End-to-End Chess Recognition
This work addresses the problem of automated chessboard analysis from real-world images for applications like game digitization or AI training, though it is incremental as it builds on deep learning paradigms with a new dataset.
The paper tackled chess recognition from images by proposing an end-to-end deep learning approach to directly predict piece configurations, avoiding error accumulation from sequential methods, and introduced a new real-world dataset (ChessReD) with 10,800 photographs. The result was a 15.26% accuracy on the test set, which is about 7 times better than the current state-of-the-art, highlighting the problem's difficulty.
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.