English
Related papers

Related papers: DocParser: End-to-end OCR-free Information Extract…

200 papers

Detecting manipulations in digital documents is becoming increasingly important for information verification purposes. Due to the proliferation of image editing software, altering key information in documents has become widely accessible.…

Computer Vision and Pattern Recognition · Computer Science 2023-06-27 Hailey Joren , Otkrist Gupta , Dan Raviv

We present Qianfan-OCR, a 4B-parameter end-to-end vision-language model that unifies document parsing, layout analysis, and document understanding within a single architecture. It performs direct image-to-Markdown conversion and supports…

Digitization of scanned receipts aims to extract text from receipt images and save it into structured documents. This is usually split into two sub-tasks: text localization and optical character recognition (OCR). Most existing OCR models…

Computation and Language · Computer Science 2023-10-17 Hongkuan Zhang , Edward Whittaker , Ikuo Kitagishi

The widespread use of charts and infographics as a means of data visualization in various domains has inspired recent research in automated chart understanding. However, information extraction from chart images is a complex multitasked…

Computer Vision and Pattern Recognition · Computer Science 2024-08-30 Osama Mustafa , Muhammad Khizer Ali , Momina Moetesum , Imran Siddiqi

Despite significant advancements in Large Vision Language Models (LVLMs), a gap remains, particularly regarding their interpretability and how they locate and interpret textual information within images. In this paper, we explore various…

Computer Vision and Pattern Recognition · Computer Science 2025-10-01 Ingeol Baek , Hwan Chang , Sunghyun Ryu , Hwanhee Lee

This paper introduces a new information extraction model for business documents. Different from prior studies which only base on span extraction or sequence labeling, the model takes into account advantage of both span extraction and…

Computation and Language · Computer Science 2022-05-27 Nguyen Hong Son , Hieu M. Vu , Tuan-Anh D. Nguyen , Minh-Tien Nguyen

OrbWeaver, an automatic knowledge extraction system paired with a human interface, streamlines the use of unintuitive natural language processing software for modeling systems from their documentation. OrbWeaver enables the indirect…

Human-Computer Interaction · Computer Science 2021-04-12 Steve Schmidt , Denley Lam , Patrick Hayden

Document image quality assessment (DIQA) is an important and challenging problem in real applications. In order to predict the quality scores of document images, this paper proposes a novel no-reference DIQA method based on character…

Computer Vision and Pattern Recognition · Computer Science 2018-07-12 Hongyu Li , Fan Zhu , Junhua Qiu

The indexing and searching of historical documents have garnered attention in recent years due to massive digitization efforts of important collections worldwide. Pure textual search in these corpora is a problem since optical character…

Information Retrieval · Computer Science 2020-04-23 Taivanbat Badamdorj , Adiel Ben-Shalom , Nachum Dershowitz , Lior Wolf

DeepSeek-OCR utilizes an optical 2D mapping approach to achieve high-ratio vision-text compression, claiming to decode text tokens exceeding ten times the input visual tokens. While this suggests a promising solution for the LLM…

Computation and Language · Computer Science 2026-01-09 Yunhao Liang , Ruixuan Ying , Bo Li , Hong Li , Kai Yan , Qingwen Li , Min Yang , Okamoto Satoshi , Zhe Cui , Shiwen Ni

Traditional OCR systems (OCR-1.0) are increasingly unable to meet people's usage due to the growing demand for intelligent processing of man-made optical characters. In this paper, we collectively refer to all artificial optical signals…

Computer Vision and Pattern Recognition · Computer Science 2024-09-04 Haoran Wei , Chenglong Liu , Jinyue Chen , Jia Wang , Lingyu Kong , Yanming Xu , Zheng Ge , Liang Zhao , Jianjian Sun , Yuang Peng , Chunrui Han , Xiangyu Zhang

Since the dawn of the computing era, information has been represented digitally so that it can be processed by electronic computers. Paper books and documents were abundant and widely being published at that time; and hence, there was a…

Computation and Language · Computer Science 2012-04-03 Youssef Bassil , Mohammad Alwani

Research in Document Intelligence and especially in Document Key Information Extraction (DocKIE) has been mainly solved as Token Classification problem. Recent breakthroughs in both natural language processing (NLP) and computer vision…

Computation and Language · Computer Science 2023-04-24 Laurent Lam , Pirashanth Ratnamogan , Joël Tang , William Vanhuffel , Fabien Caspani

Large Language Models (LLMs) have demonstrated remarkable capabilities in text comprehension, but their ability to process complex, hierarchical tabular data remains underexplored. We present a novel approach to extracting structured data…

Computation and Language · Computer Science 2025-11-25 Vikram Aggarwal , Jay Kulkarni , Aditi Mascarenhas , Aakriti Narang , Siddarth Raman , Ajay Shah , Susan Thomas

Automatically extracting chemical structures from documents is essential for the large-scale analysis of the literature in chemistry. Automatic pipelines have been developed to recognize molecules represented either in figures or in text…

Computer Vision and Pattern Recognition · Computer Science 2026-03-31 Tim Strohmeyer , Lucas Morin , Gerhard Ingmar Meijer , Valéry Weber , Ahmed Nassar , Peter Staar

While humans can extract information from unstructured text with high precision and recall, this is often too time-consuming to be practical. Automated approaches, on the other hand, produce nearly-immediate results, but may not be reliable…

Computation and Language · Computer Science 2023-02-21 Bradley Butcher , Miri Zilka , Darren Cook , Jiri Hron , Adrian Weller

A typical information extraction pipeline consists of token- or span-level classification models coupled with a series of pre- and post-processing scripts. In a production pipeline, requirements often change, with classes being added and…

Artificial Intelligence · Computer Science 2022-01-19 Ramon Pires , Fábio C. de Souza , Guilherme Rosa , Roberto A. Lotufo , Rodrigo Nogueira

Post-OCR processing has significantly improved over the past few years. However, these have been primarily beneficial for texts consisting of natural, alphabetical words, as opposed to documents of numerical nature such as invoices,…

Computation and Language · Computer Science 2023-07-04 Arthur Hemmer , Jérôme Brachat , Mickaël Coustaty , Jean-Marc Ogier

Current research on the advantages and trade-offs of using characters, instead of tokenized text, as input for deep learning models, has evolved substantially. New token-free models remove the traditional tokenization step; however, their…

Computation and Language · Computer Science 2023-10-10 Christos Theodoropoulos , Marie-Francine Moens

Extracting Handwritten text is one of the most important components of digitizing information and making it available for large scale setting. Handwriting Optical Character Reader (OCR) is a research problem in computer vision and natural…

Computer Vision and Pattern Recognition · Computer Science 2022-06-10 Mohammad Daniyal Shaiq , Musa Dildar Ahmed Cheema , Ali Kamal