Description

This project aims to analyze high volume emotional videos and images to recognize human facial expression and/or emotion using deep learning methods. The emotional videos and images are collected from the literature (such as UvA-NEMO [1], Cohn-Kanade [2], AFEW [3], MMI [4], and/or MAHNOB [5]). Initially, Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) were applied to distinguish between posed and genuine smile from UvA-NEMO smile database, and 3D Mesh model and CNN were applied to recognize emotion from Cohn-Kanade (CK and CK+) database. In this connection, more experiments are needed to develop high performing models for recognizing or classifying human emotions and/or facial expressions from the emotional videos and images.

[1] https://www.uva-nemo.org/

[2] http://www.consortium.ri.cmu.edu/ckagree/

[3] https://cs.anu.edu.au/few/AFEW.html

[4] https://mmifacedb.eu/

[5] https://mahnob-db.eu/