End-to-End Chess Recognition

TL;DR

This paper proposes an end-to-end deep learning approach for chess recognition from real-world photographs, introducing a new challenging dataset and achieving significant improvements over previous methods.

Contribution

The paper introduces a novel end-to-end deep learning model for chess recognition and a new dataset with real-world images captured from various angles.

Findings

Outperforms existing methods by ~7x in accuracy.

Recognizes chess configurations in 15.26% of test images.

Introduces ChessReD dataset with 10,800 real photographs.

Abstract

Chess recognition is the task of extracting the chess piece configuration from a chessboard image. Current approaches use a pipeline of separate, independent, modules such as chessboard detection, square localization, and piece classification. Instead, we follow the deep learning philosophy and explore an end-to-end approach to directly predict the configuration from the image, thus avoiding the error accumulation of the sequential approaches and eliminating the need for intermediate annotations. Furthermore, we introduce a new dataset, Chess Recognition Dataset (ChessReD), that consists of 10,800 real photographs and their corresponding annotations. In contrast to existing datasets that are synthetically rendered and have only limited angles, ChessReD has photographs captured from various angles using smartphone cameras; a sensor choice made to ensure real-world applicability. Our approach in chess recognition on the introduced challenging benchmark dataset outperforms related approaches, successfully recognizing the chess pieces' configuration in 15.26% of ChessReD's test images. This accuracy may seem low, but it is ~7x better than the current state-of-the-art and reflects the difficulty of the problem. The code and data are available through: https://github.com/ThanosM97/end-to-end-chess-recognition.