On Graph Extraction from Image Data

Andreas Holzinger, Bernd Malle, Nicola Giuliani

Research output: Chapter in Book/Report/Conference proceedingChapter

Abstract

Hot topics in knowledge discovery and interactive data mining from natural images include the application of topological methods and machine learning algorithms. For any such approach one needs at first a relevant and robust digital content representation from the image data. However, traditional pixel-based image analysis techniques do not effectively extract, hence represent the content. A very promising approach is to extract graphs from images, which is not an easy task. In this paper we present a novel approach for knowledge discovery by extracting graph structures from natural image data. For this purpose, we created a framework built upon modern Web technologies, utilizing HTML canvas and pure Javascript inside a Web-browser, which is a very promising engineering approach. Following on a short description of some popular image classification and segmentation methodologies, we outline a specific data processing pipeline suitable for carrying out future scientific research. A demonstration of our implementation, compared to the results of a traditional watershed transformation performed in Matlab showed very promising results in both quality and runtime, despite
some open problems. Finally, we provide a short discussion of a few open problems and outline some of our future research routes
LanguageEnglish
Title of host publicationBrain Informatics and Health, BIH 2014, Lecture Notes in Artificial Intelligence LNAI 8609
Place of PublicationHeidelberg, Berlin
PublisherSpringer
Pages552-563
Edition1
StatusPublished - 2014

Fingerprint

Data mining
HTML
Web browsers
Image classification
Watersheds
Image segmentation
World Wide Web
Image analysis
Learning algorithms
Learning systems
Demonstrations
Pipelines
Pixels

Keywords

  • Knowledge Discovery
  • data mining
  • graphs

ASJC Scopus subject areas

  • Artificial Intelligence

Fields of Expertise

  • Information, Communication & Computing

Treatment code (Nähere Zuordnung)

  • Basic - Fundamental (Grundlagenforschung)
  • Theoretical
  • Experimental

Cite this

Holzinger, A., Malle, B., & Giuliani, N. (2014). On Graph Extraction from Image Data. In Brain Informatics and Health, BIH 2014, Lecture Notes in Artificial Intelligence LNAI 8609 (1 ed., pp. 552-563). Heidelberg, Berlin: Springer.

On Graph Extraction from Image Data. / Holzinger, Andreas; Malle, Bernd; Giuliani, Nicola.

Brain Informatics and Health, BIH 2014, Lecture Notes in Artificial Intelligence LNAI 8609. 1. ed. Heidelberg, Berlin : Springer, 2014. p. 552-563.

Research output: Chapter in Book/Report/Conference proceedingChapter

Holzinger, A, Malle, B & Giuliani, N 2014, On Graph Extraction from Image Data. in Brain Informatics and Health, BIH 2014, Lecture Notes in Artificial Intelligence LNAI 8609. 1 edn, Springer, Heidelberg, Berlin, pp. 552-563.
Holzinger A, Malle B, Giuliani N. On Graph Extraction from Image Data. In Brain Informatics and Health, BIH 2014, Lecture Notes in Artificial Intelligence LNAI 8609. 1 ed. Heidelberg, Berlin: Springer. 2014. p. 552-563.
Holzinger, Andreas ; Malle, Bernd ; Giuliani, Nicola. / On Graph Extraction from Image Data. Brain Informatics and Health, BIH 2014, Lecture Notes in Artificial Intelligence LNAI 8609. 1. ed. Heidelberg, Berlin : Springer, 2014. pp. 552-563
@inbook{bb070424e0b040efaa12247e4752a282,
title = "On Graph Extraction from Image Data",
abstract = "Hot topics in knowledge discovery and interactive data mining from natural images include the application of topological methods and machine learning algorithms. For any such approach one needs at first a relevant and robust digital content representation from the image data. However, traditional pixel-based image analysis techniques do not effectively extract, hence represent the content. A very promising approach is to extract graphs from images, which is not an easy task. In this paper we present a novel approach for knowledge discovery by extracting graph structures from natural image data. For this purpose, we created a framework built upon modern Web technologies, utilizing HTML canvas and pure Javascript inside a Web-browser, which is a very promising engineering approach. Following on a short description of some popular image classification and segmentation methodologies, we outline a specific data processing pipeline suitable for carrying out future scientific research. A demonstration of our implementation, compared to the results of a traditional watershed transformation performed in Matlab showed very promising results in both quality and runtime, despitesome open problems. Finally, we provide a short discussion of a few open problems and outline some of our future research routes",
keywords = "Knowledge Discovery, data mining, graphs",
author = "Andreas Holzinger and Bernd Malle and Nicola Giuliani",
year = "2014",
language = "English",
pages = "552--563",
booktitle = "Brain Informatics and Health, BIH 2014, Lecture Notes in Artificial Intelligence LNAI 8609",
publisher = "Springer",
edition = "1",

}

TY - CHAP

T1 - On Graph Extraction from Image Data

AU - Holzinger,Andreas

AU - Malle,Bernd

AU - Giuliani,Nicola

PY - 2014

Y1 - 2014

N2 - Hot topics in knowledge discovery and interactive data mining from natural images include the application of topological methods and machine learning algorithms. For any such approach one needs at first a relevant and robust digital content representation from the image data. However, traditional pixel-based image analysis techniques do not effectively extract, hence represent the content. A very promising approach is to extract graphs from images, which is not an easy task. In this paper we present a novel approach for knowledge discovery by extracting graph structures from natural image data. For this purpose, we created a framework built upon modern Web technologies, utilizing HTML canvas and pure Javascript inside a Web-browser, which is a very promising engineering approach. Following on a short description of some popular image classification and segmentation methodologies, we outline a specific data processing pipeline suitable for carrying out future scientific research. A demonstration of our implementation, compared to the results of a traditional watershed transformation performed in Matlab showed very promising results in both quality and runtime, despitesome open problems. Finally, we provide a short discussion of a few open problems and outline some of our future research routes

AB - Hot topics in knowledge discovery and interactive data mining from natural images include the application of topological methods and machine learning algorithms. For any such approach one needs at first a relevant and robust digital content representation from the image data. However, traditional pixel-based image analysis techniques do not effectively extract, hence represent the content. A very promising approach is to extract graphs from images, which is not an easy task. In this paper we present a novel approach for knowledge discovery by extracting graph structures from natural image data. For this purpose, we created a framework built upon modern Web technologies, utilizing HTML canvas and pure Javascript inside a Web-browser, which is a very promising engineering approach. Following on a short description of some popular image classification and segmentation methodologies, we outline a specific data processing pipeline suitable for carrying out future scientific research. A demonstration of our implementation, compared to the results of a traditional watershed transformation performed in Matlab showed very promising results in both quality and runtime, despitesome open problems. Finally, we provide a short discussion of a few open problems and outline some of our future research routes

KW - Knowledge Discovery

KW - data mining

KW - graphs

M3 - Chapter

SP - 552

EP - 563

BT - Brain Informatics and Health, BIH 2014, Lecture Notes in Artificial Intelligence LNAI 8609

PB - Springer

CY - Heidelberg, Berlin

ER -