# Page Layout Analysis System for Unconstrained Historic Documents

arXiv: https://arxiv.org/abs/2102.11838 · HTML: https://mlsanity.com/paper/2102.11838/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 23 references that are in the map.
- First posted on arXiv 23 Feb 2021.

## Builds on (most cited first, 9 of 9)

- [V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentation](https://mlsanity.com/paper/1606.04797/) (2016)
- [Learning to Extract Semantic Structure from Documents Using Multimodal Fully Convolutional Neural Network](https://mlsanity.com/paper/1706.02337/) (2017)
- [A Two-Stage Method for Text Line Detection in Historical Documents](https://mlsanity.com/paper/1802.03345/) (2018)
- [Joint Layout Analysis, Character Detection and Recognition for Historical Document Digitization](https://mlsanity.com/paper/2007.06890/) (2020)
- [docExtractor: An off-the-shelf historical document element extraction](https://mlsanity.com/paper/2012.08191/) (2020)
- [BADAM: A Public Dataset for Baseline Detection in Arabic-script Manuscripts](https://mlsanity.com/paper/1907.04041/) (2019)
- [Multi-Task Handwritten Document Layout Analysis](https://mlsanity.com/paper/1806.08852/) (2018)
- [Labeling, Cutting, Grouping: an Efficient Text Line Segmentation Method for Medieval Manuscripts](https://mlsanity.com/paper/1906.11894/) (2019)
- [Brno Mobile OCR Dataset](https://mlsanity.com/paper/1907.01307/) (2019)

## Built on by (most cited first, 20 of 20)

- [AT-ST: Self-Training Adaptation Strategy for OCR in Domains with Limited Transcriptions](https://mlsanity.com/paper/2104.13037/) (2021)
- [TS-Net: OCR Trained to Switch Between Text Transcription Styles](https://mlsanity.com/paper/2103.05489/) (2021)
- [Unified Line and Paragraph Detection by Graph Convolutional Networks](https://mlsanity.com/paper/2203.09638/) (2022)
- [Zero-Shot Paragraph-level Handwriting Imitation with Latent Diffusion Models](https://mlsanity.com/paper/2409.00786/) (2024)
- [ICDAR 2025 Competition on FEw-Shot Text line segmentation of ancient handwritten documents (FEST)](https://mlsanity.com/paper/2509.12965/) (2025)
- [Importance of Textlines in Historical Document Classification](https://mlsanity.com/paper/2201.09575/) (2022)
- [Self-supervised Pre-training of Text Recognizers](https://mlsanity.com/paper/2405.00420/) (2024)
- [PILOT: A Promptable Interleaved Layout-aware OCR Transformer](https://mlsanity.com/paper/2504.03621/) (2025)
- [BiblioPage: A Dataset of Scanned Title Pages for Bibliographic Metadata Extraction](https://mlsanity.com/paper/2503.19658/) (2025)
- [AnnoPage Dataset: Dataset of Non-Textual Elements in Documents with Fine-Grained Categorization](https://mlsanity.com/paper/2503.22526/) (2025)
- [Studying Illustrations in Manuscripts: An Efficient Deep-Learning Approach](https://mlsanity.com/paper/2601.05269/) (2025)
- [Few-shot Writer Adaptation via Multimodal In-Context Learning](https://mlsanity.com/paper/2603.29450/) (2026)
- [METATR: A Multilingual, Evolving Benchmark for Automatic Text Recognition](https://mlsanity.com/paper/2605.26712/) (2026)
- [People and Places of Historical Europe: Bootstrapping Annotation Pipeline and a New Corpus of Named Entities in Late Medieval Texts](https://mlsanity.com/paper/2305.16718/) (2023)
- [TextBite: A Historical Czech Document Dataset for Logical Page Segmentation](https://mlsanity.com/paper/2503.16664/) (2025)
- [Masked Self-Supervised Pre-Training for Text Recognition Transformers on Large-Scale Datasets](https://mlsanity.com/paper/2503.22513/) (2025)
- [FP-THD: Full page transcription of historical documents](https://mlsanity.com/paper/2601.17040/) (2026)
- [CzechTopic: A Benchmark for Zero-Shot Topic Localization in Historical Czech Documents](https://mlsanity.com/paper/2603.03884/) (2026)
- [End-to-End Text Line Detection and Ordering](https://mlsanity.com/paper/2606.04166/) (2026)
- [Impact of Iterative Fine-Tuning on Transcription Accuracy in Complex Historical Sanskrit Manuscripts](https://mlsanity.com/paper/2608.18696/) (2026)

## Abstract (arXiv)

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.