Smoothed Boundary Distance Loss Function for Enhancing Character Extraction from High-Resolution Scans of Historical Documents

This paper introduces a novel loss function, the smoothed boundary distance loss, designed to enhance character segmentation in high-resolution scans of old printed documents. Our method calculates deviation between the boundary of predicted character strokes and the counterpart of the ground truth strokes. Diverging from traditional Euclidean distance metrics, our approach determines the deviation indirectly utilizing boundary pixel value difference over a Gaussian smoothed version of the ground-truth for computational efficiency. The proposed method not only smoothens the boundary lines in character extraction but also effectively eliminates noise and outliers, significantly improving the clarity and accuracy of the segmentation process.