https://ym-xu.github.io/living-survey/fields/document-understanding/#tag=ocrReading the characters: printed, scene and multilingual text recognition and spotting.Thu, 12 Nov 2026 15:12:01 +0000https://arxiv.org/abs/2611.13752https://arxiv.org/abs/2611.13752Tue, 10 Nov 2026 00:00:00 +0000Fonseca Cacho, Jorge Ramón OCR post-processing needs OCR text aligned word by word with its ground truth. Data sets rarely provide that mapping, and a monotone aligner can lose its place when zoning errors permute the reading order. We revisit this problem, the Zoning Problem of our 2019 paper, with a protocol that tests correctness under such p…https://arxiv.org/abs/2611.13609https://arxiv.org/abs/2611.13609Tue, 10 Nov 2026 00:00:00 +0000Mannon Ochilov, Oybek Narzullayev, Bahodir Zaripov In Uzbek official and technical documents, a large share of OCR errors is caused not by poor image quality but by characters that are visually identical across the two alphabets in use. Because the script transition is still under way, Cyrillic and Latin appear on the same page and often within a single sentence, and i…https://arxiv.org/abs/2611.08091https://arxiv.org/abs/2611.08091Thu, 05 Nov 2026 00:00:00 +0000Ismail El Jamiy, Khadija Msalek, Guillaume Loizelet, Farah Benamara, et al. Despite recent progress in handwritten text recognition, medieval Arabic scientific manuscripts remain an open challenge for current vision-language models (VLMs) due to cursive ligatures, variable diacritization, and more importantly the lack of training data. This paper aims to address this gap, by proposing the firs…https://arxiv.org/abs/2611.05539https://arxiv.org/abs/2611.05539Tue, 03 Nov 2026 00:00:00 +0000Jorge Ramón Fonseca Cacho LLMs can repair noisy OCR transcripts of historical documents, but they also change text that was already correct. We propose EditVeto, a veto gate placed after a full-context LLM rewrite. The rewrite is character-aligned to the OCR input, its differences are split into blocks, and a 0.6B-parameter gate keeps or revert…https://arxiv.org/abs/2611.04874https://arxiv.org/abs/2611.04874Tue, 03 Nov 2026 00:00:00 +0000Zhiheng Li, Zongyang Ma, Jiaxian Chen, Cheng Cui, et al. Optical Character Recognition (OCR) is among the oldest and most widely deployed applications of artificial intelligence. This survey reviews its development, focusing on the Foundation Model Era. We define OCR through faithful transcription: within a specified visual scope, OCR should completely reconstruct the text, …https://arxiv.org/abs/2611.03339https://arxiv.org/abs/2611.03339Mon, 02 Nov 2026 00:00:00 +0000Yakoub Bazi, Sarah Alsaleh, Mohamad M. Al Rahhal, Mohamed A. Mekhtiche, et al. Geospatial text spotting involves locating and transcribing geographic labels, such as road names, district names, and landmarks, in raster maps. These labels are often small, densely arranged, and arbitrarily oriented. Although Arabic text recognition has been studied extensively in documents and natural scenes, Arabi…https://arxiv.org/abs/2611.03097https://arxiv.org/abs/2611.03097Mon, 02 Nov 2026 00:00:00 +0000Tiansheng Hu, Yichuan Wang, James V. Talwar, Nicholas Tomlin, et al. Complex documents such as scientific papers contain rich information in tables, figures, and equations; however, existing deep research (DR) agents typically reduce papers to OCR-extracted text. We instead ask whether vision-language models (VLMs) can enable page-native deep research: directly retrieving and reasoning …https://arxiv.org/abs/2610.41426https://arxiv.org/abs/2610.41426Fri, 30 Oct 2026 00:00:00 +0000Zhibin Ma, Pengwen Dai, Zhigang Yao, Xugong Qin, et al. Existing Scene Text Recognition (STR) models are inherently coupled with a specific decoding strategy by their training paradigms, limiting their flexibility in deployment across diverse recognition scenarios. In this paper, we propose FlexReader, an STR model that supports multiple decoding strides, enabling a single …https://arxiv.org/abs/2610.41254https://arxiv.org/abs/2610.41254Fri, 30 Oct 2026 00:00:00 +0000Brian Tang, Kang G. Shin While modern Vision-Language Models (VLMs) have been remarkably successful in general scene text recognition, they consistently struggle with the long-tail distribution of text that is degraded by motion blur or low resolution. These limitations are particularly apparent in egocentric applications like smart glasses, w…https://arxiv.org/abs/2610.40233https://arxiv.org/abs/2610.40233Thu, 29 Oct 2026 00:00:00 +0000Chutong Meng, Alec J. Bateman, Antonios Anastasopoulos While mining parallel sentences from web pages has proven effective for low-resource machine translation, the majority of the world's languages have little to no web presence. What they do have, though, are