Smarttext: Learning To Generate Harmonious Textual Layout Over Natural Image

Peiying Zhang, Chenhui Li, Changbo Wang

Abstract

Automatic typography is important because it helps designers avoid highly repetitive tasks and amateur users achieve high-quality textual layout designs. However, there are often many parameters that need to be adjusted in automatic typography work. In this paper, we propose an efficient content-aware learning-based framework to generate harmonious textual layout over natural image. Our method incorporates both semantic features and visual perception principles. First, we combine a semantic visual saliency detection network with diffusion equations and a text-region proposal algorithm to generate candidate text anchors with various positions and sizes. Second, we develop a deep scoring network to assess the aesthetic quality of the candidate results. We design multiple evaluations to compare our method with several baselines and a commercial poster design tool. The results demonstrate that our method can generate harmonious textual layout in various actual scenarios with better performance.
BibTeX
@inproceedings{zhang2020smarttext,
  author = {Peiying Zhang and Chenhui Li and Changbo Wang},
  title = {{Smarttext: Learning To Generate Harmonious Textual Layout Over Natural Image}},
  booktitle = {ICME},
  year = {2020},
  doi = {10.1109/icme46284.2020.9102780},
}

Loading related content...

Figure