Emotion Detection using Deep Learning
- 0 Collaborators
This project demonstrates the use of Deep Learning to detect emotion (sad, angry, happy etc) from the images of faces. ...learn more
Project status: Under Development
Intel Technologies
Intel Python
Overview / Usage
This project can be used for video analytics. It uses computer vision techniques to automatically detect emotion from the images of faces.
Methodology / Approach
The dataset suffers from the problem of class imbalance. And there is a significant amount of label noise present in the dataset.
I tackled the first problem using weighted categorical cross-entropy loss and I am yet to deal with the second one.
Technologies Used
-
TensorFlow
-
Google Colab
Repository
https://github.com/sayakpaul/Emotion-Detection-using-Deep-Learning