Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/aymen016/emotion-recognition-using-face-detection
A deep learning-based project that detects human faces and predicts their emotions in real-time using OpenCV and a trained neural network model.
https://github.com/aymen016/emotion-recognition-using-face-detection
gpu-acceleration haar-cascade-classifier keras-tensorflow matplotlib numpy opencv python
Last synced: about 2 months ago
JSON representation
A deep learning-based project that detects human faces and predicts their emotions in real-time using OpenCV and a trained neural network model.
- Host: GitHub
- URL: https://github.com/aymen016/emotion-recognition-using-face-detection
- Owner: Aymen016
- Created: 2024-11-26T21:15:53.000Z (about 2 months ago)
- Default Branch: main
- Last Pushed: 2024-11-26T21:24:36.000Z (about 2 months ago)
- Last Synced: 2024-11-26T22:27:20.324Z (about 2 months ago)
- Topics: gpu-acceleration, haar-cascade-classifier, keras-tensorflow, matplotlib, numpy, opencv, python
- Homepage:
- Size: 1.95 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Emotion Recognition Using Face Detection 🎭🤖
**A deep learning-based project for recognizing emotions through facial expressions in real-time! This project leverages OpenCV for face detection and a trained deep learning model for emotion classification. Perfect for exploring AI applications in human emotion analysis!**
---
## 🚀 Features
- **Real-Time Face Detection**: Detect faces from a live webcam feed using OpenCV's Haar Cascade Classifier.
- **Emotion Prediction**: Recognize emotions such as Happy, Sad, Angry, Neutral, and more using a trained convolutional neural network (CNN).
- **Efficient Preprocessing**: Grayscale conversion, normalization, and resizing for optimal model input.
- **Interactive Output**: Display detected faces and their predicted emotions directly on the webcam feed.
---
## 📂 Repository Structure
```bash
Emotion-Recognition-Using-Face-Detection/
├── model_file.h5 # Trained model file
├── haarcascade_frontalface_default.xml # Haar Cascade file for face detection
├── train_model.ipynb # Jupyter Notebook for training the emotion recognition model
├── real_time_emotion.py # Main Python script for real-time emotion recognition
├── requirements.txt # Dependencies for the project
├── README.md # Project documentation
└── images/ # Sample images or screenshots of the application
```
---
## 🛠️ Tools and Technologies
- **Programming Language**: Python 🐍
- **Deep Learning Framework**: TensorFlow/Keras
- **Computer Vision Library**: OpenCV
- **Numerical Computing**: NumPy
- **Visualization**: Matplotlib (optional)
- **Face Detection**: Haar Cascade Classifier
---
## 💻 Installation and Setup
1. **Clone the Repository**:
```bash
git clone https://github.com/yourusername/Emotion-Recognition-Using-Face-Detection.git
cd Emotion-Recognition-Using-Face-Detection
2. **Install Dependencies**:
Install the required libraries using pip:
```bash
pip install -r requirements.txt
3. **Download Haar Cascade File**:
Ensure the `haarcascade_frontalface_default.xml` file is in the project directory. If not, download it from the [OpenCV GitHub repository] (https://github.com/opencv/opencv/tree/master/data/haarcascades).
4. **Run the Application**:
Start the real-time emotion recognition script:
```bash
python real_time_emotion.py
```
---
### 📊 Model Overview
The emotion recognition model is a Convolutional Neural Network (CNN) trained on a dataset of facial expressions. It processes grayscale images resized to 48x48 pixels for efficient and accurate emotion classification.
**Predicted Emotions:**
- Happy 😊
- Sad 😢
- Angry 😡
- Neutral 😐
- Surprise 😲
#### Model Accuracy:
The model achieves an accuracy of **67%** on the FER-2013 test dataset. While this provides a solid foundation for recognizing emotions from facial expressions, there's room for improvement. We aim to fine-tune the model for better real-world performance.
---
### 🎯 Future Enhancements
- **Add More Emotions**: Train the model to recognize additional emotions like Fear, Disgust, etc.
- **Improve Accuracy**: Fine-tune the model for better real-world performance.
- **Multi-Face Detection**: Extend the application to predict emotions for multiple faces simultaneously.
- **Web Integration**: Create a web-based interface for wider accessibility.
---
### 🧠 Dataset Used
The model was trained using the **FER-2013** dataset, which contains labeled facial expressions.
[Learn more about the dataset here](https://www.kaggle.com/datasets/msambare/fer2013).
---
### 📸 Demo
Real-Time Emotion Detection in Action
> The image taken:
> After emotion detection:
---
### 🤝 Contributions
Contributions are welcome! Feel free to fork the repository and submit pull requests with improvements, bug fixes, or new features.