VisionQuest: Facial Emotion Recognition 🎭

📌 Overview

VisionQuest is a Computer Vision application designed to recognize human emotions from facial images. Using a Convolutional Neural Network (CNN) built with PyTorch, the model processes images and classifies them into one of seven universal emotions.

This project explores the end-to-end pipeline of a Deep Learning project: from data preprocessing and augmentation to model training, evaluation, and real-time inference.

🎯 Objectives

• To build a robust CNN architecture capable of feature extraction from facial images.
• To handle class imbalances in emotion datasets (e.g., distinguishing 'Fear' vs 'Surprise').
• To implement detailed evaluation metrics (F1-Score, Confusion Matrix) beyond simple accuracy.

🧠 Model & Dataset

The Emotions: The model is trained to recognize the following classes:

1. Angry 😡
2. Disgust 🤢
3. Fear 😱
4. Happy 😀
5. Neutral 😐
6. Sad 😢
7. Surprise 😲

Tech Stack:

• Core: Python 3.10
• Deep Learning: PyTorch, Torchvision
• Data Handling: Pandas, NumPy
• Visualization: Matplotlib, Seaborn
• Metrics: Scikit-Learn

📂 Project Structure# Emotion-detector