Skip to content

developedbyjerry/Face-Detection-and-Recognition-with-Mary-Kom_Applied-AI-Lab-Deep-Learning-for-Computer-Vision

Repository files navigation

Applied-AI-Lab-Deep-Learning-for-Computer-Vision

WorldQuant University

👤 Face Detection and Recognition with Mary Kom 🥊

🌟 Project Overview

The project aims to teach you how to perform face detection and recognition tasks using a video of an interview with Indian Olympic boxer Mary Kom. 🎥 You'll leverage a state-of-the-art pre-trained Multi-task Cascaded Convolutional Network (MTCNN) model combined with the Inception-ResNet model to achieve accurate face recognition. 🧠
The goal is to extract selected video frames of Mary Kom and her interviewer, create face embeddings for each of them, and use these embeddings to detect their faces in new images. 🖼️ Finally, you'll wrap your code into a Flask app that allows users to upload an image and perform face recognition. 🌐

Key Components:

  1. Pre-trained Models:

    • MTCNN (Multi-task Cascaded Convolutional Network): Used for detecting face bounding boxes and cropping faces from images.
    • Inception-ResNet: Used to create face embeddings for face recognition tasks.
  2. Face Embeddings:

    • Extract face embeddings for Mary Kom and her interviewer using selected video frames.
    • Create a library of known face embeddings to facilitate face recognition.
  3. Recognition Tasks:

    • Detect faces in new images by comparing them with the library of known faces.
    • Determine if an image contains a face that matches the known face embeddings.
  4. Application Development:

    • Build a Flask app to allow users to upload images and perform face recognition tasks through a user-friendly interface.

Skills and Knowledge Gained:

  • 🤖 How to use pre-trained MTCNN and Inception-ResNet V1 models from facenet_pytorch
  • 📦 How to obtain face bounding boxes and cropped faces using MTCNN
  • 🧬 How to create face embeddings using Inception-ResNet
  • 📚 How to construct a library of known face embeddings
  • 🔍 How to determine if an image contains a face from the library of known faces
  • 🚀 How to build and deploy a Flask app for face recognition

This project is a fantastic opportunity to explore advanced computer vision techniques and to harness the power of state-of-the-art models and build a practical seamless application for face recognition! 👩‍💻✨


About

No description, website, or topics provided.

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published

Languages