Large-scale Tag-based Font Retrieval with Generative Feature Learning

TL;DR

This paper introduces a large-scale font retrieval system using a generative feature learning approach that leverages synthetic font images and an attention mechanism to improve accuracy and usability in font selection.

Contribution

The paper presents a novel generative feature learning algorithm and an integrated recognition-retrieval model for large-scale tag-based font retrieval, addressing limitations of traditional methods.

Findings

Outperforms state-of-the-art font retrieval methods

Successfully leverages synthetic font images for feature learning

Demonstrates robustness to nuisance factors like text variations

Abstract

Font selection is one of the most important steps in a design workflow. Traditional methods rely on ordered lists which require significant domain knowledge and are often difficult to use even for trained professionals. In this paper, we address the problem of large-scale tag-based font retrieval which aims to bring semantics to the font selection process and enable people without expert knowledge to use fonts effectively. We collect a large-scale font tagging dataset of high-quality professional fonts. The dataset contains nearly 20,000 fonts, 2,000 tags, and hundreds of thousands of font-tag relations. We propose a novel generative feature learning algorithm that leverages the unique characteristics of fonts. The key idea is that font images are synthetic and can therefore be controlled by the learning algorithm. We design an integrated rendering and learning process so that the visual feature from one image can be used to reconstruct another image with different text. The resulting feature captures important font design details while is robust to nuisance factors such as text. We propose a novel attention mechanism to re-weight the visual feature for joint visual-text modeling. We combine the feature and the attention mechanism in a novel recognition-retrieval model. Experimental results show that our method significantly outperforms the state-of-the-art for the important problem of large-scale tag-based font retrieval.