Skip to content
/ pegbis Public

Python implementation of "Efficient Graph-Based Image Segmentation" paper

Notifications You must be signed in to change notification settings

salaee/pegbis

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

PEGBIS (Python Efficient Graph-Based Image Segmentation)

Python implementation of "Efficient Graph-Based Image Segmentation" paper written by P. Felzenszwalb, D. Huttenlocher. The paper is available: https://cs.brown.edu/~pff/papers/seg-ijcv.pdf
C++ implementation is written by the author and is available on: https://cs.brown.edu/~pff/segment/
The C++ implementation is much more faster than python implementation (obviously).

Results

parameters: (Sigma=0.5, K=300, Min=50)
alt text
parameters: (Sigma=0.5, K=300, Min=50)
alt text
parameters: (Sigma=0.5, K=1000, Min=50)
alt text
parameters: (Sigma=0.8, K=500, Min=10)
alt text
parameters: (Sigma=0.5, K=500, Min=50)
alt text

Requirements

Python 3.5

Libraries used:

scipy and matplotlib

About

Python implementation of "Efficient Graph-Based Image Segmentation" paper

Topics

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages