Learning Style Similarity for Searching Infographics

TL;DR

This paper introduces a machine learning-based method to measure style similarity between infographics, utilizing human perception data and visual features to enable style-based image retrieval.

Contribution

It presents a novel approach combining crowdsourced perception data with computer vision to quantify infographic style similarity, which was previously underexplored.

Findings

Color histograms and HoG features are most effective for style characterization.

The learned similarity metric enables preliminary infographic image retrieval.

Combines human perception data with machine learning for style analysis.

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.