Roderic Page · Front Matter · 2023
How to cite: <strong> Page, R. (2023). Document layout analysis. https://doi.org/10.59350/z574z-dcw92 </strong> Some notes to self on document layout analysis. I'm revisiting the problem of taking a PDF or a scanned document and determining its structure (for example, where is the title, abstract, bibliography, where are the figures and their captions, etc.). There are lots of papers on this topic, and lots of tools.
Cited by 0Open access
Galal M. BinMakhashen, Sabri A. Mahmoud · ACM Computing Surveys · 2019
Document layout analysis (DLA) is a preprocessing step of document understanding systems. It is responsible for detecting and annotating the physical structure of documents. DLA has several important applications such as document retrieval, content categorization, text recognition, and the like. The objective of DLA is to ease the subsequent analysis/recognition phases by identifying the document-homogeneous blocks and by determining their relationships. The DLA pipeline consists of several phases that could vary among DLA methods, depending on the documents’ layouts and final analysis objectives. In this regard, a universal DLA algorithm that fits all types of document-layouts or that satisfies all analysis objectives has not been developed, yet. In this survey paper, we present a critical study of different document layout analysis techniques. The study highlights the motivational reasons for pursuing DLA and discusses comprehensively the different phases of the DLA algorithms based on a general framework that is formed as an outcome of reviewing the research in the field. The DLA framework consists of preprocessing, layout analysis strategies, post-processing, and performance evaluation phases. Overall, the article delivers an essential baseline for pursuing further research in document layout analysis.
Cited by 166
Showmik Bhowmik · SpringerBriefs in computer science · 2023
Cited by 7Open access
Roderic Page · Front Matter · 2023
How to cite: <strong> Page, R. (2023). Document layout analysis. https://doi.org/10.59350/z574z-dcw92 </strong> Some notes to self on document layout analysis. I'm revisiting the problem of taking a PDF or a scanned document and determining its structure (for example, where is the title, abstract, bibliography, where are the figures and their captions, etc.). There are lots of papers on this topic, and lots of tools.
Cited by 0Open access
X. Jiang, Betreuer Da-chuan Chen, Tammo Mueller et al. · 2005
This document gives an overview about document layout analysis. It presents in detail one method which is part of the pre-processing phase, called skew angle estimation. In doing so it introduces a special technique of how determining the skew angle, namely the Hough Transform. Fur-thermore it presents numerous ways of approaches to speed up the process of skew angle detection. The second part deals with page segmentation which is one of the huge parts in document image analysis. It illustrates a means of partitioning using bounding boxes of different entities. It discusses advantages and
Cited by 0
Vicente Bosch Campos · 2020
[EN] Handwritten Text Segmentation (HTS) is a task within the Document Layout Analysis field that aims to detect and extract the different page regions of interest found in handwritten documents. HTS remains an active topic, that has gained importance with the years, due to the increasing demand to provide textual access to the myriads of handwritten document collections held by archives and libraries. \nThis thesis considers HTS as a task that must be tackled in two specialized phases: detection and extraction. We see the detection phase fundamentally as a recognition problem that yields the vertical positions of each region of interest as a by-product. The extraction phase consists in calculating the best contour coordinates of the region using the position information provided by the detection phase. \nOur proposed detection approach allows us to attack both higher level regions: paragraphs, diagrams, etc., and lower level regions like text lines. In the case of text line detection we model the problem to ensure that the system's yielded vertical position approximates the fictitious line that connects the lower part of the grapheme bodies in a text line, commonly known as the \nbaseline. \nOne of the main contributions of this thesis, is that the proposed modelling approach allows us to include prior information regarding the layout of the documents being processed. This is performed via a Vertical Layout Model (VLM). \nWe develop a Hidden Markov Model (HMM) based framework to tackle both region detection and classification as an integrated task and study the performance and ease of use of the proposed approach in many corpora. We review the modelling simplicity of our approach to process regions at different levels of information: text lines, paragraphs, titles, etc. We study the impact of adding deterministic and/or probabilistic prior information and restrictions via the VLM that our approach provides. \nHaving a separate phase that accurately yields the detection position (base- lines in the case of text lines) of each region greatly simplifies the problem that must be tackled during the extraction phase. In this thesis we propose to use a distance map that takes into consideration the grey-scale information in the image. This allows us to yield extraction frontiers which are equidistant to the adjacent text regions. We study how our approach escalates its accuracy proportionally to the quality of the provided detection vertical position. Our extraction approach gives near perfect results when human reviewed baselines are provided.
