ChessLens is an intelligent, real-time chess game digitization system powered by computer vision and deep learning. Designed to bridge the gap between physical and digital chessboards, ChessLens monitors a live chess game through a camera, processes each move, and dynamically updates a virtual board on screen.
Unlike traditional Digital Game Technology (DGT) boards, ChessLens requires no embedded hardware or special pieces — just a standard chessboard, a webcam, and a laptop. It uses homography estimation to correct perspective distortion, a deep learning model to identify occupied squares, and real-time frame analysis to detect and visualize piece movements.
Built with scalability and accessibility in mind, ChessLens is ideal for broadcasting live chess games in tournaments, coaching setups, or casual club matches — all without expensive infrastructure.
Achieved an accuracy of 93.75%.
This repository contains the report, slides, and jupyter notebook and related code files for the final course project of the Computer Vision (CS342) course offered at Ramakrishna Mission Vivekananda Educational and Research Institute, Belur as a part of the Master of Science in Big Data Analytics programme.
- Python 3.12
- OpenCV – Image & video processing
- TensorFlow / Keras – CNN for Occupancy Detection
- Tkinter – Live board visualization
- CairoSVG – Renders SVG chessboards
- python-chess – FEN management & move legality
This project was done by the team BSB64, whose team members are:
- April 28, 2025
