Skip to content

gnurt2041/Facial-Emotion

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

23 Commits
 
 
 
 
 
 
 
 

Repository files navigation

Facial Emotion Detection using CNN

The objective of the project is to detect facial expression using image dataset. Convolutional Neural Network is used to classify the images. The output class consists of 7 different types namely angry, disgust, fear, happy, neutral, sad, surprise.

Dataset Information

The training archive contains 7 different type of human emotions

Dataset link: https://www.kaggle.com/datasets/aadityasinghal/facial-expression-dataset

Environment: Google Colab

The directory structure:

Facial-Emotions-Detection/
	├── train/
        ├── train/
        │   ├── angry/
        │   ├── disgust/
        │       ├── Training_10371709.jpg
        │       ├── Training_10598340.jpg
        │   ├── :
        │   ├── surprise/ 
        └── test/
main/
	└── facial_emotions_detection.ipynb

Libraries

  • pandas
  • numpy
  • matplotlib
  • seaborn
  • keras
  • tensorflow
  • scikit-learn
  • japanize-matplotlib

    Neural Network

  • CNN Architecture

    Result

    Accuracy: ~63.2%