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

Face Detection Cleanup and Options #92

Merged
merged 5 commits into from
Apr 29, 2017
Merged

Face Detection Cleanup and Options #92

merged 5 commits into from
Apr 29, 2017

Conversation

kylemcdonald
Copy link
Contributor

Hi Audun, thanks again for this great library!

I noticed that the way jsfeat face detection is done can create some problems. For example: lots of initializations of small faces, or initialization of faces in areas with no details.

I grabbed the most recent jsfeat haar demo and rewrote jsfeat-detect.js to match it. This fixes the small initializations by using a small working canvas for doing the detection. I also added more parameters (all inside the params.faceDetection object) which allows the ability to turn on canny edge detection for face detection, which reduces initialization of faces in areas with no details. These options also close #89 by allowing the user to limit the size of faces that are detected.

Finally, I also updated jsfeat and added a note to the readme about the development environment.

Thanks!

@auduno auduno merged commit 65eb77f into auduno:dev Apr 29, 2017
@auduno
Copy link
Owner

auduno commented Apr 29, 2017

Sorry about the delay, finally got around to merging this!

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

Successfully merging this pull request may close these issues.

Configuration option for minimum/maximum face size
2 participants