mlsanityData to 7 Oct 2026

Handwritten Text Recognition: A Survey

arXiv 2502.08417 ↗First posted 12 Feb 2025cs.CV cs.AIcited by 12

Not on the map. Why?

Abstract (arXiv)

Handwritten Text Recognition (HTR) has become an essential field within pattern recognition and machine learning, with applications spanning historical document preservation to modern data entry and accessibility solutions. The complexity of HTR lies in the high variability of handwriting, which makes it challenging to develop robust recognition systems. This survey examines the evolution of HTR models, tracing their progression from early heuristic-based approaches to contemporary state-of-the-art neural models, which leverage deep learning techniques. The scope of the field has also expanded, with models initially capable of recognizing only word-level content progressing to recent end-to-end document-level approaches. Our paper categorizes existing work into two primary levels of recognition: (1) up to line-level, encompassing word and line recognition, and (2) beyond line-level, addressing paragraph- and document-level challenges. We provide a unified framework that examines research methodologies, recent advances in benchmarking, key datasets in the field, and a discussion of the results reported in the literature. Finally, we identify pressing research challenges and outline promising future directions, aiming to equip researchers and practitioners with a roadmap for advancing the field.

Key facts. Cited by 12 papers in the map (data through 7 Oct 2026). Builds on 63 of its 200 references that are in the map. First posted on arXiv 12 Feb 2025.

Builds on

63 of 200 references.

References · 63

  1. 2017Attention Is All You Needcited by 59,932
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,204
  3. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  4. 2023Visual Instruction Tuningcited by 7,792
  5. 2014Neural Machine Translation by Jointly Learning to Align and Translatecited by 4,530
  6. 2016Pointer Sentinel Mixture Modelscited by 2,992
  7. 2019XLNet: Generalized Autoregressive Pretraining for Language Understandingcited by 2,801
  8. 2021BEiT: BERT Pre-Training of Image Transformerscited by 2,360
  9. 2014Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modelingcited by 2,341
  10. 2019ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Taskscited by 2,219
  11. 2024PaliGemma: A versatile 3B VLM for transfercited by 679
  12. 2019LayoutLM: Pre-training of Text and Layout for Document Image Understandingcited by 549
38 more
  1. 2015An End-to-End Trainable Neural Network for Image-based Sequence Recognition and Its Application to Scene Text Recognitioncited by 519
  2. 2021OCR-free Document Understanding Transformercited by 400
  3. 2021TrOCR: Transformer-based Optical Character Recognition with Pre-trained Modelscited by 278
  4. 2016Joint CTC-Attention based End-to-End Speech Recognition using Multi-task Learningcited by 254
  5. 2021DocFormer: End-to-End Transformer for Document Understandingcited by 254
  6. 2021Read Like Humans: Autonomous, Bidirectional and Iterative Language Modeling for Scene Text Recognitioncited by 194
  7. 2015Variable Rate Image Compression with Recurrent Neural Networkscited by 168
  8. 2020DocBank: A Benchmark Dataset for Document Layout Analysiscited by 152
  9. 2022DocLayNet: A Large Human-Annotated Dataset for Document-Layout Analysiscited by 146
  10. 2023Document Understanding Dataset and Evaluation (DUDE)cited by 132
  11. 2021Simpler is Better: Few-shot Semantic Segmentation with Classifier Weight Transformercited by 116
  12. 2022Towards End-to-End Unified Scene Text Detection and Layout Analysiscited by 96
  13. 2022Unified Pretraining Framework for Document Understandingcited by 85
  14. 2020Pay Attention to What You Read: Non-recurrent Handwritten Text-Line Recognitioncited by 71
  15. 2020Sequence-to-Sequence Contrastive Learning for Text Recognitioncited by 70
  16. 2020GANwriting: Content-Conditioned Generation of Styled Handwritten Word Imagescited by 68
  17. 2022DAN: a Segmentation-free Document Attention Network for Handwritten Document Recognitioncited by 62
  18. 2019Evaluating Sequence-to-Sequence Models for Handwritten Text Recognitioncited by 58
  19. 2020OrigamiNet: Weakly-Supervised, Segmentation-Free, One-Step, Full Page Text Recognition by learning to unfoldcited by 53
  20. 2020End-to-end Handwritten Paragraph Text Recognition Using a Vertical Attention Networkcited by 50
  21. 2016Joint Line Segmentation and Transcription for End-to-End Handwritten Paragraph Recognitioncited by 46
  22. 2016Scan, Attend and Read: End-to-End Handwritten Paragraph Recognition with MDLSTM Attentioncited by 45
  23. 2021Rethinking Text Line Recognition Modelscited by 45
  24. 2023DTrOCR: Decoder-only Transformer for Optical Character Recognitioncited by 40
  25. 2013Dropout improves Recurrent Neural Networks for Handwriting Recognitioncited by 39
  26. 2023Know Your Self-supervised Learning: A Survey on Image-based Generative and Discriminative Trainingcited by 39
  27. 2023Handwritten Text Generation from Visual Archetypescited by 32
  28. 2021MetaHTR: Towards Writer-Adaptive Handwritten Text Recognitioncited by 27
  29. 2018An Efficient End-to-End Neural Model for Handwritten Text Recognitioncited by 25
  30. 2019A Scalable Handwritten Text Recognition Systemcited by 25
  31. 2021Full Page Handwriting Recognition via Image to Sequence Extractioncited by 24
  32. 2024HTR-VT: Handwritten Text Recognition with Vision Transformercited by 24
  33. 2020Boosting offline handwritten text recognition in historical documents with few labeled linescited by 19
  34. 2021SPAN: a Simple Predict & Align Network for Handwritten Paragraph Recognitioncited by 19
  35. 2021Rescoring Sequence-to-Sequence Models for Text Line Recognition with CTC-Prefixescited by 18
  36. 2024VATr++: Choose Your Words Wisely for Handwritten Text Generationcited by 18
  37. 2020Attention-based Fully Gated CNN-BGRU for Russian Handwritten Textcited by 17
  38. 2022Boosting Modern and Historical Handwritten Text Recognition with Deformable Convolutionscited by 14

50 most cited of 63 All 63 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 12.

12 papers.

  1. 2026A Human-in-the-Loop Label Error Detection Framework Applied to Arabic-Script HTR Datasetscited by 3
  2. 2026What Is Wrong with Synthetic Data for Scene Text Recognition? A Strong Synthetic Engine with Diverse Simulations and Self-Evolutioncited by 2
  3. 2026Democratizing the medieval English legal traditioncited by 1
  4. 2026Handwriting Extraction and Analysis of Signature Lists in Swiss Popular Initiativescited by 0
  5. 2026Stringalign: Moving beyond summary statistics with a transparent Unicode-aware tool for evaluating automatic transcription modelscited by 0
  6. 2026Performance Gap Analysis between Latin and Arabic Scripts HTRcited by 0
  7. 2026LLM-Driven AutoML for Cross-Lingual Handwritten OCR: Closed-Loop Neural Architecture Search with GPT-5, GPT-4o, and Claude Sonnet 4cited by 0
  8. 2026OCR-Based Field Extraction for Archaeological Pottery Metadata: The CENTURIA Datasetcited by 0
  9. 2026ExpertHTR: Unified Handwritten Text Recognition with Multi-Task Learning and Sparse Mixture-of-Expertscited by 0
  10. 2026Amnesia by Design, Memory By Necessity: Persistent State for Document Intelligencecited by 0
  11. 2026Handwritten Text Recognition Lives in the High-Pixel Variance Subspacecited by 0
  12. 2026Exploring In-Context Learning for Handwritten Text Recognitioncited by 0