☆
Investigating differentially private learning for document key information extraction
Saifullah Saifullah, Stefan Agne, Andreas Dengel, Sheraz Ahmed
International Journal on Document Analysis and Recognition (IJDAR)
· Computer Science Applications
· 2026-11-13
Abstract Modern deep learning models have driven significant performance breakthroughs in document key information extraction (KIE) systems. At the same time, however, their data-driven nature exposes these systems to a new class of...
☆
LLM-based automatic form data extraction from unstructured documents: an unsupervised multi-strategy approach
Linfei Ma, Dexing Wei, Chao Xie, Lun Zhang, Jian Huang, Yihua Ding
International Journal on Document Analysis and Recognition (IJDAR)
· Computer Science Applications
· 2026-11-09
☆
A modified vision transformer for Kurdish cursive RTL handwritten text recognition
Faraedwn M. Salih, Abdulbasit K. Al-Talabani
International Journal on Document Analysis and Recognition (IJDAR)
· Computer Science Applications
· 2026-10-25
☆
Understanding the limits of object detection for administrative document layout analysis
Hoang-Minh Vo, Thanh-Dien Tran, Thi-Huyen-Tran Luong, Thi-Ngoc-Diem Pham
International Journal on Document Analysis and Recognition (IJDAR)
· Computer Science Applications
· 2026-10-25
☆
Shirorekhanet: a multi-scale attention network for text line-level segmentation of sanskrit manuscripts
Latikkumar Kothwar, Parul Sahare
International Journal on Document Analysis and Recognition (IJDAR)
· Computer Science Applications
· 2026-10-06
☆
HSB-GDL: a heterogeneous subgraph benchmark for classification and query spotting
Muhammad Farhan, Malik Daler Ali Awan, Muhammad Muzzamil Luqman, Souhail Bakkali, Mickael Coustaty, Nadeem Iqbal Kajla
International Journal on Document Analysis and Recognition (IJDAR)
· Computer Science Applications
· 2026-10-06
☆
CA-DIFF: enhancing stylistic consistency in handwriting generation—a diffusion model perspective
Aniket Gurav, Sukalpa Chanda, Narayanan C. Krishnan
International Journal on Document Analysis and Recognition (IJDAR)
· Computer Science Applications
· 2026-10-03
☆
Hallucination-aware evaluation and confidence-guided selective routing for hybrid VLM-OCR: an empirical study on scene text and receipt documents
Juran Kim, Chang yup Han, Jinhong Yang
International Journal on Document Analysis and Recognition (IJDAR)
· Computer Science Applications
· 2026-09-30
☆
Trace the scribbles: a text restoration and artifact correction network for child handwriting enhancement
Sumi Suresh Mini Suresh, Sahana Rangasrinivasan, Abbie Olszewski, Srirangaraj Setlur, Venu Govindaraju
International Journal on Document Analysis and Recognition (IJDAR)
· Computer Science Applications
· 2026-09-01
Abstract Child handwriting enhancement poses unique challenges distinct from other document restoration tasks. Unlike the global degradation observed in historical manuscripts, children’s handwriting exhibits locally inconsistent faint...
☆
Accurate localization of characters in handwritten words
Said Yasin, Torsten Zesch
International Journal on Document Analysis and Recognition (IJDAR)
· Computer Science Applications
· 2026-08-25
Abstract Providing precise character-level feedback on handwritten text requires systems capable of localizing individual characters. However, existing handwriting datasets typically lack character-level annotations, limiting the...
☆
DocDjinn: controllable synthetic document generation with VLMs and handwriting diffusion
Marcel Lamott, Saifullah Saifullah, Nauman Riaz, Yves-Noel Weweler, Tobias Alt-Veit, Ahmad Sarmad Ali, Muhammad Armaghan Shakir, Adrian Kalwa, Momina Moetesum, Andreas Dengel, Sheraz Ahmed, Faisal Shafait, Ulrich Schwanecke, Adrian Ulges
International Journal on Document Analysis and Recognition (IJDAR)
· Computer Science Applications
· 2026-08-25
Abstract Effective document intelligence models rely on large amounts of annotated training data. However, procuring sufficient and high-quality data poses significant challenges due to the labor-intensive and costly nature of data...
☆
Literally reading behind the lines: a benchmark for OCR on cluttered printed documents
Rajat Verma, Vriti Sharma, Manikandan Ravikiran, Rohit Saluja, Laxmidhar Behera
International Journal on Document Analysis and Recognition (IJDAR)
· Computer Science Applications
· 2026-08-21
☆
Benchmarking OCR and vision-language models for Turkish text recognition: a comprehensive evaluation using synthetic data
Yasin Yılmaz, Erol Görkem Hanoğlu, Ayşe Gül Özkan, Kasım Öztoprak
International Journal on Document Analysis and Recognition (IJDAR)
· Computer Science Applications
· 2026-08-21
☆
Leveraging principal component analysis and machine learning on hyperspectral images band-fusion for writer identification
Muhammad Moin Qasim, Saeed Mian Qaisar, Khurram Khurshid
International Journal on Document Analysis and Recognition (IJDAR)
· Computer Science Applications
· 2026-08-16
☆
Connector and multi-level adapter based approach for scene text detection and recognition
Hai-Sheng Li, Qiuyi Li, Shuxiang Song, Cong Hu, Xiaohu Tang
International Journal on Document Analysis and Recognition (IJDAR)
· Computer Science Applications
· 2026-08-10
☆
Structure-centric representation learning for fine-grained sketch-based image retrieval
Mohammed A. S. Al-mohamadi, C. J. Prabhakar
International Journal on Document Analysis and Recognition (IJDAR)
· Computer Science Applications
· 2026-08-10
☆
Large language models for OCR in cultural heritage: a comparative study on Slovene Folkloristic texts
Octavian M. Machidon, Jasmina Rejec, Domen Vreš, Alina L. Machidon
International Journal on Document Analysis and Recognition (IJDAR)
· Computer Science Applications
· 2026-08-01
Abstract The digitization of historical and folkloristic texts presents significant challenges for optical character recognition (OCR), particularly when documents contain complex layouts, embedded illustrations, irregular typography,...
