Latest Research in Document Optical Recognition

Top Research Topics in Document Optical Recognition

• Computer Vision and Pattern Recognition — 24 papers
• Handwritten Text Recognition Techniques — 16 papers
• Computation and Language — 8 papers
• Machine Learning — 3 papers
• Academic Writing and Publishing — 2 papers
• Intelligence, Security, War Strategy — 2 papers
• Robotics and Sensor-Based Localization — 1 papers
• Image Processing and 3D Reconstruction — 1 papers
• Writing and Handwriting Education — 1 papers
• Gun Ownership and Violence Research — 1 papers

Highest-Cited Papers

1. A Free Lunch? Adapting PP-OCRv6 for Historical Text Recognition
2. When Low CER is Not Enough: An Analysis of Hallucinations in Vision-Language OCR Systems on Historical Uruguayan Documents
3. Localization for Indoor Robots using Implicit Map Representations
4. Synthetic Data-Driven Transformer OCR for Kurdish Sorani via Dynamic Line Generation and Script-Aware Normalization
5. Measuring Annotation Efficiency for Handwritten Devanagari Recognition: Sample-Complexity Curves for Four Pretraining Regimes
6. A Lightweight Web Platform for Real-Time Kuzushiji Recognition via One-Shot Pruning
7. A Multilevel Visual and Textual Framework for Near-Duplicate Diagram Detection in Electronic Documents
8. Automated Handwriting Analysis for Early Risk Screening of Learning Disabilities in Arabic-Speaking Children Using Convolutional Neural Networks (CNNs)
9. A Hybrid Multimodal Transformer-Based Approach for Text Extraction and Audio Generation from Images Using NLP
10. A Hybrid Multimodal Transformer-Based Approach for Text Extraction and Audio Generation from Images Using NLP
11. PorTEXTO: A European Portuguese Benchmark for Visual Text Extraction
12. Character-Level Visual Guidance for Arbitrarily Shaped Scene Text Detection and Recognition
13. News/Resources
14. ExpertHTR: Unified Handwritten Text Recognition with Multi-Task Learning and Sparse Mixture-of-Experts
15. Combining Synthetic and Real Data for Low-Resource Historical OCR: A Manchu Case Study
16. The Small Sample Challenge: Unsupervised Authorship Clustering in Croatian
17. EMBLEM: Enhancing Multi-script Table Detection through Masking
18. Rotation-free Online Handwritten Character Recognition Using Linear Recurrent Units
19. Unsupervised Domain Adaptation for Symbol Spotting in Historical Encrypted Manuscripts
20. Reading or Guessing? Visual Grounding Failures of Vision-Language Models for OCR in Ancient Greek Editions

Sub-Regions

• Computer Vision and Pattern Recognition — 54 papers
• Intelligence, Security, War Strategy — 11 papers
• Computation and Language — 10 papers