Skip to content

sumitbehal/Image-Completion

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 

Repository files navigation

Image-Completion

In this project, I used some tactics over RGB values of various pixels to detect the black spots on the video. First, video was broken down into frames and then solving the problem for every frame. Goal was to complete the image and removing black square from various frames and then merge them again to form a the new video. Check out some of the frames which have been corrected down below:

frame1 new1

frame15 new15

frame54 new54

PS: 1.I have used plenty of for loops, if you think you can contribute to reduce them! Project is open for contribution and this will improve the code quality! 2. You can apply this tactic to solve simple images like this. This model will brutally fail if used in facial images. Reason: Since I have used average RGB of the surroundings, so it works on simple images like sky or any forest etc.

https://www.kaggle.com/general/99432

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published