Skip to content

Zhejiang University Course: Artificial Intelligence (19 Spring) Individual Project -- Image Restoration

Notifications You must be signed in to change notification settings

jessiepyx/image_restoration_AI_ZJU

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 

Repository files navigation

image_restoration_AI_ZJU

Zhejiang University Course: Artificial Intelligence (19 Spring) Individual Project -- Image Restoration.
Course website is here.

This project uses Python 3.6.

Discription

The task is to build regression models to reconstruct corrupted images. Input images are masked by random noise with specified noise rate.

I implemented two regression models:

  • Linear Model with Gassian Basis Function (and analysis by line, as specified in assignment instruction)
  • k-Nearest Neighbor Model (which performs better)

Results

0.8 noise (Corrupted/Gaussian Basis/kNN)

A A_gauss A kNN

0.4 noise (Corrupted/Gaussian Basis/kNN)

B B_gauss B kNN

0.6 noise (Corrupted/Gaussian Basis/kNN)

C C_gauss C kNN

0.7 noise (Original/Corrupted/Gaussian Basis/kNN)

car_ori car car_gauss car kNN

0.5 noise (Original/Corrupted/Gaussian Basis/kNN)

car_ori car car_gauss car kNN

About

Zhejiang University Course: Artificial Intelligence (19 Spring) Individual Project -- Image Restoration

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages