Font Style that Fits an Image – Font Generation Based on Image Context

When fonts are used on documents, they intentionally selected by designers. For example, when designing a book cover, the typography of text is an important factor in overall feel book. In addition, it needs to be appropriate font for rest cover. Thus, we propose method generating title image based its context within We end-to-end neural network that inputs target location mask, and desired outputs stylized suitable The proposed uses combination multi-input encoder-decoder, skeleton prediction network, perception adversarial discriminator. demonstrate can effectively produce desirable cover through quantitative qualitative results. code found at https://github.com/Taylister/FontFits.