我们提出了TextMonkey，一种专为文本中心任务设计的大型多模态模型（LMM）。我们的方法在多个维度上引入了改进：通过采用零初始化的移位窗口注意力（Shifted Window Attention），我们在更高输入分辨率下实现了跨窗口连接，并稳定了早期训练；我们假设图像可能包含冗余标记，通过使用相似性过滤出重要标记，我们不仅能够精简标记长度，还能提升模型性能。此外，通过扩展模型能力以涵盖文本检测与定位（text spotting and grounding），并在响应中融入位置信息，我们增强了可解释性。该模型还通过微调学会了执行截图任务。在12个基准上的评估显示了显著改进：场景文本中心任务（包括STVQA、TextVQA和OCRVQA）提升5.2%，文档导向任务（如DocVQA、InfoVQA、ChartVQA、DeepForm、Kleister Charity和WikiTableQuestions）提升6.9%，关键信息抽取任务（包括FUNSD、SROIE和POIE）提升2.8%。在场景文本检测方面，它以10.9%的提升表现优异，并在OCRBench（一个包含29项OCR相关评估的综合基准）上以561分的成绩树立了新标准，超越了先前开源的用于文档理解的大型多模态模型。代码将在https://github.com/Yuliang-Liu/Monkey发布。
英文摘要：
We present TextMonkey, a large multimodal model (LMM) tailored for text-centric tasks. Our approach introduces enhancement across several dimensions: By adopting Shifted Window Attention with zero-initialization, we achieve cross-window connectivity at higher input resolutions and stabilize early training; We hypothesize that images may contain redundant tokens, and by using similarity to filter out significant tokens, we can not only streamline the token length but also enhance the model's performance. Moreover, by expanding our model's capabilities to encompass text spotting and grounding, and incorporating positional information into responses, we enhance interpretability. It also learns to perform screenshot tasks through finetuning. Evaluation on 12 benchmarks shows notable improvements: 5.2% in Scene Text-Centric tasks (including STVQA, TextVQA, and OCRVQA), 6.9% in Document-Oriented tasks (such as DocVQA, InfoVQA, ChartVQA, DeepForm, Kleister Charity, and WikiTableQuestions), and 2.8% in Key Information Extraction tasks (comprising FUNSD, SROIE, and POIE). It outperforms in scene text spotting with a 10.9\% increase and sets a new standard on OCRBench, a comprehensive benchmark consisting of 29 OCR-related assessments, with a score of 561, surpassing previous open-sourced large multimodal models for document understanding. Code will be released at https://github.com/Yuliang-Liu/Monkey.
Pretraining has proven successful in Document Intelligence tasks where deluge of documents are used to pretrain the models only later to be finetuned on downstream tasks. One of the problems of the pretraining approaches is the inconsistent usage of pretraining data with different OCR engines leading to incomparable results between models. In other words, it is not obvious whether the performance gain is coming from diverse usage of amount of data and distinct OCR engines or from the proposed models. To remedy the problem, we make public the OCR annotations for IDL documents using commercial O…
Optical Character Recognition (OCR), the task of extracting textual information from scanned documents is a vital and broadly used technology for digitizing and indexing physical documents. Existing technologies perform well for clean documents, but when the document is visually degraded, or when there are non-textual elements, OCR quality can be greatly impacted, specifically due to erroneous detections. In this paper we present an improved detection network with a masking system to improve the quality of OCR performed on documents. By filtering non-textual elements from the image we can util…
IBM Research - Haifa（IBM研究院（海法））；IBM Research - Zurich（IBM研究院（苏黎世））
For digitizing or indexing physical documents, Optical Character Recognition (OCR), the process of extracting textual information from scanned documents, is a vital technology. When a document is visually damaged or contains non-textual elements, existing technologies can yield poor results, as erroneous detection results can greatly affect the quality of OCR. In this paper we present a detection network dubbed BusiNet aimed at OCR of business documents. Business documents often include sensitive information and as such they cannot be uploaded to a cloud service for OCR. BusiNet was designed t…
ClinOCR-Bench: A Comprehensive Clinical Scanned Document Dataset for Optical Character Recognition Model Evaluation
McWilliams School of Biomedical Informatics, University of Texas Health Science Center at Houston（德克萨斯大学健康科学中心休斯顿分校麦威廉斯生物医学信息学学院）；Enterprise Development & Integration, University of Texas MD Anderson Cancer Center（德克萨斯大学MD安德森癌症中心企业开发与集成）
Detection and recognition of text from scans and other images, commonly denoted as Optical Character Recognition (OCR), is a widely used form of automated document processing with a number of methods available. Yet OCR systems still do not achieve 100% accuracy, requiring human corrections in applications where correct readout is essential. Advances in machine learning enabled even more challenging scenarios of text detection and recognition "in-the-wild" - such as detecting text on objects from photographs of complex scenes. While the state-of-the-art methods for in-the-wild text recognition …
This paper presents DavarOCR, an open-source toolbox for OCR and document understanding tasks. DavarOCR currently implements 19 advanced algorithms, covering 9 different task forms. DavarOCR provides detailed usage instructions and the trained models for each algorithm. Compared with the previous opensource OCR toolbox, DavarOCR has relatively more complete support for the sub-tasks of the cutting-edge technology of document understanding. In order to promote the development and application of OCR technology in academia and industry, we pay more attention to the use of modules that different s…
The National School for Applied Sciences of Tetuan（得土安应用科学国立学校）
Digital camera and mobile document image acquisition are new trends arising in the world of Optical Character Recognition and text detection. In some cases, such process integrates many distortions and produces poorly scanned text or text-photo images and natural images, leading to an unreliable OCR digitization. In this paper, we present a novel nonparametric and unsupervised method to compensate for undesirable document image distortions aiming to optimally improve OCR accuracy. Our approach relies on a very efficient stack of document image enhancing techniques to recover deformation of the…
