Computational Classification of Chess Pieces
Date
2018-05
Authors
De Graff, Nathan
Major Professor
Advisor
Committee Member
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
This project aims to create a computational classifier for a standard set of chess pieces on a chess board. This classifier will then be used to parse images or videos of our chess board (i.e. “Black Rook in E6...”) to create a chess game tabulator. We demonstrate methods to isolate pieces from their surroundings, transform them into a comparable formats, and find their closest match among a database of images. In doing so, we make full use of OpenCV, a popular computer vision library for C++. Our result is a highly accurate automated classifier which can identify each game piece on a chess board in order to correctly tabulate a video stream of a chess match.
Series Number
Journal Issue
Is Version Of
Versions
Series
Academic or Administrative Unit
Type
Presentation