Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/pkmandke/openface-pc
Openface Facenet CNN real-time PC implementation using external logitech webcam
https://github.com/pkmandke/openface-pc
Last synced: 6 days ago
JSON representation
Openface Facenet CNN real-time PC implementation using external logitech webcam
- Host: GitHub
- URL: https://github.com/pkmandke/openface-pc
- Owner: pkmandke
- Created: 2019-02-09T16:15:13.000Z (almost 6 years ago)
- Default Branch: master
- Last Pushed: 2019-03-27T14:21:43.000Z (almost 6 years ago)
- Last Synced: 2024-11-14T23:31:40.894Z (2 months ago)
- Language: Jupyter Notebook
- Size: 288 KB
- Stars: 0
- Watchers: 0
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Openface(Facenet CNN) real-time implementation
## Reference
The pre-trained model & it's associated pre-processing is credited to [the openface implementation](https://github.com/cmusatyalab/openface). Further, the Facenet CNN model architecture has been inspired by [this](https://arxiv.org/abs/1503.03832) paper by Schroff et al.
## What is in this repo?
This repository provides helper scripts that implement the openface CNN for real-time face recongition on a PC using an external webcam(Logitech) or laptops internal camera. The pre-trained CNN architecture used is the nn4.small2.v1 by [openface](https://github.com/cmusatyalab/openface).
The faces have been cropped and warped using an affine transform as is done in the original model by [openface](https://github.com/cmusatyalab/openface).Running main.py in /scripts starts the API for adding a new face and/or detecting a pre-trained face. The path/s to the pre-trained CNN and the face detection model by [dlib](http://dlib.net/) need to be added manually in the main.py file as the right varibales.
# Author
[Prathamesh Mandke](https://www.linkedin.com/in/prathamesh-mandke-866866168/)