In this class, we will learn about Gaussian Filter.
● Gaussian Filter
A Gaussian kernel gives less weight to pixels further from the center of the window.
This 3 x 3 kernel is an approximation of a 2D Gaussian function.
● Difference between Gaussian filter and Box Filtering
Box Filtering makes the image smaller.
● Shadow Effect
We can create shadow effect by overlaying Gaussiann blur image and original image.
● Soft Focus Effect
Soft Focus Effect is possible by blending Gaussian blurred image and the original image by half.
● Tilt Shift Effect
Tilt Shift Effect is the use of camera movements that change the orientation or position of the lens with respect to the film or image sensor on cameras.
We focus on important objects, showing them clearly and blur the others.
Tilt Shift Effect is also possible using Gaussian blur.
Next class, we will learn about Image Subsampling.
'AI > Computer Vision Materials' 카테고리의 다른 글
3.1 Image Pyramid (0) | 2020.08.03 |
---|---|
3.0 Image Subsampling (0) | 2020.08.03 |
2.2 Box Filter (0) | 2020.08.03 |
2.1 Point Processing (0) | 2020.08.03 |
2.0 Image Filtering (0) | 2020.08.03 |