Auteurs : Wasim, Syed Talal ¹; Collaud, Romain ²; Défayes, Lara ²; Henchoz, Nicolas ²; Salzmann, Mathieu ³; Ribes Lemay, Delphine ²

• 1 Computer Vision Lab, Ecole Polytechnique fédérale de Lausanne, Switzerland and Department of Computer Vision, Mohamed bin Zayed University of Artificial Intelligence
• 2 EPFL+ECAL Lab, Ecole Polytechnique fédérale de Lausanne, Switzerland
• 3 Computer Vision Lab, Ecole Polytechnique fédérale de Lausanne, Switzerland

Whether a document is of historical or contemporary significance, typography plays a crucial role in its composition. From the early days of modern printing, typographic techniques have evolved and transformed, resulting in changes to the features of typography. By analyzing these features, we can gain insights into specific time periods, geographical locations, and messages conveyed through typography. Therefore, in this paper, we aim to investigate the feasibility of training a model to classify serif typeswithout knowledge of the font and character. We also investigate how to train a vectorial-based image model able to group together fonts with similar features. Specifically, we compare the use of state-of-theart image classification methods, such as the EfficientNet-B2 and the Vision Transformer Base model with different patch sizes, and the state-of-the-art fine-grained image classification method, TransFG, on the serif classification task. We also evaluate the use of the DeepSVG model to learn to group fonts with similar features. Our investigation reveals that fine-grained image classification methods are better suited for the serif classification tasks and that leveraging the character labels helps to learn more meaningful font similarities.This repository contains: - Paper published in the Journal of data mining and digital humanities:WasimEtAl_Toward_Automatic_Typography_Analysis__Serif_Classification_and_Font_Similarities.pdf - Two datasets: The first for serif classification  consisting of 126666 training and 2914 font-independent testing images in raster format.  The second dataset for svg based similarity learning consists of 124010 training and 2914  font-independent testing images. The images have been categorized into sans-serif,  linear-serif, slab-serif, and triangular serif by a designer at the EPFL+ECAL Labfont_serif_dataset.zipfont_svg_dataset.zip - model weights:serif_B_16_long_checkpoint.bin: refers to TransFG ViT B/16 Backendserif_B_32_long_checkpoint.bin: refers to TransFG ViT B/32 BackendViT-B_16.npz ViT-B_32.npz are publicly available at: https://github.com/TACJu/TransFGand were used for training TransFG ViT B/16 Backend and TransFG ViT B/32 Backend - code:https://github.com/TalalWasim/GEST-Serif