Face Landmarks Detection

This is a deep learning project that aims to detect facial landmarks in images using PyTorch. The model is based on the ResNet-18 architecture and is trained on the iBUG 300W Large Face Landmark Dataset.

Table of Contents

• Introduction
• Requirements
• Installation
• Dataset
• Usage
• Acknowledgements
• License

Introduction

Facial landmarks detection is an important task in computer vision and has various applications, including face recognition, emotion analysis, and facial expression synthesis. In this project, we use a deep learning model based on the ResNet-18 architecture to accurately predict 68 facial landmarks in an image.

Requirements

• Python 3.x
• PyTorch
• torchvision
• NumPy
• Matplotlib
• OpenCV

Installation

To install the required libraries, run the following command:

pip install torch torchvision numpy matplotlib opencv-python

Dataset

The iBUG 300W Large Face Landmark Dataset contains images of faces along with their corresponding ground-truth facial landmarks annotations. The dataset is used for both training and testing the model.

You can download the dataset from the following link: iBUG 300W Large Face Landmark Dataset

Usage

To use the model for facial landmarks detection, you can follow these steps:

1. Clone this repository to your local machine.
2. Download the iBUG 300W Large Face Landmark Dataset and place it in the data directory.
3. Install the required libraries using the installation instructions above.

Acknowledgements

I would like to thank the authors of the iBUG 300W Large Face Landmark Dataset for providing the valuable dataset for this project.

License

This project is licensed under the MIT License - see the LICENSE file for details.