Cited by 1Open access
Jianying Hu, R. Kashi, Gordon Wilfong · 1999
This paper describes methods for document image classification at the spatial layout level. The goal is to develop fast algorithms for initial document type classification without OCR, which can then be verified using more elaborate methods based on more detailed geometric and syntactic models. A novel feature set called interval encoding is introduced to capture elements of spatial layout. This feature set encodes region layout information in fixed-length vectors by capturing structural characteristics of the image. We demonstrate the usefulness of these features derived from interval coding, in a hidden Markov model based page layout classification system that is trainable and extendible.
Cited by 20
Ibrahim M. Amer, Salma Hamdy, Mostafa G. M. Mostafa · 2017
Document layout analysis (DLA) is an essential step for Optical Character Recognition Systems (OCR). The text of the document fed to the OCR must be extracted first and isolated from images if exist. The DLA task is difficult as there is no fixed layout for all documents, but instead, there are several layouts. There are various approaches for DLA for various different languages. In this paper, some of the previous techniques used in this field will be listed and then we will discuss the proposed method that depends on deep learning for documents' text localization. We used Arabic Printed Text Image database (APTI [19]), ImageNet [18] and a dataset collected from different Arabic newspapers for training and evaluation.
Cited by 7
Sebastian Tewes, Yufan Chen, Omar Moured et al. · Lecture notes in computer science · 2025
Cited by 1
PIRLO, Giuseppe, Chimienti M, Dassisti M et al. · CINECA IRIS Institutional Research Information System (University of Bari Aldo Moro) · 2013
A new layout-based document image retrieval system is presented in this paper. The system is specifically designed for commercial form retrieval and uses mathematical morphology to extract structural components from the document image. Document layout description is performed by the Radon Transform whereas Dynamic Time Warping is used for matching. The experimental results have been carried out on both real and simulated data sets. They demonstrate the effectiveness of the proposed approach and their robustness with respect to different classes of commercial forms and shifted/rotated document images.
Cited by 0
Tewes, Sebastian, Chen, Yufan, Moured, Omar et al. · ArXiv.org · 2025
Document Layout Analysis (DLA) is a fundamental task in document understanding. However, existing DLA and adaptation methods often require access to large-scale source data and target labels. This requirements severely limiting their real-world applicability, particularly in privacy-sensitive and resource-constrained domains, such as financial statements, medical records, and proprietary business documents. According to our observation, directly transferring source-domain fine-tuned models on target domains often results in a significant performance drop (Avg. -32.64%). In this work, we introduce Source-Free Document Layout Analysis (SFDLA), aiming for adapting a pre-trained source DLA models to an unlabeled target domain, without access to any source data. To address this challenge, we establish the first SFDLA benchmark, covering three major DLA datasets for geometric- and content-aware adaptation. Furthermore, we propose Document Layout Analysis Adapter (DLAdapter), a novel framework that is designed to improve source-free adaptation across document domains. Our method achieves a +4.21% improvement over the source-only baseline and a +2.26% gain over existing source-free methods from PubLayNet to DocLayNet. We believe this work will inspire the DLA community to further investigate source-free document understanding. To support future research of the community, the benchmark, models, and code will be publicly available at https://github.com/s3setewe/sfdla-DLAdapter.
