https://github.com/pathak-ashutosh/eye-blink-detection
Detect eye blinks based on eye aspect ratio (EAR) introduced by Soukupová and Čech in their 2016 paper, Real-Time Eye Blink Detection Using Facial Landmarks.
https://github.com/pathak-ashutosh/eye-blink-detection
blink-detection-algorithm computer-vision deep-learning eye-detection eye-tracking hog machine-learning svm
Last synced: 6 months ago
JSON representation
Detect eye blinks based on eye aspect ratio (EAR) introduced by Soukupová and Čech in their 2016 paper, Real-Time Eye Blink Detection Using Facial Landmarks.
- Host: GitHub
- URL: https://github.com/pathak-ashutosh/eye-blink-detection
- Owner: pathak-ashutosh
- License: mit
- Created: 2018-08-25T18:35:46.000Z (about 7 years ago)
- Default Branch: master
- Last Pushed: 2019-07-16T13:20:23.000Z (about 6 years ago)
- Last Synced: 2025-04-23T11:57:40.057Z (6 months ago)
- Topics: blink-detection-algorithm, computer-vision, deep-learning, eye-detection, eye-tracking, hog, machine-learning, svm
- Language: Python
- Homepage:
- Size: 72.2 MB
- Stars: 66
- Watchers: 2
- Forks: 28
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Eye-blink-detection
This project has been completed by help from [pyimagesearch.com](pyimagesearch.com)
### Eye blink detection using dlib and OpenCV
#### What is eye aspect ratio (EAR)?
From the last project - Detecting facial landmarks - we know that we can apply facial landmark detection to localize important regions of the face, including eyes, eyebrows, nose, ears, and mouth. This also implies that we can extract specific facial structures by knowing the indexes of the particular face parts. In terms of blink detection, we are only interested in two sets of facial structures — the eyes.
### How to run:
Download or clone this repository on your local device and run the following command in the terminal while being in the Eye-blink-detection folder - `python detect_blinks.py`. If there's any package/module missing, you can easily install them using the `pip` command.