본문 바로가기
AI/Computer Vision Materials

2.0 Image Filtering

by 쵸빙 2020. 8. 3.

In this class, we will learn about 'Image 'Filtering'.

 

 

 

 

 

 

● Image

What is an image?

image

 

An image is an array of numbers.

 

Color images is made up of 3 colors, Red, Green, Blue.

And actual intensity values per pixel is 0-255.

 

● 2D function

It is helpful to think of an image as a 2D function.

So, what is the range of f(x)?

For example, 8-bit image would have 256 values.

 

 

Filtering, Warping

What kind of image transformations can we perform?

As you see in the image above, filtering changes the pixel values.

And Warping changes the pixel location.

 

To implement those image transformation, some function calculation is needed.

In filtering case, we should change the range of image.

In warping case, we should change the domain of image.

 

 

kind of image filtering

So, what kind of image filtering can we perform?

Point operation, which processes point, can be possible.

Neighborhood operation, which uses filtering, can also be possible.

 

 

examples of poing processing

The pictures above are examples of Point Processing.

 

 

Filtering

The pictures above are the examples of filtering.

 

 

Next time, we will look Point Processing in detail.

'AI > Computer Vision Materials' 카테고리의 다른 글

2.2 Box Filter  (0) 2020.08.03
2.1 Point Processing  (0) 2020.08.03
1.2 Application of computer vision  (0) 2020.07.31
1.1 What is Computer Vision?  (0) 2020.07.31
8.X TF-IDF  (0) 2020.07.31