Open
Conversation
|
Hey @goigle Thanks for the PR! We are looking into this 😄 |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Currently, the points for the 5 landmark dlib model are wrong. The range uses 1 point for each eye, when it should be two points. The range for dlib 68 for the eyes are 36-42 (6 pts) and 42-48 (6pts). For dlib 5, it's 0-1 (1pt) and 2-3 (1pt) respectively. Changing the range to 0-2 and 2-4 correctly gives 2 pts for each eye and allows properly calculating the centerpoint of the eye.
This fix makes the face aligner work identically for both dlib models, like intended:
Here's a chart showing the proper indexes for dlib's 5 and 68 face landmark models