Predicting Forsyth-Edwards Notation with Chess Images: An Advanced Analysis Using Convolutional Neural Networks

In this research, we propose a novel method to predict Forsyth-Edwards Notation (FEN) scores of the digitalchessboard image with the help of Convolutional Neural Networks (CNNs). Our model is able to efficientlytranslate visual board configurations into related FEN representations by employing the extensive use ofdeep learning and in-depth Exploratory Data Analysis (EDA). Our data preprocessing pipeline was basedon the extensive preprocessing of images, including the data labeling, resizing, cleaning, augmentation,and data splitting into stratified batches to guarantee variety and quality of the data that would allow itssuccessful training. In order to further optimize feature extraction and spatial awareness, we incorporatedan example of Principal Component Analysis (PCA) and feature engineering techniques that currentlyenhance the model to help differentiate between different board states. The CNN model that we designedperformed a training accuracy of 98.6 percent and test accuracy of 98.4 percent and the loss and accuracycurves were well behaved within the training epochs. We measured the performance with several metrics,our model had a Micro F1 Score of 0.992, a Macro F1 Score of 0.990, a Weighted F1 Score of 0.989, ourmodel shows strong predictive performance on all classes including rare chess pieces and empty squares.Our model was tested in terms of reliability, collating all predicted FEN strings against ground truth FENscollected at online chess repositories, thus confirming their practicality. The model can be used in the reallifesituation so that with the help of our system it is possible to extract correct FENs on the basis of gameplayscreenshots to analyze the game in real-time and automatically record chess games. We summarize asolid and effective vision-based approach to the chess state recognition and open the path towards furtherdevelopment of the computer vision-based solutions in the choice of the strategic board games.