MTCNN_face_detection_alignment is an implementation of the “Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networks” algorithm. The algorithm uses a cascade of three convolutional networks (P-Net, R-Net, O-Net) to jointly detect faces (bounding boxes) and align facial landmarks in a coarse-to-fine manner, leveraging multi-task learning. Non-maximum suppression and bounding box regression at each stage. The repository includes Caffe / MATLAB code, support scripts, and instructions for dependencies. Non-maximum suppression and bounding box regression at each stage. Online hard sample mining to improve training robustness.
Features
- Joint detection + alignment in a cascaded three-stage network
- Online hard sample mining to improve training robustness
- Non-maximum suppression and bounding box regression at each stage
- Support for landmark localization (e.g. eyes, nose, mouth)
- Support code for both Linux and Windows Caffe backends
- Flexible deployment (MATLAB / Caffe)
Categories
Computer Vision LibrariesLicense
MIT LicenseFollow MTCNN Face Detection Alignment
Other Useful Business Software
Our Free Plans just got better! | Auth0
You asked, we delivered! Auth0 is excited to expand our Free and Paid plans to include more options so you can focus on building, deploying, and scaling applications without having to worry about your security. Auth0 now, thank yourself later.
Rate This Project
Login To Rate This Project
User Reviews
Be the first to post a review of MTCNN Face Detection Alignment!