Emotion Detection using Convolutional Neural Network

Overview

This repository contains Python code for building and training a Convolutional Neural Network (CNN) for emotion detection. The model is trained on a dataset consisting of facial images representing different emotions.

Dataset

The dataset is structured with separate folders for each emotion category. Each folder contains images corresponding to that emotion.

Folder Structure

• angry/
• disgusted/
• fearful/
• happy/
• neutral/
• sad/
• surprised/

Model Architecture

The CNN model consists of multiple convolutional layers, batch normalization, activation functions, and fully connected layers. It is compiled using the Adam optimizer and categorical crossentropy loss.

Training and Evaluation

The model is trained using data augmentation on the training set and evaluated on a separate testing set. Training history, including loss and accuracy over epochs, is visualized using matplotlib.

Clone the repository:

https://github.com/swapnilpawar24/Emotion-detection-.git

Datasets :

The dataset contain 35,685 examples of 48x48 pixel gray scale images of faces divided into train and test dataset. Images are categorized based on the emotion shown in the facial expressions (happiness, neutral, sadness, anger, surprise, disgust, fear).
Dataset link

Author

Swapnil Pawar