resources that are the result of centuries of efforts by linguists, such as grammars, dictionaries, and other doc…https://arxiv.org/abs/2610.39308https://arxiv.org/abs/2610.39308Thu, 29 Oct 2026 00:00:00 +0000Shu Wei, Jingjing Wu, Qunyi Xie, Lingshu Zhang, et al. Unlimited OCR ushers the era of long-horizon parsing, substantially mitigating the growth of working memory as document lengthens. However, as document length scales to hundreds of pages, the visual context grows substantially, sharply increasing the computational cost of each decoding step and limiting the scalability…https://arxiv.org/abs/2610.36850https://arxiv.org/abs/2610.36850Tue, 27 Oct 2026 00:00:00 +0000Preethi S, Meeradevi T, Arun Prakash A Evaluation of Tamil handwritten character recognition (HCR) has largely focused on clean test images, and a standardized multi-corruption robustness benchmark for isolated Tamil HCR has not been established. We introduce uTHCD-C, a corruption-robustness benchmark based on the unconstrained Tamil Handwritten Character D…https://arxiv.org/abs/2610.36540https://arxiv.org/abs/2610.36540Tue, 27 Oct 2026 00:00:00 +0000Ousmane Hamadou, Jean Louis Kedieng Ebongue Fendji · BMVC 2026 Workshop Handwritten civil-status registers across Sub-Saharan Africa are being photographed, but rarely transcribed, which leaves their content unsearchable. Local administrations that hold these records typically lack GPUs, reliable connectivity, and the budget for external digitization services. We study whether a frugal pip…https://arxiv.org/abs/2610.35240https://arxiv.org/abs/2610.35240Mon, 26 Oct 2026 00:00:00 +0000Radha Krishna Deshpande, Ajoy Mondal, Akash Manna, C V Jawahar India's historical public archives present severe computer vision and document image analysis challenges: decades of parliamentary records survive only as degraded, multi-column scanned pages featuring mixed scripts, complex layouts, and dense visual noise where OCR failure is the primary obstacle to information retrie…https://arxiv.org/abs/2610.34148https://arxiv.org/abs/2610.34148Sun, 25 Oct 2026 00:00:00 +0000Majid Adibian, Hossein Saberi, Hossein Zeinali Optical character recognition (OCR) systems depend strongly on the scale and diversity of their training data. One approach to document OCR first analyzes the page layout and extracts text-line images, which are then transcribed by a recognition model. Multilingual line-level recognition involving Persian, Arabic, and …https://arxiv.org/abs/2610.32463https://arxiv.org/abs/2610.32463Fri, 23 Oct 2026 00:00:00 +0000Sugam Karki, Raúl Vázquez, Yova Kementchedjhieva While large vision-language models excel at optical character recognition, it remains unclear how their underlying vision encoders process text and its meaning, and whether they support anything resembling reading comprehension. We systematically study transformer-based vision encoders, using cross-modal alignment betw…https://arxiv.org/abs/2610.33066https://arxiv.org/abs/2610.33066Tue, 20 Oct 2026 00:00:00 +0000Yu Xia, Yinglun Li, Yuhui Chen, Jinlong Huang, et al. We introduce OvisOCR3, a 0.8B model for a broad range of OCR-related tasks. OvisOCR3 unifies document parsing, general OCR, key information extraction (KIE), document figure captioning, and cross-page table reconstruction in a single model. We train the model on real and synthetic data through continued pretraining and…https://arxiv.org/abs/2610.27309https://arxiv.org/abs/2610.27309Mon, 19 Oct 2026 00:00:00 +0000Paraskevi Platanou, John Pavlopoulos Optical Character Recognition (OCR) and handwritten character recognition (HCR) in low-resource historical material collections often rely on data augmentation, yet augmentation strategies are typically evaluated almost exclusively through predictive accuracy. This leaves open whether a model's improved performance is …https://arxiv.org/abs/2610.26362https://arxiv.org/abs/2610.26362Mon, 19 Oct 2026 00:00:00 +0000Islam Mesabah, Ali Elhosary, Priyabanta Sandulu, Darko Obradovic, et al. Document annotation is a fundamental yet labor-intensive step in building document information extraction systems. While Optical Character Recognition (OCR) and Large Language Models (LLMs) can automate parts of this process, we argue that annotation systems should be judged not by how completely they remove human effo…https://arxiv.org/abs/2611.00078https://arxiv.org/abs/2611.00078Sun, 18 Oct 2026 00:00:00 +0000Faizan Iqbal, Haq Nawaz Malik, Hafsah Pervaiz Optical character recognition (OCR) remains inaccessible to many low-resource scripts because annotated document images are unavailable and synthetic training data can fail to preserve script-specific visual structure. We present a data-centric framework that