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

New filters: Noise, grayscale and oily skin detection #65

Open
wants to merge 7 commits into
base: new_filters
Choose a base branch
from

Conversation

shigabeev
Copy link

@shigabeev shigabeev commented Aug 1, 2024

Changes:

  • Changed deepface to RetinaFace face detector. Why? Pytorch, GPU support.
  • Added Noise and grain detection filter. I have to refactor model weights somehow though.
  • Added Grayscale detection filter. It detects if image is grayscale even if it has 3 dimensions and was compressed.
  • Added Oily skin detection filter. Useful for portrait images.

Feel free to leave comments for refactoring. If you want a faster communication channel, ping me in telegram.

Usage:


focus_filter = FaceFocusFilter(threshold=2000.0,
                                detect_face=True,
                                workers=1,
                                batch_size=1)
noise_filter = NoiseEstimationFilter(model_path='noise_estimator_model.joblib',
                                    params_path='feature_params.joblib',
                                    workers=4,
                                    batch_size=4)
grayscale_filter = GrayscaleFilter(workers=1,
                                batch_size=1)
oily_skin_filter = OilySkinFilter(workers=1,
                                batch_size=16,
                                 model_name="dima806/skin_types_image_detection")

@shigabeev shigabeev changed the title New filters New filters: Noise, grayscale and oily skin detection Aug 1, 2024
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.

1 participant