siromermer/Dynamic-Chess-Board-Piece-Extraction
Pipeline to convert real-life chess boards into a 2D digital format(FEN) from images and live camera feeds. The system has 2 versions: one for real-time processing using the OAK-D Lite camera and another for high-precision analysis of static images. YOLO is used to detect chess pieces, and traditional cv methods determine board positioning
This system helps you instantly convert physical chess board setups into a digital FEN (Forsyth-Edwards Notation) string. You can feed it an image of a chessboard or use a live camera, and it will output the board's exact state in a format usable by chess software. This is perfect for chess players, coaches, or content creators who want to quickly digitize real-life game positions.
Use this if you need to convert a physical chessboard position from an image or live video into a standard digital FEN string for analysis or sharing.
Not ideal if you need perfectly accurate piece recognition for every single piece in complex or unusual board setups without further model training.
Stars
55
Forks
9
Language
Jupyter Notebook
License
—
Category
Last pushed
Jan 10, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/computer-vision/siromermer/Dynamic-Chess-Board-Piece-Extraction"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
Pbatch/CameraChessWeb
Record a chess game live and upload the PGN to Lichess
rondinellimorais/chess_recognition
This project uses computer vision techniques to detect objects on a chessboard. The data are...
Amirarsalan-sn/chess-arm-vision
This is Dchess ! A robotic Chess grandmaster.
David-davidlxl/Lobsterpincer-Spectator-For-Win-RPi-Combo
Real-time chessboard processor (Windows and Raspberry Pi's combination version)
Dilanya/Chess-Pieces-Detection
This is a model created using YOLO and Roboflow to identify chess pieces.