Logos are one of the most important graphic design forms that use an abstracted shape to clearly represent the spirit of a community. Among various styles of abstraction, a particular golden-ratio design is frequently employed by designers to create a concise and regular logo. In this context, designers utilize a set of circular arcs with golden ratios (i.e., all arcs are taken from circles whose radii form a geometric series based on the golden ratio) as the design elements to manually approximate a target shape. This error-prone process requires a large amount of time and effort, posing a significant challenge for design space exploration. In this work, we present a novel computational framework that can automatically generate golden ratio logo abstractions from an input image. Our framework is based on a set of carefully identified design principles and a constrained optimization formulation respecting these principles. We also propose a progressive approach that can efficiently solve the optimization problem, resulting in a sequence of abstractions that approximate the input at decreasing levels of detail. We evaluate our work by testing on images with different formats including real photos, clip arts, and line drawings. We also extensively validate the key components and compare our results with manual results by designers to demonstrate the effectiveness of our framework. Moreover, our framework can largely benefit design space exploration via easy specification of design parameters such as abstraction levels, golden circle sizes, etc.

Given an input image (a), we first extract prominent feature lines (b) in a preprocessing step, then perform progressive optimization to fitting circular arcs onto line segments while merging them (c), resulting in an abstracted shape (d) that respects golden ratio design principles. Here we use different colors to depict individual line segments in (b). For clarity we only sample three abstractions during the progressive optimization in (c).

Our framework can generate visually plausible golden ratio logo abstractions automatically from images in different formats, including real photos (row 1 and 2), clip arts (row 3 and 4), and line drawings (row 5). The smaller inset shows the raw input image

This work is supported in part by the National Science and Technology Council (110-2221-E-007-060-MY3 and 110-2221-E-007-061-MY3), the RCUK grant CAMERA (EP/M023281/1, EP/T022523/1), and a gift from Adobe

@inproceedings{hsiao2023img2logo,
  title={Img2Logo: Generating Golden Ratio Logos from Images},
  author={Hsiao, Kai-Wen and Yang, Yong-Liang and Chiu, Yung-Chih and Hu, Min-Chun and Yao, Chih-Yuan and Chu, Hung-Kuo},
  booktitle={Computer Graphics Forum},
  volume={42},
  number={2},
  pages={37--49},
  year={2023},
  organization={Wiley Online Library}
}