Jump to ContentJump to Main Navigation
Show Summary Details
More options …

tm - Technisches Messen

Plattform für Methoden, Systeme und Anwendungen der Messtechnik

[TM - Technical Measurement: A Platform for Methods, Systems, and Applications of Measurement Technology
]

Editor-in-Chief: Puente León, Fernando / Zagar, Bernhard

12 Issues per year


IMPACT FACTOR 2016: 0.348

CiteScore 2016: 0.28

SCImago Journal Rank (SJR) 2016: 0.241
Source Normalized Impact per Paper (SNIP) 2016: 0.343

Online
ISSN
2196-7113
See all formats and pricing
More options …
Volume 82, Issue 5 (May 2015)

Issues

Synthesizing images using parameterized models for automated optical inspection (AOI)

Synthese von Bildern mittels parametrisierter Modelle für die automatische optische Inspektion (AOI)

Max-Gerd Retzlaff
  • Corresponding author
  • Karlsruhe Institute of Technology (KIT), Institute for Visualization and Data Analysis, Computer Graphics Group, Karlsruhe
  • Fraunhofer Institute of Optronics, System Technologies and Image Exploitation (IOSB), Karlsruhe
  • Email
  • Other articles by this author:
  • De Gruyter OnlineGoogle Scholar
/ Josua Stabenow
  • Karlsruhe Institute of Technology (KIT), Institute for Visualization and Data Analysis, Computer Graphics Group, Karlsruhe
  • Email
  • Other articles by this author:
  • De Gruyter OnlineGoogle Scholar
/ Jürgen Beyerer
  • Karlsruhe Institute of Technology (KIT), Institute for Anthropomatics and Robotics, Vision and Fusion Laboratory (IES), Karlsruhe
  • Fraunhofer Institute of Optronics, System Technologies and Image Exploitation (IOSB), Karlsruhe
  • Email
  • Other articles by this author:
  • De Gruyter OnlineGoogle Scholar
/ Carsten Dachsbacher
  • Karlsruhe Institute of Technology (KIT), Institute for Visualization and Data Analysis, Computer Graphics Group, Karlsruhe
  • Email
  • Other articles by this author:
  • De Gruyter OnlineGoogle Scholar
Published Online: 2015-04-23 | DOI: https://doi.org/10.1515/teme-2014-0041

Abstract

When designing or improving systems for automated optical inspection (AOI), systematic evaluation is an important but costly necessity to achieve and ensure high quality. Computer graphics methods can be used to quickly create large virtual sets of samples of test objects and to simulate image acquisition setups. We use procedural modeling techniques to generate virtual objects with varying appearance and properties, mimicking real objects and sample sets. Physical simulation of rigid bodies is deployed to simulate the placement of virtual objects, and using physically-based rendering techniques we create synthetic images. These are used as input to an AOI system instead of physically acquired images. This enables the development, optimization, and evaluation of the image processing and classification steps of an AOI system independently of a physical realization. We demonstrate this approach for shards of glass, as sorting glass is one challenging practical application for AOI.

Zusammenfassung

Bei Entwurf und Optimierung von Systemen zur automatischen optischen Inspektion ist eine systematische Evaluierung von großer Bedeutung, um hohe Qualität zu erreichen und zu garantieren, zugleich aber kostspielig. Methoden der Computergrafik können eingesetzt werden, um schnell große virtuelle Kontrollproben von Testobjekten zu erzeugen und die Bildgewinnung zu simulieren. Wir verwenden Techniken der prozeduralen Modellierung, um virtuelle Objekte in großer Vielfalt und mit variantenreichem Aussehen zu erzeugen, die reale Objekte und Messproben nachahmen. Physikalische Simulation von Starrkörpern wird verwendet, um die Platzierung der virtuellen Objekte zu simulieren, und mit physikalisch basierten Rendering-Methoden erzeugen wir synthetische Bilder. Diese Bilder werden als Eingabe für ein AOI-System anstatt physikalisch gewonnener Bilder eingesetzt. Dieses Vorgehen erlaubt eine Entwicklung, Verbesserung und Evaluierung der Bildverarbeitungs- und Klassifikationsschritte eines AOI-Systems unabhängig von einer physischen Realisierung. Wir demonstrieren den vorgestellten Ansatz für Glasscherben, da die Glassortierung eine anspruchsvolle praktische Anwendung der AOI darstellt.

Keywords: Computer graphics; procedural modeling; AOI; synthetic images; optimization

Schlagwörter: Computergrafik; prozedurale Modellierung; AOI; synthetische Bilder; Optimierung

About the article

Max-Gerd Retzlaff

Max-Gerd Retzlaff is pursuing his Ph.D. at the Karlsruhe Institute of Technology (KIT). In collaboration with the Fraunhofer IOSB he develops procedural models and sensor realistic rendering methods for the simulation and optimization of automatic optical inspection (AOI) systems.

Karlsruhe Institute of Technology (KIT), Institute for Visualization and Data Analysis, Computer Graphics Group, Am Fasanengarten 5, 76131 Karlsruhe, Germany; and Fraunhofer Institute of Optronics, System Technologies and Image Exploitation (IOSB), Fraunhoferstr. 1, 76131 Karlsruhe, Germany

Josua Stabenow

Josua Stabenow is studying computer science at the Karlsruhe Institute of Technology (KIT) and wrote his Bachelor's thesis at the Computer Graphics Group.

Karlsruhe Institute of Technology (KIT), Institute for Visualization and Data Analysis, Computer Graphics Group, Am Fasanengarten 5, 76131 Karlsruhe, Germany

Jürgen Beyerer

Jürgen Beyerer is full Professor for Informatics at the Institute for Anthropomatics and Robotics at the Karlsruhe Institute of Technology (KIT) since March 2004 and Head of the Fraunhofer Institute of Optronics, System Technologies and Image Exploitation (IOSB), Karlsruhe. Research interests include automated visual inspection, optimal acquisition of image data, image processing, statistical signal theory, metrology, information theory, fusion of data and information from heterogeneous sources, active vision, variable image acquisition and processing, and system theory.

Karlsruhe Institute of Technology (KIT), Institute for Anthropomatics and Robotics, Vision and Fusion Laboratory (IES), Adenauerring 4, 76131 Karlsruhe, Germany; and Fraunhofer Institute of Optronics, System Technologies and Image Exploitation (IOSB), Fraunhoferstr. 1, 76131 Karlsruhe, Germany

Carsten Dachsbacher

Carsten Dachsbacher is full professor for computer graphics and heading the Institute for Visualization and Data Analysis at the Karlsruhe Institute of Technology (KIT). Prior to joining KIT, he has been Assistant Professor at the University Stuttgart, and post-doctoral fellow at REVES/INRIA Sophia-Antipolis, France, within a Marie-Curie Fellowship. He received his Ph.D. from the University of Erlangen, Germany. His research includes real-time computer graphics, (interactive) global illumination, procedural modeling, GPU techniques, and visualization.

Karlsruhe Institute of Technology (KIT), Institute for Visualization and Data Analysis, Computer Graphics Group, Am Fasanengarten 5, 76131 Karlsruhe, Germany


Revised: 2015-03-20

Accepted: 2015-03-20

Received: 2015-01-31

Published Online: 2015-04-23

Published in Print: 2015-05-28


Citation Information: tm - Technisches Messen, ISSN (Online) 2196-7113, ISSN (Print) 0171-8096, DOI: https://doi.org/10.1515/teme-2014-0041.

Export Citation

©2015 Walter de Gruyter Berlin/Boston. Copyright Clearance Center

Comments (0)

Please log in or register to comment.
Log in