LayoutParser: A Unified Toolkit for Deep Learning Based Document Image Analysis

Z Shen, R Zhang, M Dell, BCG Lee, J Carlson… - Document Analysis and …, 2021 - Springer
Recent advances in document image analysis (DIA) have been primarily driven by the
application of neural networks. Ideally, research outcomes could be easily deployed in …

A survey of historical document image datasets

K Nikolaidou, M Seuret, H Mokayed… - International Journal on …, 2022 - Springer
This paper presents a systematic literature review of image datasets for document image
analysis, focusing on historical documents, such as handwritten manuscripts and early …

DocSegTr: an instance-level end-to-end document image segmentation transformer

S Biswas, A Banerjee, J Lladós, U Pal - arxiv preprint arxiv:2201.11438, 2022 - arxiv.org
Understanding documents with rich layouts is an essential step towards information
extraction. Business intelligence processes often require the extraction of useful semantic …

Swindocsegmenter: An end-to-end unified domain adaptive transformer for document instance segmentation

A Banerjee, S Biswas, J Lladós, U Pal - International Conference on …, 2023 - Springer
Instance-level segmentation of documents consists in assigning a class-aware and instance-
aware label to each pixel of the image. It is a key step in document parsing for their …

Beyond document object detection: instance-level segmentation of complex layouts

S Biswas, P Riba, J Lladós, U Pal - International Journal on Document …, 2021 - Springer
Abstract Information extraction is a fundamental task of many business intelligence services
that entail massive document processing. Understanding a document page structure in …

Enhancing optical character recognition: Efficient techniques for document layout analysis and text line detection

A Fateh, M Fateh, V Abolghasemi - Engineering Reports, 2024 - Wiley Online Library
In recent years, automatic document and text analysis has gained significant importance,
driven by advancements in optical character recognition (OCR) technology and the need for …

M5HisDoc: A Large-scale Multi-style Chinese Historical Document Analysis Benchmark

Y Shi, C Liu, D Peng, C Jian… - Advances in Neural …, 2024 - proceedings.neurips.cc
Recognizing and organizing text in correct reading order plays a crucial role in historical
document analysis and preservation. While existing methods have shown promising …

Digital Peter: New dataset, competition and handwriting recognition methods

M Potanin, D Dimitrov, A Shonenkov, V Bataev… - Proceedings of the 6th …, 2021 - dl.acm.org
This paper presents a new dataset of Peter the Great's manuscripts and describes a
segmentation procedure that converts initial images of documents into lines. This new …

Efficient ocr for building a diverse digital history

J Carlson, T Bryan, M Dell - … of the 62nd Annual Meeting of the …, 2024 - aclanthology.org
Many users consult digital archives daily, but the information they can access is
unrepresentative of the diversity of documentary history. The sequence-to-sequence …

Parsing electronic theses and dissertations using object detection

A Ahuja, A Devera, EA Fox - Proceedings of the first Workshop on …, 2022 - aclanthology.org
Electronic theses and dissertations (ETDs) contain valuable knowledge that can be useful
for a wide range of purposes. To effectively utilize the knowledge contained in ETDs for …