Learning Perceptual Manifold of Fonts

TL;DR

This paper introduces a perceptual manifold approach to visualize and adjust font generation in a latent space, combining deep generative models with human perceptual feedback for personalized font design.

Contribution

It proposes a novel perceptual manifold framework using variational autoencoders and manifold learning to visualize and refine font generation based on human preferences.

Findings

Perceptual manifold effectively visualizes font preferences.

User interface improves font exploration efficiency.

Framework enables personalized font adjustments.

Abstract

Along the rapid development of deep learning techniques in generative models, it is becoming an urgent issue to combine machine intelligence with human intelligence to solve the practical applications. Motivated by this methodology, this work aims to adjust the machine generated character fonts with the effort of human workers in the perception study. Although numerous fonts are available online for public usage, it is difficult and challenging to generate and explore a font to meet the preferences for common users. To solve the specific issue, we propose the perceptual manifold of fonts to visualize the perceptual adjustment in the latent space of a generative model of fonts. In our framework, we adopt the variational autoencoder network for the font generation. Then, we conduct a perceptual study on the generated fonts from the multi-dimensional latent space of the generative model. After we obtained the distribution data of specific preferences, we utilize manifold learning approach to visualize the font distribution. In contrast to the conventional user interface in our user study, the proposed font-exploring user interface is efficient and helpful in the designated user preference.