Learning Typographic Style
This addresses font style analysis and generation for designers and typographers, but it is incremental as it builds on existing deep learning methods.
The paper tackled the problem of learning typographic style from a small subset of four letters, using deep neural networks to discriminate whether a new letter belongs to the same font and generate other letters with similar characteristics, with results quantitatively and qualitatively measured.
Typography is a ubiquitous art form that affects our understanding, perception, and trust in what we read. Thousands of different font-faces have been created with enormous variations in the characters. In this paper, we learn the style of a font by analyzing a small subset of only four letters. From these four letters, we learn two tasks. The first is a discrimination task: given the four letters and a new candidate letter, does the new letter belong to the same font? Second, given the four basis letters, can we generate all of the other letters with the same characteristics as those in the basis set? We use deep neural networks to address both tasks, quantitatively and qualitatively measure the results in a variety of novel manners, and present a thorough investigation of the weaknesses and strengths of the approach.