A Saliency-based Convolutional Neural Network for Table and Chart Detection in Digitized Documents

Kavasidis, Isaak; Palazzo, Simone; Spampinato, Concetto; Pino, C.; Giordano, Daniela; Giuffrida, Davide; Messina, Pablo

doi:10.48550/arxiv.1804.06236

Cited by 11 publications

(13 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[10], [11]. Examples include table detection from document images using heuristics [12], vertical arrangement of text blocks [13] and deep learning methods [14]- [17].…”

Section: Related Workmentioning

confidence: 99%

Biosynthesis of the nosiheptide indole side ring centers on a cryptic carrier protein NosJ

Ding

et al. 2017

Nat Commun

View full text Add to dashboard Cite

Nosiheptide is a prototypal thiopeptide antibiotic, containing an indole side ring in addition to its thiopeptide-characteristic macrocylic scaffold. This indole ring is derived from 3-methyl-2-indolic acid (MIA), a product of the radical S-adenosylmethionine enzyme NosL, but how MIA is incorporated into nosiheptide biosynthesis remains to be investigated. Here we report functional dissection of a series of enzymes involved in nosiheptide biosynthesis. We show NosI activates MIA and transfers it to the phosphopantetheinyl arm of a carrier protein NosJ. NosN then acts on the NosJ-bound MIA and installs a methyl group on the indole C4, and the resulting dimethylindolyl moiety is released from NosJ by a hydrolase-like enzyme NosK. Surface plasmon resonance analysis show that the molecular complex of NosJ with NosN is much more stable than those with other enzymes, revealing an elegant biosynthetic strategy in which the reaction flux is controlled by protein–protein interactions with different binding affinities.

show abstract

“…[10], [11]. Examples include table detection from document images using heuristics [12], vertical arrangement of text blocks [13] and deep learning methods [14]- [17].…”

Section: Related Workmentioning

confidence: 99%

Biosynthesis of the nosiheptide indole side ring centers on a cryptic carrier protein NosJ

Ding

et al. 2017

Nat Commun

View full text Add to dashboard Cite

show abstract

“…Deep Convolutional Neural Networks (DCNNs) have proved to be useful in highly complex computer vision tasks to identify visually distinguished features of images. The effectiveness of DCNNs are also being explored in recent years in document object analysis by various research groups [5]- [8]. Hao et al [5] applied deep learning for detection of tables in PDF documents.…”

Section: B Deep Learning Based Methodsmentioning

confidence: 99%

“…some charts and plots with several intersections of horizontal and vertical lines will resemble the structure of the tables. Traditional rule based methods have had difficulties to detect them with high precision [5]- [8].…”

Section: Introductionmentioning

confidence: 99%

Graphical Object Detection in Document Images

Saha

Mondal

Jawahar

2019

2019 International Conference on Document Analysis and Recognition (ICDAR)

View full text Add to dashboard Cite

Graphical elements: particularly tables and figures contain a visual summary of the most valuable information contained in a document. Therefore, localization of such graphical objects in the document images is the initial step to understand the content of such graphical objects or document images. In this paper, we present a novel end-to-end trainable deep learning based framework to localize graphical objects in the document images called as Graphical Object Detection (GOD). Our framework is data-driven and does not require any heuristics or meta-data to locate graphical objects in the document images. The GOD explores the concept of transfer learning and domain adaptation to handle scarcity of labeled training images for graphical object detection task in the document images. Performance analysis carried out on the various public benchmark data sets: ICDAR-2013, ICDAR-POD 2017 and UNLV shows that our model yields promising results as compared to state-of-the-art techniques.

show abstract

“…Kavasidis et al [52] proposed a fully convolutional neural network for table and chart detection that overcomes the shortcomings of existing methods. This paper proposes a fully-convolutional neural network based on saliency that performs multi-scale reasoning on visual cues, followed by a fully-connected conditional random field (CRF) for localizing tables and charts in digital/digitized documents.…”

Section: Table Detection and Structure Detectionmentioning

confidence: 99%

TNCR: Table Net Detection and Classification Dataset

Abdallah,

Berendeyev,

Nuradin

et al. 2021

Preprint

View full text Add to dashboard Cite

We present TNCR, a new table dataset with varying image quality collected from free websites. TNCR dataset can be used for table detection in scanned document images and their classification into 5 different classes. TNCR contains 9428 high-quality labeled images. In this paper, we have implemented state-of-the-art deep learning-based methods for table detection to create several strong baselines. Cascade Mask R-CNN with ResNeXt-101-64x4d Backbone Network achieves the highest performance compared to other methods with a precision of 79.7%, recall of 89.8%, and f1 score of 84.4% on the TNCR dataset. We have made TNCR open source in the hope of encouraging more deep learning approaches to table detection, classification and structure recognition. The dataset and trained model checkpoints are available at https://github.com/abdoelsayed2016/TNCR_Dataset

show abstract

A Saliency-based Convolutional Neural Network for Table and Chart Detection in Digitized Documents

Cited by 11 publications

References 0 publications

Biosynthesis of the nosiheptide indole side ring centers on a cryptic carrier protein NosJ

Biosynthesis of the nosiheptide indole side ring centers on a cryptic carrier protein NosJ

Graphical Object Detection in Document Images

TNCR: Table Net Detection and Classification Dataset

Contact Info

Product

Resources

About