🎭 Real-Time Facial Emotion Detection System

A real-time Facial Emotion Detection system built using OpenCV and TensorFlow/Keras.
The system detects faces from a webcam feed and predicts human emotions using a CNN model trained on the FER-2013 dataset.

This project is suitable for Machine Learning mini projects, final year projects, and face attendance systems with emotion analysis.

📌 Features

• Real-time webcam emotion detection
• Face detection using Haar Cascade
• Emotion recognition using a pretrained CNN (Mini-Xception)
• Supports 7 emotions:
• Angry
• Disgust
• Fear
• Happy
• Sad
• Surprise
• Neutral
• Works on CPU (no GPU required)
• Lightweight and fast

🧠 Model Used

• Mini-Xception CNN
• Trained on FER-2013 dataset
• Input size: 64 × 64 grayscale face images
• Framework: TensorFlow + Keras

⚠️ Note: Real-time emotion recognition accuracy depends on lighting, face orientation, and expression intensity.

🛠️ Technologies Used

• Python 3.10
• TensorFlow / Keras
• OpenCV
• NumPy

📂 Project Structure