Text/graphic labelling of ancient printed documents

Journet, Nicholas; Églin, Véronique; Ramel, Jean-Yves; Mullot, Rémy

doi:10.1109/icdar.2005.235

Cited by 28 publications

(8 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Such approaches fail on document images with complex layout where the text and graphic regions are placed in a random fashion. In [13], author use orientation distribution using autocorrelation over a fixed window for locating text graphic in ancient document images. The algorithm fails if the window happens to contain single text line.…”

Section: Related Workmentioning

confidence: 99%

Text graphic separation in Indian newspapers

Garg

Bansal

Chaudhury

et al. 2013

Proceedings of the 4th International Workshop on Multilingual OCR

View full text Add to dashboard Cite

Digitization of newspaper article is important for registering historical events. Layout analysis of Indian newspaper is a challenging task due to the presence of different font size, font styles and random placement of text and non-text regions. In this paper we propose a novel framework for learning optimal parameters for text graphic separation in the presence of complex layouts. The learning problem has been formulated as an optimization problem using EM algorithm to learn optimal parameters depending on the nature of the document content.

show abstract

Section: Related Workmentioning

confidence: 99%

Text graphic separation in Indian newspapers

Garg

Bansal

Chaudhury

et al. 2013

Proceedings of the 4th International Workshop on Multilingual OCR

View full text Add to dashboard Cite

show abstract

“…The main part of the document segment process is combining them into higher-level structures through different heuristics methods and labeling them according to different structural features. The spatial auto-correlation approach (Journet et al, 2005;Journet et al, 2008) is a bottom-up texture-based method for document layout analysis. It starts by extracting texture features directly from the image pixels to form homogeneous regions and will auto-correlate the document image with itself to highlight periodicity and texture orientation.…”

Section: Rule-based Approachesmentioning

confidence: 99%

DocBank: A Benchmark Dataset for Document Layout Analysis

Li¹,

Xu²,

Cui³

et al. 2020

Proceedings of the 28th International Conference on Computational Linguistics

135

View full text Add to dashboard Cite

Document layout analysis usually relies on computer vision models to understand documents while ignoring textual information that is vital to capture. Meanwhile, high quality labeled datasets with both visual and textual information are still insufficient. In this paper, we present DocBank, a benchmark dataset that contains 500K document pages with fine-grained tokenlevel annotations for document layout analysis. DocBank is constructed using a simple yet effective way with weak supervision from the L A T E X documents available on the arXiv.com. With DocBank, models from different modalities can be compared fairly and multi-modal approaches will be further investigated and boost the performance of document layout analysis. We build several strong baselines and manually split train/dev/test sets for evaluation. Experiment results show that models trained on DocBank accurately recognize the layout information for a variety of documents. The DocBank dataset is publicly available at https: //github.com/doc-analysis/DocBank.

show abstract

“…To address this problem, Delaunay triangulation was employed to solve text line segmentation [21] and extracting author and title regions [55]. Journet et al [20] further used a spatial autocorrelation approach to highlight some periodicities and texture orientation for segmenting graphic elements in a page. This autocorrelation approach performs better for a document having a complex layout or text written in various fonts.…”

Section: Traditional Document Layout Segmentationmentioning

confidence: 99%

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

Biswas

Riba

Lladós

et al. 2021

IJDAR

View full text Add to dashboard Cite

Information extraction is a fundamental task of many business intelligence services that entail massive document processing. Understanding a document page structure in terms of its layout provides contextual support which is helpful in the semantic interpretation of the document terms. In this paper, inspired by the progress of deep learning methodologies applied to the task of object recognition, we transfer these models to the specific case of document object detection, reformulating the traditional problem of document layout analysis. Moreover, we importantly contribute to prior arts by defining the task of instance segmentation on the document image domain. An instance segmentation paradigm is especially important in complex layouts whose contents should interact for the proper rendering of the page, i.e., the proper text wrapping around an image. Finally, we provide an extensive evaluation, both qualitative and quantitative, that demonstrates the superior performance of the proposed methodology over the current state of the art.

show abstract

Text/graphic labelling of ancient printed documents

Abstract: Abstract

Cited by 28 publications

References 9 publications

Text graphic separation in Indian newspapers

Text graphic separation in Indian newspapers

DocBank: A Benchmark Dataset for Document Layout Analysis

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

Contact Info

Product

Resources

About