Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Evaluate the accuracy of stitching algorithms #207

Open
niovl opened this issue Dec 13, 2023 · 4 comments
Open

Evaluate the accuracy of stitching algorithms #207

niovl opened this issue Dec 13, 2023 · 4 comments

Comments

@niovl
Copy link

niovl commented Dec 13, 2023

image
Hi, I'm working on a process for evaluating the accuracy of stitching algorithms. I'd like to know the details of your code implementation. Can you provide it?

@jmuhlich
Copy link
Collaborator

We received the MATLAB code for stitching accuracy directly from the MIST authors upon request. They said they would release the code on GitHub but that was years ago and I don't think it has happened yet. The code has a public domain license so I should be free to share it, but I want to check with the MIST team first. I did start to reimplement the code in Python but I never fully verified it: https://github.com/jmuhlich/mist_evaluation

The separate code I wrote myself for the registration accuracy evaluation (figure 5b/d/f, figure 6, and figures S1-S6) is here, if you think it would be of any use: https://github.com/jmuhlich/ashlar-paper-figures

@jmuhlich
Copy link
Collaborator

The data files needed for the stitching accuracy evaluation are available here: https://isg.nist.gov/deepzoomweb/data/referenceimagestitchingdata

@niovl
Copy link
Author

niovl commented Feb 19, 2024

The data files needed for the stitching accuracy evaluation are available here: https://isg.nist.gov/deepzoomweb/data/referenceimagestitchingdata

I found it too, thanks for reconfirming

@niovl
Copy link
Author

niovl commented Feb 19, 2024

We received the MATLAB code for stitching accuracy directly from the MIST authors upon request. They said they would release the code on GitHub but that was years ago and I don't think it has happened yet. The code has a public domain license so I should be free to share it, but I want to check with the MIST team first. I did start to reimplement the code in Python but I never fully verified it: https://github.com/jmuhlich/mist_evaluation

The separate code I wrote myself for the registration accuracy evaluation (figure 5b/d/f, figure 6, and figures S1-S6) is here, if you think it would be of any use: https://github.com/jmuhlich/ashlar-paper-figures

Thank you very much, these materials are helpful for my research. At the same time, I also got a share from MIST authors.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants