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

use focuspoint with face detection library #7

Closed
gion opened this issue Sep 3, 2014 · 4 comments
Closed

use focuspoint with face detection library #7

gion opened this issue Sep 3, 2014 · 4 comments
Labels

Comments

@gion
Copy link
Contributor

gion commented Sep 3, 2014

Have you thought about using this lib along with some other face detection libraries out there?
There is nude.js, jquery.facedetection and many others libraries and algorithms exist that can be used to detect the most important part of an image.
I think it would be a nice experiment/feature to use focuspoint to automatically focus to an important part of an image.
I personally had issues with "half shown faces" on certain resolutions on some of my projects, and I think that this combo might be a good solution.

@jonom
Copy link
Owner

jonom commented Sep 3, 2014

No I hadn't thought of that but that is a great idea. Nude.js seems to only detect nudity... but I can imagine how it could be used with FocusPoint on certain websites. Lol.

If you experiment with combining these different libraries please let me know how it goes.

Another approach would be to do face/subject detection server side on images and cache the result, then you can produce appropriate markup for your images based on this. The advantage of this is you don't have to wait client side for the image to be fully loaded and then analysed before it is positioned.

@gion
Copy link
Contributor Author

gion commented Sep 3, 2014

I will try to experiment something when I have some spair time.
I think that the backened approach might save some time with caching and all, but I like the ideea of computing things on the client on the fly. Imagine you want to pull images from a public 3rd party feed. I would be a bit nasty to proxy each image request.
Hmm.. I'm going to think about it :))

Anyway, 👍 for the ideea behind this plugin

@ethanclevenger91
Copy link

Did anyone ever build something doing this successfully? It seems the coordinates you pass to focuspoint are a bit different than what facedetection spits out, but I'm sure translating probably isn't all that complicated.

@jonom
Copy link
Owner

jonom commented Mar 1, 2016

Closing this for now as it shouldn't be necessary to modify this plugin to add this feature, devs could use a face detection library of their choice to calculate coords and pass them through to FocusPoint. Note that v2 (in development) uses a different grid system so may be more compatible.

Willing to include an example of above if anyone wants to contribute one.

@jonom jonom closed this as completed Mar 1, 2016
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
Projects
None yet
Development

No branches or pull requests

3 participants