/Facial-features-from-video

A modular pipeline to extract several facial features from videos such as face landmarks, eye gaze direction, head pose and Action Units

Primary LanguagePython

GSOC 2018 Project

Devendra Pratap Yadav, 2014csb1010@iitrpr.ac.in

Organization :

Red Hen Lab
Cognitive Vision lab, University of Bremen
Mentors - Dr. Mehul Bhatt, Jakob Suchan, Sri Krishna

Video Processing Pipeline

This project contains a modular pipeline to extract several facial features from videos such as face landmarks, eye gaze direction, head pose and Action Units. Each module in the pipeline extracts a specific facial feature for each face detected in the video frame. These features can be used to obtain information about a person's facial expressions, facial movements, gaze and emotions. The video_processing_pipeline folder contains code and detailed documentation for the project.
This work is part of a larger project which aims to use multimodal features to detect and characterize emotion in videos.