摘要
传统的Canny边缘检测算法采用的是高斯平滑,用来去除图像中的计算噪声,这种去噪方法虽然对抑制高斯噪声效果较好,但对脉冲噪声等的去除并不理想。针对这一问题,提出了用小波变换与中值滤波相结合的方法取代了传统的高斯滤波法,并对平滑后的图像作图像增强。实验表明,该方法有效地提高了边缘检测的准确性,得到了比较理想的边缘检测效果。
The conventional Canny algorithm for edge detection uses a Gaussian smoothing, and removes the image noise. Although there is a good effect in inhibition Gaussian noise, this denoising is not satisfactory in removal of impulse noise. To solve this problem, an improved edge detection algorithm was proposed by replacing Gaussian filter with wavelet transform and median filtering, and the image enhancement was carried out after smoothing. Experimental results show that the accuracy of edge detection is improved evidently, and a much better edge detection effect is obtained.
出处
《电脑开发与应用》
2010年第4期67-69,共3页
Computer Development & Applications
关键词
CANNY边缘检测
高斯平滑
小波变换
中值滤波
高斯滤波
Canny edge detection, Gaussian smoothing, wavelet transform, median filtering, Gaussian filter
