Authors:Athanasios Masouris andJan van Gemert
Affiliation:Computer Vision Lab, Delft University of Technology, Delft, The Netherlands
Keyword(s):Chess Recognition, Chess Dataset, Computer Vision, Deep Learning.
Abstract:Chess recognition is the task of extracting the chess piece configuration from a chessboard image. Currentapproaches 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 approachto directly predict the configuration from the image, thus avoiding the error accumulation of the sequentialapproaches 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 correspondingannotations. 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 toensure real-world applicability. Our approach in chess recognition on the introduced challenging benchmarkdataset outperforms related approaches, successfully recognizing the chess pieces’ configuration in 15.26% ofChessReD’s test images. This accuracy may seem low, but it is ≈7x better than the current state-of-the-art andreflects the difficulty of the problem. The code and data are available through: https://github.com/ThanosM97/end-to-end-chess-recognition.(More)
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.