Laplacian of Gaussian (LoG)
2012-05-09 15:43
411 查看
As Laplace operator may detect edges as well as noise (isolated, out-of-range), it may be desirable to smooth the image first by convolution with a Gaussian kernel of width
to suppress the noise before using Laplace for edge detection:
The first equal sign is due to the fact that
So we can obtain the Laplacian of Gaussian
first and then convolve it with the input image. To do so, first consider
and
Note that for simplicity we omitted the normalizing coefficient
.
Similarly we can get
Now we have LoG as an operator or convolution kernel defined as
The Gaussian
and its first and second derivatives
and
are shown here:
This 2D LoG can be approximated by a 5 by 5 convolution kernel such as
The kernel of any other sizes can be obtained by approximating the continuous expression of LoG given above. However, make sure that the sum (or average) of all elements of the kernel has to be zero (similar to the Laplace kernel) so that the convolution
result of a homogeneous regions is always zero.
The edges in the image can be obtained by these steps:
Applying LoG to the image
Detection of zero-crossings in the image
Threshold the zero-crossings to keep only those strong ones (large difference between the positive maximum and the negative minimum)
The last step is needed to suppress the weak zero-crossings most likely caused by noise.
to suppress the noise before using Laplace for edge detection:
The first equal sign is due to the fact that
So we can obtain the Laplacian of Gaussian
first and then convolve it with the input image. To do so, first consider
and
Note that for simplicity we omitted the normalizing coefficient
.
Similarly we can get
Now we have LoG as an operator or convolution kernel defined as
The Gaussian
and its first and second derivatives
and
are shown here:
This 2D LoG can be approximated by a 5 by 5 convolution kernel such as
The kernel of any other sizes can be obtained by approximating the continuous expression of LoG given above. However, make sure that the sum (or average) of all elements of the kernel has to be zero (similar to the Laplace kernel) so that the convolution
result of a homogeneous regions is always zero.
The edges in the image can be obtained by these steps:
Applying LoG to the image
Detection of zero-crossings in the image
Threshold the zero-crossings to keep only those strong ones (large difference between the positive maximum and the negative minimum)
The last step is needed to suppress the weak zero-crossings most likely caused by noise.
相关文章推荐
- Laplacian of Gaussian (LoG)
- LOG-laplacian of Gaussian and DoG
- Laplacian of Gaussian (LoG)
- Laplacian of Gaussian (LoG)
- Laplacian of Gaussian (LoG)
- Laplacian of Gaussian (LoG)
- Laplacian of Gaussian (LoG)
- Laplacian of Gaussian (LoG)
- LOG-laplacian of Gaussian and DoG
- Laplacian of Gaussian (LOG)
- 边缘检测(6)Log(Laplacianof Gassian )算子
- 边缘检测(6)Log(Laplacianof Gassian )算子
- matlab laplacian of gaussian(拉普拉斯高斯) 图像滤波
- Laplacian of Gaussian
- 图的拉普拉斯矩阵学习-Laplacian Matrices of Graphs
- GANs学习系列(7): 拉普拉斯金字塔生成式对抗网络Laplacian Pyramid of Adversarial Networks
- 生成式对抗网络GAN研究进展(四)——Laplacian Pyramid of Adversarial Networks,LAPGAN
- 论文笔记之:Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks
- the principle of laplacian filter
- Image Processing --- Gaussian Pyramid & Laplacian Pyramid