional algorithm in edge detection.The algorithm uses bilateral filtering instead of Gaussian filtering, which can reduce the edge loss and increase the gradient of two directions to retain more real edges.The Curvelet transform is applied to the image, to enhance the details of the image.The experimental results show that the edges detected by this algorithm are more realistic and clear, and the antinoise ability is stronger, which has obvious advantages over the traditional Canny operator.
展开▼