☆
Special issue on advanced topics in document analysis (2026 ICDAR-IJDAR journal track)
Koichi Kise, Gernot A. Fink, Alicia Fornés, Daniel Lopresti
International Journal on Document Analysis and Recognition (IJDAR)
· Computer Science Applications
· 2026-07-30
☆
From pixels to strokes: A survey on generative handwriting
Prajakta Joshi, Yash Madhukar Patil, Saptarshi Saha, David Doermann
International Journal on Document Analysis and Recognition (IJDAR)
· Computer Science Applications
· 2026-07-28
☆
Adversarial Optical Character Recognition to Protect Character Content: A Universal Adversarial Image Generation Scheme
Zigang Chen, Yingrong Liu, Deyang Xie, Zhangqi Wang, Dongfeng Yuan, Haihua Zhu
International Journal on Document Analysis and Recognition (IJDAR)
· Computer Science Applications
· 2026-07-27
☆
MoCoMER-V2: mask & match for self-supervised attention to recognize handwritten math expression
Sandip Pramanik, Shree Mitra, Ritabrata Chakraborty, Nibaran Das
International Journal on Document Analysis and Recognition (IJDAR)
· Computer Science Applications
· 2026-07-27
☆
Handwritten Text Recognition for Historical Latin Manuscripts via Model Adaptation and Synthetic Data Augmentation
Maria Mihaela Trusca, Mark Depauw, Margherita Fantoli, Violet Soen, Ine de Daele, Kevin Verbruggen, Tim Van de Cruys
International Journal on Document Analysis and Recognition (IJDAR)
· Computer Science Applications
· 2026-07-26
☆
Extraction of literal information from clinical document images using deep learning and pattern recognition techniques
Ravichandra Sriram, S. Siva Sathya
International Journal on Document Analysis and Recognition (IJDAR)
· Computer Science Applications
· 2026-07-25
☆
A document is worth a structured record: Principled inductive bias design for document recognition
Benjamin Meyer, Lukas Tuggener, Sascha Hänzi, Daniel Schmid, Erdal Ayfer, Benjamin F. Grewe, Ahmed Abdulkadir, Thilo Stadelmann
International Journal on Document Analysis and Recognition (IJDAR)
· Computer Science Applications
· 2026-07-23
Abstract Many document types use intrinsic, convention-driven structures that serve to encode precise and structured information, such as the conventions governing engineering drawings. However, many state-of-the-art approaches treat...
☆
Different strokes for different folks: writer identification for historical Arabic manuscripts
Hamza A. Abushahla, Ariel Justine N. Panopio, Layth Al-Khairulla, Mohamed I. AlHajri
International Journal on Document Analysis and Recognition (IJDAR)
· Computer Science Applications
· 2026-07-02
☆
A study of handwritten text recognition with cross-out words
Gayan H. Pathirage, Simon Corbillé, Filip Wåhlin, Nazrul Islam, Elisa H. Barney Smith
International Journal on Document Analysis and Recognition (IJDAR)
· Computer Science Applications
· 2026-07-02
Abstract Handwritten Text Recognition (HTR) is a challenging task in computer vision and the presence of crossed-out words in handwritten documents significantly impacts the recognition process. In this study, we first analyze the...
☆
IndianPCL: A Dataset for Multimodal Legal Document Understanding
Sagar Chakraborty, Neeraj Boddeda, Aditya Palakurty, Gaurav Harit, Saptarshi Ghosh
International Journal on Document Analysis and Recognition (IJDAR)
· Computer Science Applications
· 2026-07-01
☆
AIKON: a modular computer vision platform for historical corpora
Ségolène Albouy, Somkeo Norindr, Paul Kervegan, Fouad Aouinti, Rémy Delanaux, Clara Grometto, Robin Champenois, Stavros Lazaris, Alexandre Guilbaud, Matthieu Husson, Mathieu Aubry
International Journal on Document Analysis and Recognition (IJDAR)
· Computer Science Applications
· 2026-06-30
Abstract Historical document analysis has progressed to a point where the main bottleneck for many historical applications is not algorithms, but relevant interfaces, that can support historians’ workflow. While specialized tools exist...
☆
APAU-Net: Adaptive prior-aware U-Net for handwritten text-line segmentation in historical documents
Mohamed Amine Beghoura, Abdelouahab Attia, Abderraouf Bouziane, M. Hassaballah
International Journal on Document Analysis and Recognition (IJDAR)
· Computer Science Applications
· 2026-06-30
☆
DKDS: A Benchmark Dataset of Degraded Kuzushiji Documents with Seals for Detection and Binarization
Rui-Yang Ju, Kohei Yamashita, Hirotaka Kameko, Shinsuke Mori
International Journal on Document Analysis and Recognition (IJDAR)
· Computer Science Applications
· 2026-06-29