Exploratory Font Selection Using Crowdsourced Attributes

摘要

This paper presents interfaces for exploring large collections ofrnfonts for design tasks. Existing interfaces typically list fonts in arnlong, alphabetically-sorted menu that can be challenging and frustratingrnto explore. We instead propose three interfaces for font selection.rnFirst, we organize fonts using high-level descriptive attributes,rnsuch as “dramatic” or “legible.” Second, we organize fontsrnin a tree-based hierarchical menu based on perceptual similarity.rnThird, we display fonts that are most similar to a user’s currentlyselectedrnfont. These tools are complementary; a user may search forrn“graceful” fonts, select a reasonable one, and then refine the resultsrnfrom a list of fonts similar to the selection. To enable these tools, wernuse crowdsourcing to gather font attribute data, and then train modelsrnto predict attribute values for new fonts.We use attributes to helprnlearn a font similarity metric using crowdsourced comparisons. Wernevaluate the interfaces against a conventional list interface and findrnthat our interfaces are preferred to the baseline. Our interfaces alsornproduce better results in two real-world tasks: finding the nearestrnmatch to a target font, and font selection for graphic designs.