Learning style similarity for searching infographics

TLDR

Infographics are complex graphic designs that integrate text, images, charts, and sketches, yet despite their growing popularity and the rapid expansion of online design portfolios, little research has examined how to leverage these resources. The paper proposes a method to measure style similarity between infographics. Using crowdsourced human perception data, the authors employ computer vision and machine learning to learn a style similarity metric, evaluating various visual features and learning algorithms and determining that color histograms combined with Histograms‑of‑Gradients best characterize infographic style. The metric, based on color histograms and HoG features, effectively characterizes infographic style and is validated in a preliminary image retrieval test.

Abstract

Infographics are complex graphic designs integrating text, images, charts and sketches. Despite the increasing popularity of infographics and the rapid growth of online design portfolios, little research investigates how we can take advantage of these design resources. In this paper we present a method for measuring the style similarity between infographics. Based on human perception data collected from crowdsourced experiments, we use computer vision and machine learning algorithms to learn a style similarity metric for infographic designs. We evaluate different visual features and learning algorithms and find that a combination of color histograms and Histograms-of-Gradients (HoG) features is most effective in characterizing the style of infographics. We demonstrate our similarity metric on a preliminary image retrieval test.