- Active Shape Model
- Active Appearance Model
- Constrained Local Model
Only achieve good results in controlled environments (frontal face and proper lightning).
- ERT: cascade based on gradient boosting. โ๏ธ
Paper: One Millisecond Face Alignment with an Ensemble of Regression Trees paper by Kazemi and Sullivan (2014).
In order to run ERT you should download the pretrained model from: https://www.pyimagesearch.com/2017/04/03/facial-landmarks-dlib-opencv-python/ in the "--shape-predictor" section and then extract the ".dat" file to the main folder.
- MultiTask Cascaded CNN:
- Dense Face Alignment
- Style Aggregated Network
- Look at Boundary
- Wing Loss
- PFLD
- AWing
- Geometry Aggregated Network
- Deep Adaptive Graph