mlsanityData to 7 Oct 2026

Page Layout Analysis System for Unconstrained Historic Documents

arXiv 2102.11838 ↗First posted 23 Feb 2021cs.CVcited by 20

Not on the map. Why?

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.

Key facts. Cited by 20 papers in the map (data through 7 Oct 2026). Builds on 9 of its 23 references that are in the map. First posted on arXiv 23 Feb 2021.

Builds on

9 of 23 references.

References · 9

  1. 2016V-Net: Fully Convolutional Neural Networks for Volumetric Medical Image Segmentationcited by 2,284
  2. 2017Learning to Extract Semantic Structure from Documents Using Multimodal Fully Convolutional Neural Networkcited by 92
  3. 2018A Two-Stage Method for Text Line Detection in Historical Documentscited by 26
  4. 2020Joint Layout Analysis, Character Detection and Recognition for Historical Document Digitizationcited by 20
  5. 2020docExtractor: An off-the-shelf historical document element extractioncited by 20
  6. 2019BADAM: A Public Dataset for Baseline Detection in Arabic-script Manuscriptscited by 12
  7. 2018Multi-Task Handwritten Document Layout Analysiscited by 8
  8. 2019Labeling, Cutting, Grouping: an Efficient Text Line Segmentation Method for Medieval Manuscriptscited by 8
  9. 2019Brno Mobile OCR Datasetcited by 7

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 2; 2022: 2; 2023: 1; 2024: 2; 2025: 7; 2026: 6.

20 papers.

Sort:

By area:

  1. 2021AT-ST: Self-Training Adaptation Strategy for OCR in Domains with Limited Transcriptionscited by 10
  2. 2021TS-Net: OCR Trained to Switch Between Text Transcription Stylescited by 7
  3. 2022Unified Line and Paragraph Detection by Graph Convolutional Networkscited by 7
  4. 2024Zero-Shot Paragraph-level Handwriting Imitation with Latent Diffusion Modelscited by 5
  5. 2025ICDAR 2025 Competition on FEw-Shot Text line segmentation of ancient handwritten documents (FEST)cited by 4
  6. 2022Importance of Textlines in Historical Document Classificationcited by 2
  7. 2024Self-supervised Pre-training of Text Recognizerscited by 2
  8. 2025PILOT: A Promptable Interleaved Layout-aware OCR Transformercited by 2
  9. 2025BiblioPage: A Dataset of Scanned Title Pages for Bibliographic Metadata Extractioncited by 1
  10. 2025AnnoPage Dataset: Dataset of Non-Textual Elements in Documents with Fine-Grained Categorizationcited by 1
  11. 2025Studying Illustrations in Manuscripts: An Efficient Deep-Learning Approachcited by 1
  12. 2026Few-shot Writer Adaptation via Multimodal In-Context Learningcited by 1
8 more
  1. 2026METATR: A Multilingual, Evolving Benchmark for Automatic Text Recognitioncited by 1
  2. 2023People and Places of Historical Europe: Bootstrapping Annotation Pipeline and a New Corpus of Named Entities in Late Medieval Textscited by 0
  3. 2025TextBite: A Historical Czech Document Dataset for Logical Page Segmentationcited by 0
  4. 2025Masked Self-Supervised Pre-Training for Text Recognition Transformers on Large-Scale Datasetscited by 0
  5. 2026FP-THD: Full page transcription of historical documentscited by 0
  6. 2026CzechTopic: A Benchmark for Zero-Shot Topic Localization in Historical Czech Documentscited by 0
  7. 2026End-to-End Text Line Detection and Orderingcited by 0
  8. 2026Impact of Iterative Fine-Tuning on Transcription Accuracy in Complex Historical Sanskrit Manuscriptscited by 0