Authors : Ganesh Shelke; Durgesh Sakhare; Prashant Jadhav; Shreyas Sakat; Sachin Amrit

Volume/Issue : Volume 10 - 2025, Issue 4 - April

Google Scholar : https://tinyurl.com/cmnmc53s

Scribd : https://tinyurl.com/e8hjv7un

DOI : https://doi.org/10.38124/ijisrt/25apr133

Google Scholar

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Note : Google Scholar may take 15 to 20 days to display the article.

Abstract : In this study we present such an artificial intelligence driven system capable of determining the chess pieces on a physical board and providing recommendations of the best move, given the current game position. The system employs the combination of YOLOv8 object detection algorithm for accurate piece recognition and Stockfish chess engine for strategic move recommendations which allows it to run time analysis of gameplay in a real time basis. We train the YOLOv8 model on a chess image dataset with 606 chess images tagged, and thus detect with precision between 91% and 98% depending on the piece. It looks at the application of deep learning technology in the analysis of chess and its key role for automated systems to both improve and compete in educational and competitive play. Through this work, we show the potential in use of chess with AI technologies and addressing some issues in position recognition accuracy and piece identification. Beyond this, it describes in detail a plan for future improvements, including more advanced image processing techniques and further applications of the system to other board games and other sports. Overall, the results from this research provide evidence of the profound shifts that AI can bring to traditional game play, laying the groundwork for future work in intelligent gaming solutions which can both enhance the game player experience, promote learning, and further enhance the competitive dimension of chess.

Keywords : Artificial Intelligence, Chess, Deep Learning, Object Detection, YOLOv8, Stockfish, Move Suggestion.

References :

1. Esteva, A., et al. (2017). "Dermatologist-level classification of skin cancer with deep neural networks," Nature, vol. 542, no. 7639, pp. 115-118, 2017.
2. LeCun, Y., Bengio, Y., and Hinton, G. (2015). "Deep learning," Nature, vol. 521, no. 7553, pp. 436-444.
3. A foundational overview of deep learning principles that serve as the basis for developing models capable of recognizing chess pieces and suggesting moves.
4. Silver, D., et al. (2017). "Mastering the game of Go without human knowledge," Nature, vol. 550, pp. 354-359.
5. Redmon, J., et al. (2016). "You Only Look Once: Unified, real-time object detection," Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 779-788.
6. Rajpurkar, P., et al. (2017). "CheXNet: Radiologist-level pneumonia detection on chest X-rays with deep learning," arXiv preprint arXiv:1711.05225.
7. McCarthy, J. (2007). "The 50th anniversary of the Dartmouth Conference," AI Magazine, vol. 28, no. 1, pp. 67-70.
8. Goodfellow, I., et al. (2014). "Generative adversarial nets," Advances in Neural Information Processing Systems, vol. 27.
9. Krizhevsky, A., Sutskever, I., and Hinton, G. (2012). "ImageNet classification with deep convolutional neural networks," Advances in Neural Information Processing Systems, pp. 1097-1105.
10. Bottou, L. (2010). "Large-scale machine learning with stochastic gradient descent," Proceedings of the 19th International Conference on Computational Statistics (COMPSTAT), pp. 177-186.
11. Redmon, J., and Farhadi, A. (2018). "YOLOv3: An incremental improvement," arXiv preprint arXiv:1804.02767.