builds end-to-end OCR for such scripts from only an unannota…https://arxiv.org/abs/2610.25440https://arxiv.org/abs/2610.25440Sun, 18 Oct 2026 00:00:00 +0000Téa Wright, Laura X. Ma, Claudia Iron Hawk, Hannah J. Haynie, et al. Building and expanding access to digital archives supports language reclamation and creates lasting resources for community revitalization. Designing effective tools to support these efforts requires taking into account the community-, language-, and document-specific context. We investigate how small ($\leq$3B) vision…https://arxiv.org/abs/2610.25235https://arxiv.org/abs/2610.25235Sun, 18 Oct 2026 00:00:00 +0000Jumana Alsubhi, Ahmed Alhusayni, Abdulrahman Gharawi, Israa Hamdine, et al. Choosing an OCR system for a multilingual archive requires balancing accuracy against deployment constraints. This study compares cloud and self-hosted systems on three tasks: bounding box detection on 48 Arabic, English, and French pages, text recognition on 315 pages across nine document types, and mathematical expre…https://arxiv.org/abs/2610.24060https://arxiv.org/abs/2610.24060Fri, 16 Oct 2026 00:00:00 +0000Robin Hollifeldt, Tianru Zhang, Jessica Ström, Ekta Vats · TACL Recovering obscured text in palimpsests, i.e. the manuscripts where the original writing (under-text) was erased and overwritten for reuse, is vital for preserving lost information. Due to the nature of the material, such a task can be highly challenging and time-consuming. This paper presents an approach towards autom…https://arxiv.org/abs/2610.22726https://arxiv.org/abs/2610.22726Thu, 15 Oct 2026 00:00:00 +0000Nuzhat Khan, Ab Al-Hadi Ab Rahman, Mohamad Anuar Kamaruddin, Muhammad Paend Bakht, et al. Distinguishing visually similar characters is a persistent challenge for optical character recognition (OCR) systems, causing errors in critical applications of text digitization. While preprocessing techniques improve image quality and word-level post-processing corrects spelling errors, neither addresses character-le…https://arxiv.org/abs/2610.21318https://arxiv.org/abs/2610.21318Thu, 15 Oct 2026 00:00:00 +0000Eunchan Jo, Seounghyun Jang, Sangwoo Mo Multimodal document retrieval-augmented generation (RAG) has focused largely on retrieval, yet its answers depend on how well a vision-language model reads the retrieved pages. We find that evidence in retrieved pages remains underused even when the correct pages are retrieved. On SciEGQA oracle pages, five prior metho…https://arxiv.org/abs/2610.20461https://arxiv.org/abs/2610.20461Wed, 14 Oct 2026 00:00:00 +0000Nguyen Nguyen, Yongyi Zang Character Error Rate (CER), the standard metric for OCR and vision-language models (VLMs), charges a typo as much as a wrong name. We introduce semCER, which keeps CER's alignment and denominator and charges each grapheme edit a severity from an LLM judge, with no word segmentation. Normalized CER keeps the score of a …https://arxiv.org/abs/2610.18238https://arxiv.org/abs/2610.18238Tue, 13 Oct 2026 00:00:00 +0000Qian Chen, Xianyin Zhang, Lifan Guo, Chi Zhang Vision-language models (VLMs) have been widely adopted for document parsing and optical character recognition (OCR), as they can accurately extract page-level elements. However, downstream applications such as retrieval-augmented generation (RAG) also require coherent document-level structure. Although these models ind…https://arxiv.org/abs/2610.11818https://arxiv.org/abs/2610.11818Thu, 08 Oct 2026 00:00:00 +0000Uddipan Basu Bir, Vincent Christlein, Andreas Maier, Mathias Zinnen · ICDAR 2026 While massive, closed-source Vision-Language Models (VLMs) set strong benchmarks for document understanding, their dependence on commercial APIs limits adoption in institutional archives due to data autonomy concerns, recurring costs, and the environmental footprint of hyperscale computing. This is especially acute in …https://arxiv.org/abs/2610.11553https://arxiv.org/abs/2610.11553Thu, 08 Oct 2026 00:00:00 +0000Zifei Wang, Wei Wen, Qiang Ji, Qian-Wen Zhang, et al. Accurate and scalable visual document retrieval (VDR) requires both fine-grained page understanding and efficient indexing, yet existing approaches struggle to achieve both. OCR-based text retrieval adds preprocessing latency and can lose visual and structural cues needed to understand complex pages. Single-vector visi…https://arxiv.org/abs/2610.11286https://arxiv.org/abs/2610.11286Thu, 08 Oct 2026 00:00:00 +0000Feifei Li, Runjie Wang, Xiaohan Zhang, Zhenxing Qian, et al. The reliability and accountability of image generative models (IGMs) are essential for building responsible and trustworthy AI systems. Recent IGMs, such as Nano Banana and GPT-Image, now support complex instruction following, realistic image