Font Style that Fits an Image -- Font Generation Based on Image Context
This addresses the need for automated font selection in graphic design, particularly for book covers, but it is incremental as it builds on existing neural network techniques for style transfer.
The paper tackled the problem of generating stylized text for book covers that matches the visual context, proposing an end-to-end neural network that inputs a book cover, target location, and title to output appropriate text. The method demonstrated effectiveness through quantitative and qualitative results, though no concrete numbers were provided.
When fonts are used on documents, they are intentionally selected by designers. For example, when designing a book cover, the typography of the text is an important factor in the overall feel of the book. In addition, it needs to be an appropriate font for the rest of the book cover. Thus, we propose a method of generating a book title image based on its context within a book cover. We propose an end-to-end neural network that inputs the book cover, a target location mask, and a desired book title and outputs stylized text suitable for the cover. The proposed network uses a combination of a multi-input encoder-decoder, a text skeleton prediction network, a perception network, and an adversarial discriminator. We demonstrate that the proposed method can effectively produce desirable and appropriate book cover text through quantitative and qualitative results.