Toward Automatic Typography Analysis: Serif Classification and Font Similarities
Lists
Only you see this
Abstract
This repository contains:\n\n - Paper published in the Journal of data mining and digital humanities:\nWasimEtAl_Toward_Automatic_Typography_Analysis__Serif_Classification_and_Font_Similarities.pdf\n\n - Two datasets: The first for serif classification \n consisting of 126666 training and 2914 font-independent testing images in raster format. \n The second dataset for svg based similarity learning consists of 124010 training and 2914 \n font-independent testing images. The images have been categorized into sans-serif, \n linear-serif, slab-serif, and triangular serif by a designer at the EPFL+ECAL Lab\n\nfont_serif_dataset.zip\nfont_svg_dataset.zip\n\n - model weights:\nserif_B_16_long_checkpoint.bin: refers to TransFG ViT B/16 Backend\nserif_B_32_long_checkpoint.bin: refers to TransFG ViT B/32 Backend\n\nViT-B_16.npz ViT-B_32.npz are publicly available at: \nhttps://github.com/TACJu/TransFG\nand were used for training TransFG ViT B/16 Backend and TransFG ViT B/32 Backend
BibTeX
@inproceedings{wasim2023toward,
author = {Syed Talal Wasim and Romain Collaud and Lara Défayes and Nicolas Henchoz and Mathieu Salzmann and Delphine Ribes},
title = {{Toward Automatic Typography Analysis: Serif Classification and Font Similarities}},
booktitle = {Zenodo},
year = {2023},
doi = {10.5281/zenodo.7683939},
}Loading related content...