基于改进Canny算子与图像形态学融合的边缘检测方法

Image edge detection based on improved Canny operator and image morphology

传统Canny算法采用高斯滤波会造成图像的过度光滑,容易导致缓变边缘的丢失,而且梯度幅值的计算方法没有充分考虑到3×3邻域内周围像素对中心像素的影响。针对上述存在的问题与不足,结合小波融合技术的优势,提出了一种基于改进Canny算子与图像形态学融合的边缘检测方法,利用改进的Canny算子和图像形态学分别对图像进行边缘检测,然后应用小波融合技术把两种方法检测出来的边缘进行图像融合,得到最终的图像边缘。仿真结果表明,该算法具有较好的抗噪能力,有效地提高了边缘检测的准确性和完整性。

The traditional Canny algorithm uses the gaussian filter,however the gaussian filter will create the image excessively smoothly,moreover easy to create the loss of the edges which change slowly.Moreover,in the traditional Canny operator the computational method of gradient magnitude has not considered the influence of pixels around on the central pixel in the 3×3 neighborhood.In view of the above existence＇s problem and the insufficiency,with the superiority of wavelet fusion technology,this article proposes a method for image edge detection based on the image fusion of improved Canny operator and image morphology.The method applies the improved Canny operator and the image morphology separately to make the image edge detection,then does image fusion of the two results that produced by those two detecting method using the wavelet fusion technology to obtain the final edge-image.The results of simulation show that the algorithm has better anti-noise ability and enhances the accuracy and the integrity of edge detection effectively.