dlib-face-recognition-cv
| Crates.io | dlib-face-recognition-cv |
| lib.rs | dlib-face-recognition-cv |
| version | 0.1.0 |
| source | src |
| created_at | 2020-05-29 18:32:14.953003 |
| updated_at | 2020-05-29 18:32:14.953003 |
| description | Unofficial Rust wrappers to the C++ library dlib, face recognition tools |
| homepage | https://github.com/podo-os |
| repository | https://github.com/podo-os/dlib-face-recognition |
| max_upload_size | |
| id | 247449 |
| size | 2,752 |
Ho Kim (kerryeon)
documentation
README
dlib-face-recognition
Inspired by a similar python library,
dlib-face-recognition is a Rust library that binds to certain specific features of the dlib C++ library.
These include:
- An FHOG-based face detector.
- A CNN-based face detector (slower, but more powerful).
- A face landmark predictor for identifying specific landmarks (eyes, nose, etc) from face rectangles.
- A face encoding neural network for generating 128 dimensional face encodings that can be compared via their euclidean distances.
Original Working
The original working is here.
Building
dlib-face-recognition requires dlib to be installed.
on (at least) OSX, I believe lapack and openblas also need to be installed.
dlib-face-recognition includes a embed-all feature flag that can be used with cargo build --features embed-all.
This will automatically download the face predictor, cnn face detector and face encoding neural network models (the fhog face detector is included in dlib and does not need to be downloaded). Alternatively, these models can be downloaded manually:
- CNN Face Detector: http://dlib.net/files/shape_predictor_68_face_landmarks.dat.bz2
- Landmark Predictor: http://dlib.net/files/mmod_human_face_detector.dat.bz2
- Face Recognition Net: http://dlib.net/files/dlib_face_recognition_resnet_model_v1.dat.bz2
If this feature flag is enabled, the matching structs will have Default::default implementations provided that allows you to load them without having to worry about file locations.