Digitization of newspapers is of interest for many reasons including preservation of history, accessibility and search ability, etc. While digitization of documents such as scientific articles and magazines is prevalent in literature, one of the main challenges for digitization of newspaper lies in its complex layout (e.g. articles spanning multiple columns, text interrupted by images) analysis, which is necessary to preserve human read-order. This work provides a major breakthrough in the digitization of newspapers on three fronts: first, releasing a dataset of 3000 fully-annotated, real-worl…
OCR has been an active research area since last few decades. OCR performs the recognition of the text in the scanned document image and converts it into editable form. The OCR process can have several stages like pre-processing, segmentation, recognition and post processing. The pre-processing stage is a crucial stage for the success of OCR, which mainly deals with noise removal. In the present paper, a modified technique for noise removal named as K-Algorithm has been proposed, which has two stages as filtering and binarization. The proposed technique shows improvised results in comparison to…
ICDAR 2025 Competition on End-to-End Document Image Machine Translation Towards Complex Layouts
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；University of Chinese Academy of Sciences（中国科学院大学）；Fanyu AI Laboratory, Zhongke Fanyu Technology Company Ltd.（中科泛宇人工智能实验室，中科泛宇科技有限公司）
Center for Visual Information Technology, IIIT Hyderabad（国际信息技术研究所海得拉巴分校视觉信息技术中心）
Word error rate of an ocr is often higher than its character error rate. This is especially true when ocrs are designed by recognizing characters. High word accuracies are critical to tasks like the creation of content in digital libraries and text-to-speech applications. In order to detect and correct the misrecognised words, it is common for an ocr module to employ a post-processor to further improve the word accuracy. However, conventional approaches to post-processing like looking up a dictionary or using a statistical language model (slm), are still limited. In many such scenarios, it is …
Optical character recognition (OCR) is a widely used pattern recognition application in numerous domains. There are several feature-rich, general-purpose OCR solutions available for consumers, which can provide moderate to excellent accuracy levels. However, accuracy can diminish with difficult and uncommon document domains. Preprocessing of document images can be used to minimize the effect of domain shift. In this paper, a novel approach is presented for creating a customized preprocessor for a given OCR engine. Unlike the previous OCR agnostic preprocessing techniques, the proposed approach…
Users of OCR systems, from different institutions and scientific disciplines, prefer and produce different transcription styles. This presents a problem for training of consistent text recognition neural networks on real-world data. We propose to extend existing text recognition networks with a Transcription Style Block (TSB) which can learn from data to switch between multiple transcription styles without any explicit knowledge of transcription rules. TSB is an adaptive instance normalization conditioned by identifiers representing consistently transcribed documents (e.g. single document, doc…
A Kannada OCR, named Lipi Gnani, has been designed and developed from scratch, with the motivation of it being able to convert printed text or poetry in Kannada script, without any restriction on vocabulary. The training and test sets have been collected from over 35 books published between the period 1970 to 2002, and this includes books written in Halegannada and pages containing Sanskrit slokas written in Kannada script. The coverage of the OCR is nearly complete in the sense that it recognizes all the punctuation marks, special symbols, Indo-Arabic and Kannada numerals and also the intersp…
OCR Hinders RAG: Evaluating the Cascading Impact of OCR on Retrieval-Augmented Generation
Shanghai AI Laboratory（上海人工智能实验室）；Peking University（北京大学）；The University of HongKong（香港大学）；Shanghai Jiaotong University（上海交通大学）；Beihang University（北京航空航天大学）
Documents are a core part of many businesses in many fields such as law, finance, and technology among others. Automatic understanding of documents such as invoices, contracts, and resumes is lucrative, opening up many new avenues of business. The fields of natural language processing and computer vision have seen tremendous progress through the development of deep learning such that these methods have started to become infused in contemporary document understanding systems. In this survey paper, we review different techniques for document understanding for documents written in English and con…
FinCriticalED: A Visual Benchmark for Financial Fact-Level OCR
Columbia University（哥伦比亚大学）；Stevens Institute of Technology（史蒂文斯理工学院）；Georgia Institute of Technology（佐治亚理工学院）；New York University（纽约大学）；University of Minnesota（明尼苏达大学）；Halmstad University（哈尔姆斯塔德大学）；Harvard University（哈佛大学）；University of Manchester（曼彻斯特大学）
Barrett Hodgson University（巴雷特霍奇森大学）；Quest International University（奎斯特国际大学）；NED University of Engineering and technology（NED工程技术大学）；Université Claude Bernard Lyon1（里昂第一大学）
Given the ubiquity of handwritten documents in human transactions, Optical Character Recognition (OCR) of documents have invaluable practical worth. Optical character recognition is a science that enables to translate various types of documents or images into analyzable, editable and searchable data. During last decade, researchers have used artificial intelligence / machine learning tools to automatically analyze handwritten and printed documents in order to convert them into electronic format. The objective of this review paper is to summarize research that has been conducted on character re…
We introduce the Brno Mobile OCR Dataset (B-MOD) for document Optical Character Recognition from low-quality images captured by handheld mobile devices. While OCR of high-quality scanned documents is a mature field where many commercial tools are available, and large datasets of text in the wild exist, no existing datasets can be used to develop and test document OCR methods robust to non-uniform lighting, image blur, strong noise, built-in denoising, sharpening, compression and other artifacts present in many photographs from mobile devices. This dataset contains 2 113 unique pages from rando…
