Skip to content

The implementation was based on both the original research paper and the implementation paper of the GrabCut algorithm. The algorithm was manually implemented, without resorting to extended libraries like OpenCV. The only Python libraries employed were those aimed at optimizing computational efficiency, such as Numpy.

Notifications You must be signed in to change notification settings

tal101d/Grabcut-and-Possion-Blending-in-Python

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Utilizing multiple Python libraries was part of the process, although the execution itself was manual rather than relying on library functions like OpenCV.

The approach taken for implementation was guided by the content of the original research paper, alongside another paper detailing the application of the GrabCut algorithm.

Incorporated within the project are datasets intended for testing purposes, along with reference data that serves as the ground truth for evaluating the performance of GrabCut. Additionally, an implementation for assessing accuracy and Jaccard index in relation to the ground truth is included.

About

The implementation was based on both the original research paper and the implementation paper of the GrabCut algorithm. The algorithm was manually implemented, without resorting to extended libraries like OpenCV. The only Python libraries employed were those aimed at optimizing computational efficiency, such as Numpy.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages