Study of lighting solutions in machine vision applications for automated assembly operations

Alberto Zorcolo, Gustavo Escobar-Palafox, Rosemary Gault, Robin Scott, Keith Ridgway

Research output: Contribution to journalConference Contribution

1 Citation (Scopus)

Abstract

The application of machine vision techniques represents an invaluable aid in many fields of manufacturing, from part inspection to metrology, robot guidance and assembly operations in general. An effective illumination of the working area constitutes a crucial aspect for optimising the performance of such techniques but unfortunately ideal light conditions are rarely available, especially if the vision system has to work within small areas, possibly close to metallic surfaces with high reflectivity. This work aims to investigate which factors mostly affect the accuracy in a typical feature recognition and measurement application. A first screening of a set of six factors was carried out by testing three different light sources, according to a two-level fractional factorial design of experiments (DOE), a Pareto analysis was performed in order to establish which parameters were the most significant. Once the key factors were identified, a second series of the experiments were carried out on a single light source, in order to optimise the key parameters and to provide useful guidelines on how to minimise measurement errors in different scenarios.
Original languageEnglish
Number of pages12
JournalIOP Conference Series: Materials Science and Engineering
Volume26
Issue number1
DOIs
Publication statusPublished - 2011
EventTrends in Aerospace Manufacturing Conference, TRAM09 - Rotherham , United Kingdom
Duration: 9 Sep 200910 Sep 2009

Keywords

  • assembly operations
  • automated assembly
  • feature recognition
  • fractional factorial designs
  • high reflectivity
  • key factors
  • key parameters
  • light conditions
  • lighting solutions
  • metallic surface
  • pareto analysis
  • robot guidance
  • small area
  • vision systems
  • working areas
  • design of experiments
  • experiments
  • feature extraction
  • light sources
  • manufacture
  • measurement errors
  • metallic compounds
  • computer vision

Fingerprint Dive into the research topics of 'Study of lighting solutions in machine vision applications for automated assembly operations'. Together they form a unique fingerprint.

  • Cite this