A downloadable tool for Windows

This project is a Real-Time Facial Expression Recognition system that uses a custom-trained YOLO model (via `ultralytics`) to detect and classify human emotions through a webcam feed. It also tracks the duration of each expression and generates an emotion timeline graph once the session ends.

🌟 Features

Real-Time Detection: Uses OpenCV to capture the live webcam feed and performs high-speed object detection and classification using a YOLO model.

9 Facial Expressions Supported:

  • Angry 😡
  • Happy 😊
  • Surprised 😲
  • Sad 😢
  • Sleepy 😴
  • Natural 😐
  • Contempt 😒
  • Disgust 🤢
  • Fear 😨

Emotion Timeline Analysis: Once you exit the video feed, the application uses `matplotlib` to plot a visually appealing timeline, showing exactly when and for how long each emotion was detected during the session.

More information
StatusReleased
CategoryTool
PlatformsWindows
AuthorFrankkie
Tagssourcecode
AI DisclosureAI Assisted, Code

Download

Download
Facial_Expression_Recognition.zip 66 MB

Install instructions

⚙️ Requirements

Make sure you have Python installed. It is recommended to use a virtual environment. You can install the required packages using the provided `requirements.txt` file.

The core dependencies include:

  • ultralytics (YOLO)
  • opencv-python
  • matplotlib
  • numpy
  • torch, torchvision, torchaudio (with CUDA 12.1 support for GPU acceleration)

To install them, run:

pip install -r requirements.txt
Note: The `requirements.txt` file is configured to download PyTorch with CUDA 12.1 support. If you are using CPU only or a different CUDA version, you may need to install PyTorch manually from the [official site](https://pytorch.org/).

🚀 How to Run

  1. Clone or download the repository to your local machine.
  2. Ensure your webcam is connected.
  3. Run the main application script:
python app.py

Leave a comment

Log in with itch.io to leave a comment.