The Flash Pack - Interview Task

A real-time facial orientation detector using MediaPipe and OpenCV that assesses if a person is looking directly at the camera by analyzing 3D facial landmarks and Euler angles. It calibrates to individual posture and camera setup, outputting the face's orientation status live.

Screenshots

Here are some screenshots demonstrating the app in action:

Getting Started

These instructions will get you a copy of the project up and running on your local machine for development and testing purposes.

Prerequisites

What things you need to install the software and how to install them:

• Python 3.9
• OpenCV
• MediaPipe
• Transforms3d

Setup

1. Clone the Repository

   git clone https://github.com/dan-yates1/flash-pack-task
   cd flash-pack-task

2. Create and Activate a Virtual Environment (Optional but recommended)

   python -m venv venv
   source venv/bin/activate  # On Windows, use `venv\Scripts\activate`

3. Install Dependencies

   pip install -r requirements.txt

4. Run Main

   python main.py

Built With

• OpenCV - The computer vision library used
• MediaPipe - Framework for building multimodal applied machine learning pipelines
• Transforms3D - Python library for 3D coordinate transformations

Acknowledgements

• Real-Time Head Pose Estimation FaceMesh with MediaPipe and OpenCV: A Comprehensive Guide - Used code for drawing coordinates
• Python Face Detection and Face Mesh (python OpenCV & MediaPipe package) - Support for setting up the project