Publication Details
Page Layout Analysis System for Unconstrained Historic Documents
Layout analysis, Historic documents analysis, Text line extraction
Extraction of text regions and individual text lines from historic documents is necessary for automatic transcription. We propose extending a CNN-based text baseline detection system by adding line height and text block boundary predictions to the model output, allowing the system to extract more comprehensive layout information. We also show that pixel-wise text orientation prediction can be used for processing documents with multiple text orientations. We demonstrate that the proposed method performs well on the cBAD baseline detection dataset. Additionally, we benchmark the method on newly introduced PERO layout dataset which we also make public.
@INPROCEEDINGS{FITPUB12493, author = "Old\v{r}ich Kodym and Michal Hradi\v{s}", title = "Page Layout Analysis System for Unconstrained Historic Documents", pages = "492--506", booktitle = "Llad\'{o}s J., Lopresti D., Uchida S. (eds) Document Analysis and Recognition - ICDAR 2021", series = "Lecture Notes in Computer Science", year = 2021, location = "Lausanne, CH", publisher = "Springer Nature Switzerland AG", ISBN = "978-3-030-86330-2", doi = "10.1007/978-3-030-86331-9\_32", language = "english", url = "https://www.fit.vut.cz/research/publication/12493" }