Harmonious Textual Layout Generation Over Natural Images via Deep Aesthetics Learning

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 and complicated aesthetic rules that need to be adjusted in automatic typography work. In this paper, we propose an efficient deep aesthetics learning approach to generate harmonious textual layout over natural images, which can be decomposed into two stages, saliency-aware text region proposal and aesthetics-based textual layout selection. Our method incorporates both semantic features and visual perception principles. First, we propose a semantic visual saliency detection network combined with a text region proposal algorithm to generate candidate text anchors with various positions and sizes. Second, a discriminative deep aesthetics scoring model is developed to assess the aesthetic quality of the candidate textual layouts. We build a new Textual Layout Aesthetics dataset with dense annotations of each image and design a reasonable evaluation metric to compare our method with richer baselines. The results demonstrate that our method can generate harmonious textual layouts in various actual scenarios with better performance.