Image acquisition and automated inspection of wine bottlenecks by tracking in multiple views

  • Authors:
  • Miguel Carrasco;Luis Pizarro;Domingo Mery

  • Affiliations:
  • Université Pierre et Marie Curie-Paris 6, Institut Systèmes Intelligents et Robotique, Ivry-sur-Seine, France and Pontificia Universidad Católica de Chile, Departamento de Ciencia d ...;Saarland University, Mathematical Image Analysis Group, Saarbrücken, Germany;Pontificia Universidad Católica de Chile, Departamento de Ciencia de la Computación, Santiago, Chile

  • Venue:
  • ISCGAV'08 Proceedings of the 8th conference on Signal processing, computational geometry and artificial vision
  • Year:
  • 2008

Quantified Score

Hi-index 0.01

Visualization

Abstract

In this paper we propose a prototype for image sequence acquisition of glass wine bottlenecks, whose main novelty is the use of an inner lighting source for better capturing of potential defects. A novel approach for automatic inspection of the bottlenecks based on tracking potential flaws along the acquired sequence is also presented. Our inspection system achieves performance rates of 87% true positives and 0% false positives.