Versatile Layout Understanding via Conjugate Graph

Prasad, Animesh; Dejean, Hervé; Meunier, Jean-Luc

doi:10.1109/icdar.2019.00054

Cited by 11 publications

(3 citation statements)

References 15 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An interesting work is described in [16]. It focuses on table analysis, but it can be foreseen that the reading order could be obtained as a byproduct of the proposed process.…”

Section: Relation With Previous Work On Reading Ordermentioning

confidence: 99%

Reading order detection on handwritten documents

Quirós

Vidal

2022

Neural Comput & Applic

View full text Add to dashboard Cite

Recent advances in Handwritten Text Recognition and Document Layout Analysis have made it possible to convert digital images of manuscripts into electronic text. However, providing this text with the correct structure and context is still an open problem that needs to be solved to actually enable extracting the relevant information conveyed by the text. The most important structure needed for a set of text elements is their reading order. Most of the studies on the reading order problem are rule-based approaches and focus on printed documents. Much less attention has been paid so far to handwritten text documents, where the problem becomes particularly important—and challenging. In this work, we propose a new approach to automatically determine the reading order of text regions and lines in handwritten text documents. The task is approached as a sorting problem where the order-relation operator is automatically learned from examples. We experimentally demonstrate the effectiveness of our method on three different datasets at different hierarchical levels.

show abstract

“…An interesting work is described in [16]. It focuses on table analysis, but it can be foreseen that the reading order could be obtained as a byproduct of the proposed process.…”

Section: Relation With Previous Work On Reading Ordermentioning

confidence: 99%

Reading order detection on handwritten documents

Quirós

Vidal

2022

Neural Comput & Applic

View full text Add to dashboard Cite

show abstract

“…*The construction of graphs with the help of groups has become one of the most interesting topics of research, and many works have been done in relation to this in the past few years (Fortunato, 2010;Kumar et al, 2021). The concept of a conjugate graph was first introduced by Erfanian and Tolue (2012) and attracted many researchers afterward (Prasad et al, 2019;Alolaiyan et al, 2019;Ling and Qin, 2022). They defined it to be a graph whose vertices are the noncentral elements of a group, and two vertices are adjacent if they are conjugate.…”

Section: Introductionmentioning

confidence: 99%

Conjugacy classes and conjugate graph of a K-metacyclic group

Yangertola,

Patra

2023

Int. j. adv. appl. sci.

View full text Add to dashboard Cite

The relationship between algebraic structures and graphs has become an interesting topic of research nowadays. In this paper, we have considered the conjugate graph related to the conjugacy relation of a group. The vertices of the said graph are the noncentral elements of the group, and two vertices are adjacent if they are conjugate. For this particular study, we focused on the conjugate graph of a K-metacyclic group of order p(p-1). We first determine the conjugacy classes of this group and then obtain its conjugate graph. Various graph properties such as planarity, line graph, complement graph, clique number, dominating number, spectrum, and Laplacian are also studied in this paper.

show abstract

“…Overlaps, missing text, and sloppy box fitting all impact the accuracy of the system, especially when a document's layout is particularly dense. Indeed, [1] mentions a situation where FRCNN is known to struggle (dense tables) and claims a new approach is needed. Likewise, the problems described are present in the figures of [5], with their 'small table' example cutting off text, and 'page column alike' partially including the caption above it.…”

Section: Introductionmentioning

confidence: 99%

A Clustering Backed Deep Learning Approach for Document Layout Analysis

Agombar¹,

Luebbering²,

Sifa³

2020

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Large organizations generate documents and records on a daily basis, often to such an extent that processing them manually becomes unduly time consuming. Because of this, automated processing systems for documents are desirable, as they would reduce the time spent handling them. Unfortunately, documents are often not designed to be machine-readable, so parsing them is a difficult problem. Image segmentation techniques and deep-learning architectures have been proposed as a solution to this, but have difficulty retaining accuracy when page layouts are especially dense. This leads to the possibilities of data being duplicated, lost, or inaccurate during retrieval. We propose a way of refining these segmentations, using a clustering based approach that can be easily combined with existing rules based refinements. We show that on a financial document corpus of 2675 pages, when using DBSCAN, this method is capable of significantly increasing the accuracy of existing deep-learning methods for image segmentation. This improves the reliability of the results in the context of automatic document analysis.

show abstract

Versatile Layout Understanding via Conjugate Graph

Cited by 11 publications

References 15 publications

Reading order detection on handwritten documents

Reading order detection on handwritten documents

Conjugacy classes and conjugate graph of a K-metacyclic group

A Clustering Backed Deep Learning Approach for Document Layout Analysis

Contact Info

Product

Resources

About