Cited by 0Open access
Ejian Zhou, Xingjiao Wu, Luwei Xiao et al. · 2022 IEEE International Conference on Image Processing (ICIP) · 2022
Document layout analysis plays a vital role in computer vision research. Current document layout analysis methods mostly use pixel-based classification for document layout analysis. However, the method based on pixel classification is insufficient for maintaining the continuity of the classification area. In this paper, we propose a document layout analysis method based on positional encoding and bounding box specification. We maintain the continuity of the analysis area by constructing a document layout analysis framework based on the bounding box. In addition, we also integrate a positional encoding module in the framework to maintain the detailed information in the document layout analysis and modeling process. Experimental results prove that our proposed method has achieved state-of-the-art results.
Cited by 0
Paul Bridson, David · University of Liverpool · 2023
Cited by 0Open access
EJian Zhou, Xingjiao Wu, Luwei Xiao et al. · IEEE RESOURCE CENTERS · 2024
Cited by 0Open access
MALERBA D., ALTAMURA O., ESPOSITO, Floriana · CINECA IRIS Institutional Research Information System (University of Bari Aldo Moro) · 2002
Cited by 0
Bridson, David Paul · OpenGrey (Institut de l'Information Scientifique et Technique) · 2009
Cited by 0
Tewes, Sebastian, Chen, Yufan, Moured, Omar et al. · arXiv (Cornell University) · 2025
Document Layout Analysis (DLA) is a fundamental task in document understanding. However, existing DLA and adaptation methods often require access to large-scale source data and target labels. This requirements severely limiting their real-world applicability, particularly in privacy-sensitive and resource-constrained domains, such as financial statements, medical records, and proprietary business documents. According to our observation, directly transferring source-domain fine-tuned models on target domains often results in a significant performance drop (Avg. -32.64%). In this work, we introduce Source-Free Document Layout Analysis (SFDLA), aiming for adapting a pre-trained source DLA models to an unlabeled target domain, without access to any source data. To address this challenge, we establish the first SFDLA benchmark, covering three major DLA datasets for geometric- and content-aware adaptation. Furthermore, we propose Document Layout Analysis Adapter (DLAdapter), a novel framework that is designed to improve source-free adaptation across document domains. Our method achieves a +4.21% improvement over the source-only baseline and a +2.26% gain over existing source-free methods from PubLayNet to DocLayNet. We believe this work will inspire the DLA community to further investigate source-free document understanding. To support future research of the community, the benchmark, models, and code will be publicly available at https://github.com/s3setewe/sfdla-DLAdapter.
Cited by 0Open access
Atul Kumar, Gurpreet Singh Lehal · Lecture notes in networks and systems · 2025
Cited by 0
Li, Jianbo · KTH Publication Database DiVA (KTH Royal Institute of Technology) · 2021
In this project, a state-of-the-art CV model called Mask Region Based Convolutional Neural Networks (Mask R-CNN) was trained, to process the layout analysis of historical documents.In addition, a practical webpage is designed, which includes a front-end for interaction, a back-end that supports search and filter functions, and a MongoDB database. Besides that, this project was deployed to the cloud through Jenkins. This project started from the training of the model, after that, built a webpage, and then deployed it in the cloud. It is already a complete and usable tool that can provide great convenience to historical documents researcher. At the same time, its architecture is decoupled, therefore, it is easy to expand and update the model in the future.
Cited by 0Open access
Endrych, David · Brno University of Technology Digital Library (Brno University of Technology) · 2019
Cílem této bakalářské práce je vytvořit nástroj pro analýzu rozložení stran textových dokumentů. Problém je řešen pomocí konvolučních neuronových sítí. Architekturou zvolenou v téhle bakalářské práci je architektura U-Net. Pro trénování modelu sítě se používá chybová funkce cross entropy s použitím mapy vah. Pomocí hledání spojitých komponent dochází k získávání regionů odstavců. Experimenty se vyhodnocují pomocí objektové metriky Symmetric Best Dice. Z experimentů vyplynulo, že je lepší používat všechny hrany odstavců než se zaměřovat pouze na vertikální hrany odstavců. Dále experimenty ukazují, že trénovací strategie vzorkování batche a adaptativní rozlišení pomáhají ke zlepšení výsledků analýzy. V experimentech je také popsána aplikace separátorů, která je užitečná při analýze vícesloupcových dokumentů.
Cited by 0