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

Can you provide codes for generating ground truth edge map? #2

Open
tyjcbzd opened this issue Nov 23, 2023 · 8 comments
Open

Can you provide codes for generating ground truth edge map? #2

tyjcbzd opened this issue Nov 23, 2023 · 8 comments

Comments

@tyjcbzd
Copy link

tyjcbzd commented Nov 23, 2023

I use inner package in open-cv to generate ground truth edge map, below is the code:
edges = cv2.Canny(image, threshold1=100, threshold2=200)
Do you also use this to generate the edge map, if so, what thresholds did you use, if not, can you pls provide the algorithm? Thanksssss!

@yike5022
Copy link

yike5022 commented Jan 3, 2024

Do you apply canny calculations to the original image of the training?

@taozh2017
Copy link
Owner

Do you apply canny calculations to the original image of the training?

Yes. Edge maps have been put into the training dataset.

@yike5022
Copy link

yike5022 commented Jan 4, 2024

Hello, do you also use the Canny algorithm on the polyp dataset? Because the polyp boundary map I generated is very strange.

@taozh2017
Copy link
Owner

Yes. I use the Canny algorithm.

@yike5022
Copy link

yike5022 commented Jan 5, 2024

How to choose the parameters of the Canny algorithm? I mean threshold1 and threshold2.

@yike5022
Copy link

Hello, have you tried to save the boundary map?

@taozh2017
Copy link
Owner

How to choose the parameters of the Canny algorithm? I mean threshold1 and threshold2.

Do not need to set a threshold, just use Matlab edge detection code. You can email me and we can discuss conveniently.

@yike5022
Copy link

Hello, what is your email address?

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

3 participants