#516 · Primary category： Computer Vision
DeepAlignmentNetwork
A deep neural network for face alignment
Project last updated：04/23/23
GitHub Stars
511
Forks
137
Contributors
2
License
MIT
Why we included this project
For anyone working through the CVPR 2017 DAN paper or rebuilding facial landmark detection from scratch, this is a faithful reference implementation. The network localizes keypoints like eye and mouth corners in still images and video, and the repo ships a live webcam demo plus evaluation scripts that reproduce the 300W benchmark results. It is a research codebase, though: it targets Python 2.7 and depends on Theano and Lasagne, and the supplied models are licensed for research use only. Teams willing to port it to a current framework still get a compact grounding in how cascaded face alignment works, which makes it a handy baseline for comparing against modern methods.
Articles for this project
No articles for this project yet.
To suggest a topic or contribute an article, contact us.
Related projects in this category
opencv
Open Source Computer Vision Library
RuView
π RuView turns commodity WiFi signals into real-time spatial intelligence, vital sign monitoring, and presence detection — all without a single pixel of video.
PaddleOCR
Turn any PDF or image document into structured data for your AI. A powerful, lightweight OCR toolkit that bridges the gap between images/PDFs and LLMs. Supports 100+ languages.
MinerU
Transforms complex documents like PDFs and Office docs into LLM-ready markdown/JSON for your Agentic workflows.
tesseract
Tesseract Open Source OCR Engine (main repository)