synthesis, and controllable scene-text rendering. As these capabilities expan…https://arxiv.org/abs/2610.11148https://arxiv.org/abs/2610.11148Thu, 08 Oct 2026 00:00:00 +0000Wenjie Liao, Xiaohui Song, Liangjie Zhao, Haonan Lu Accurate page transcription remains difficult for vision language models under limited input and training budgets. We present SP-DocReader, a self-play framework for optical character recognition (OCR) that targets residual errors after supervised fine-tuning. Reading Discrepancy Masking aligns reference and generated …https://arxiv.org/abs/2610.33004https://arxiv.org/abs/2610.33004Wed, 07 Oct 2026 00:00:00 +0000Camilo Mariño, Diego Belzarena, Marina Gardella, Ignacio Ramírez, et al. Optical Character Recognition (OCR) is essential for digitizing historical archives, yet standard evaluation metrics such as Character Error Rate (CER) do not necessarily reflect whether meaningful information, such as names, dates, and identifiers, is preserved. In this work, we investigate entitylevel analysis of OCR…https://arxiv.org/abs/2610.09439https://arxiv.org/abs/2610.09439Wed, 07 Oct 2026 00:00:00 +0000Jaidev Sanjay Khalane, Akbar Ali, V. N. Prabhakar, Shanmuganathan Raman Ancient script image restoration is a fundamental problem in computer vision, as it directly affects the reliable analysis and interpretation of historical documents and inscriptions. Ashokan Brahmi is an ancient script extensively used during the reign of Emperor Ashoka in the 3rd century BC, primarily for inscription…https://arxiv.org/abs/2610.01191https://arxiv.org/abs/2610.01191Thu, 01 Oct 2026 00:00:00 +0000Faias Satter, Noor Masrur, Sk. Md. Masudul Ahsan An optical character recognition(OCR) system can scan paper and extract text, making people's jobs easier. While numerous OCR systems are accessible in the software sector, finding a dependable equivalent solution for Bangla is tough. When it comes to handwritten texts, the case is even more rare. The first fundamental…https://arxiv.org/abs/2610.01134https://arxiv.org/abs/2610.01134Thu, 01 Oct 2026 00:00:00 +0000Faias Satter, Sk. Md. Masudul Ahsan An optical character recognition (OCR) can scan a paper and extract text using technology, making people's jobs easier. While various OCR systems are available in the software industry, finding a reliable equivalent solution for Bangla takes much work. When it comes to handwritten texts, the situation is much more unus…https://arxiv.org/abs/2609.39013https://arxiv.org/abs/2609.39013Wed, 30 Sep 2026 00:00:00 +0000Divya Godara, Sachin Gupta · EMNLP 2026 EVICALC, our system for the DocSem shared task, achieved 8.61% joint accuracy on 1,730 tasks in the official final test evaluation. It reads a PDF, selects a passage, asks a language model to write an arithmetic expression, and evaluates that expression in local code. Saved intermediate results support inspection of fa…https://arxiv.org/abs/2609.38282https://arxiv.org/abs/2609.38282Tue, 29 Sep 2026 00:00:00 +0000Baode Wang, Zuming Huang, Kexuan Ren, Jun Huang, et al. Vision-language models may rewrite anomalous text in images into linguistically plausible expressions, compromising OCR transcription faithfulness. Sequence-level task rewards and local teacher guidance are complementary, but guidance from the same teacher may not remain equally effective as the student improves. Offli…https://arxiv.org/abs/2609.37755https://arxiv.org/abs/2609.37755Tue, 29 Sep 2026 00:00:00 +0000Anton Repushko, Elena Chepel Purpose: Most Greek papyri remain unpublished and undigitised; a handwritten text recognition (HTR) pipeline that transcribes them automatically would let scholars discover documents and literary works that have so far gone unread. Recognition systems for Ancient Greek papyri are in statu nascendi, and how accurate the…https://arxiv.org/abs/2609.37712https://arxiv.org/abs/2609.37712Tue, 29 Sep 2026 00:00:00 +0000GuangJian Team, Kaili Huang, Yongshuo Zhang, Bingtao Fu, et al. Optical Character Recognition (OCR) is evolving from plain-text transcription toward general visual intelligence, requiring models to recognize, localize, and reason over textual information in complex visual environments. However, existing OCR systems often excel at only some tasks and struggle to balance recognition,…https://arxiv.org/abs/2609.37195https://arxiv.org/abs/2609.37195Tue, 29 Sep 2026 00:00:00 +0000Eric Ayllon, Abel Gandia, Jorge Calvo-Zaragoza Handwritten Text Recognition (HTR) systems have become an indispensable tool for the digitization of historical documents. Not only do they cut down time and cost, but they also allow democratizing access and processing of their contents by generating their transcripts. However, literature in HTR currently focuses most…