https://github.com/thisisashukla/face-tracker
Face tracker to detect and analyze lack of attention using facial features.
https://github.com/thisisashukla/face-tracker
computer-vision facial-landmarks tensorflowjs-models
Last synced: 6 months ago
JSON representation
Face tracker to detect and analyze lack of attention using facial features.
- Host: GitHub
- URL: https://github.com/thisisashukla/face-tracker
- Owner: thisisashukla
- Created: 2021-01-09T10:21:34.000Z (over 4 years ago)
- Default Branch: main
- Last Pushed: 2021-01-11T11:21:09.000Z (over 4 years ago)
- Last Synced: 2025-03-26T16:39:08.377Z (7 months ago)
- Topics: computer-vision, facial-landmarks, tensorflowjs-models
- Language: JavaScript
- Homepage: https://thisisashukla.github.io/face-tracker/
- Size: 3.76 MB
- Stars: 6
- Watchers: 1
- Forks: 4
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Face Tracker
This repository contains the code for demonstrating different use cases which leverage facial landmark keypoints. The facial landmark model is a Tf-Js implementation of the [paper](https://arxiv.org/pdf/1907.06724.pdf).
## Drowsy Alarm
Using the keypoint [map](./mesh_map.jpg) we can calculate the distance between keypoints of facial part such as eyelids (upper and lower) and lips (upper and lower) and put a threshold on this distance to identify when the person is drowsing off. A moving average smoothing can reduce noise.