AI PokerDetector

A custom built AI-powered poker assistant designed to detect cards in real time, calculate winning probabilities, and provide game insights using computer vision and machine learning.

Key Features

  • Real-time card detection from video feed
  • Automated tracking of player and community cards
  • Instant win probability calculations
  • Dynamic game state reset and error handling

Tech Stack

  • Python for real-time orchestration and app logic
  • YOLOv8 custom trained model on 22,000+ images
  • OpenCV frame analysis and image handling
  • PyTorch for GPU-accelerated model inference

About This Project

What started as a simple and laughable idea, quickly turned into a deep dive to learn more about computer vision and machine learning. Dont ask why I choose Poker! Using a custom-trained YOLOv8 model, it identifies cards from a video feed, maintains a structured game state, and calculates odds in real time. This project is still a work in progress and I will be adding more features and improvements as I learn more. DO NOT USE THIS FOR LIVE POKER GAMES!