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

Suggested Binarization Speed Up? #4

Open
GantMan opened this issue Dec 11, 2020 · 7 comments
Open

Suggested Binarization Speed Up? #4

GantMan opened this issue Dec 11, 2020 · 7 comments

Comments

@GantMan
Copy link

GantMan commented Dec 11, 2020

What do you think of this code for binarizing using tensors rather than JavaScript?

https://bit.ly/37a3bzm

@henrmota
Copy link

henrmota commented Dec 24, 2020

Also you can use tf.conv2d to apply the boxblur or gaussianfilter. By the way, amazing project :). One thing that I think that tensorflow doesn't receive enough credit it's image processing. An alternative way would be using something like webgl shaders, also a valid but more complicated approach.

https://codepen.io/henrmota/pen/yLazEGq?editors=0010

@GantMan
Copy link
Author

GantMan commented Dec 24, 2020

WOW! I didn't know a lot of this stuff. Great work!

@henrmota
Copy link

Yes tensorflow is great for image processing. It doesn't receive enough appreciation for it.

@GantMan
Copy link
Author

GantMan commented Dec 24, 2020

@henrmota - I have some questions about what you wrote. Let me know if you'd be willing to chat TFJS sometime. I'm on Twitter and I have a lot of slacks/discords for TFJS, but few people at our level.

@henrmota
Copy link

@henrmota
Copy link

@GantMan Hough line detection using tfjs. https://codepen.io/henrmota/pen/yLazEGq?editors=0010

@GantMan
Copy link
Author

GantMan commented Dec 26, 2020

This is some epic stuff! Connected with you on linkedin and twitter.

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