Kolár, MartinHradiš, MichalZemcík, PavelBiasotti, Silvia and Pintus, Ruggero and Berretti, Stefano2020-11-122020-11-122020978-3-03868-124-32617-4855https://doi.org/10.2312/stag.20201238https://diglib.eg.org:443/handle/10.2312/stag20201238Editing text in photographs requires the ability to find the same font, which is impossible in many settings, such as historical or manually painted text. We present a method of extracting the font from a single photographed word, without relying on the retrieval of similar fonts. A deep net extracts style information and constructs the font for all characters, enabling novel applications in image editing, font creation, and the addition of language-specific characters with diacritics to existing fonts. A qualitative user study shows that this method improves convincing font capture by over 500% over prior work.Computing methodologiesImage processing10.2312/stag.2020123837-44