Table of Contents

• About the Project
• Key Features and Objectives
• Know more about me!

About the Project

PTdTu Object Detection is a project focused on developing an object detection model entirely from the ground up. This project leverages original data and meticulous annotation efforts using Labelmg to create a custom object detection solution.

Key Features and Objectives

• Custom Dataset: PTdTu Object Detection utilizes a custom dataset curated from scratch. All data, including images and annotations, have been collected and processed meticulously to ensure quality and relevance.

• Target Classes: The object detection model is designed to identify four distinct classes:
  1. My Face: Detects the presence of my face within images.
  2. Thumbs Up: Recognizes the thumbs-up gesture.
  3. Thumbs Down: Identifies the thumbs-down gesture.
  4. Peace Sign: Detects the peace sign gesture.
• Machine Learning Framework: TensorFlow is the chosen framework for developing the object detection model. Specifically, the model is built upon the Single Shot MultiBox Detector (SSD) architecture, employing MobileNetV2 as the base model and utilizing Feature Pyramid Network (FPN) for enhanced performance.

For more detailed insights into the project, including code explanations, setup instructions, and a step-by-step guide to replicate the process, stay tuned! Comprehensive documentation providing a deeper understanding of how the project works and how to undertake similar endeavors will be available soon. If you have any questions, need further assistance, or want to collaborate, please don’t hesitate to reach out. Feel free to contact me at any time, and I’ll be happy to assist you.

Know more about me!

linkedin: linkedin.com/in/mhamidasn
github: github.com/mhamidasn

Check my other project here!

🌌Here's to pushing boundaries, unraveling mysteries, and creating a future woven with the threads of innovation🌌