Skip to content

This is our work for the course project of Medical Image Computing (MIC). Idea is to segment image in two classes using ideas of st graph cuts. For maxflow-min cut we have used the standard Boykov-Kolmogorov algorithm combined with super-pixelisation for image segmentation.

License

Notifications You must be signed in to change notification settings

Xi-Meng/Image-Segmentation-using-ST-cuts

 
 

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

20 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

Project Description:

Advanced algorithm design and analysis course assignment The idea of maximum flow and minimum cut set is used to segment the image

Dependencies:

require python 3.8

All dependencies are enlisted in requirements.txt

pip install -r requirements.txt	

Note:

Extension need not be png

Runtime Commands

fast_seg.py The main code used to produce the segmentation results. command-line arguments

  1. -i / --img : -i
  2. -a / --algo : values “bk”/”ff”
  • “bk” - used to perform segmentation using boykov kolmogorov algorithm
  • “ff” - used to perform segmentation using ford fulkerson algorithm

Example: python fast_seg.py -i ./images/bunny.png -a bk

Instructions

The Marking process can be roughly marked, only need to draw some lines.

  • Press the "o" key on your keyboard to start marking an object.
  • Press the "b" key on your keyboard to start marking the background.
  • When you have finished marking, press the esc key on your keyboard.

Results

alt text

alt text

About

This is our work for the course project of Medical Image Computing (MIC). Idea is to segment image in two classes using ideas of st graph cuts. For maxflow-min cut we have used the standard Boykov-Kolmogorov algorithm combined with super-pixelisation for image segmentation.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages

  • Python 100.0%