Chaotic species based particle swarm optimization algorithms and its application in PCB components detection

  • Authors:
  • Na Dong;Chun-Ho Wu;Wai-Hung Ip;Zeng-Qiang Chen;Kai-Leung Yung

  • Affiliations:
  • School of Electrical Engineering and Automation, Tianjin Unversity, Tianjin 300072, China and Department of Industrial and Systems Engineering (ISE),The Hong Kong Polytechnic University, Hung Hom, ...;Department of Industrial and Systems Engineering (ISE),The Hong Kong Polytechnic University, Hung Hom, Kln, Hong Kong, China;Department of Industrial and Systems Engineering (ISE),The Hong Kong Polytechnic University, Hung Hom, Kln, Hong Kong, China;Department of Automation, Nankai Unversity, Tianjin 300071, China;Department of Industrial and Systems Engineering (ISE),The Hong Kong Polytechnic University, Hung Hom, Kln, Hong Kong, China

  • Venue:
  • Expert Systems with Applications: An International Journal
  • Year:
  • 2012

Quantified Score

Hi-index 12.05

Visualization

Abstract

An improved particle swarm optimizer using the notion of chaos and species is proposed for solving a template matching problem which is formulated as a multimodal optimization problem. Template matching is one of the image comparison techniques. This technique is widely applied to determine the existence, location and alignment of a component within a captured image in the printed circuit board (PCB) industry where 100% quality assurance is always required. In this research, an efficient auto detection method using a multiple templates matching technique for PCB components detection is described. The new approach using chaotic species based particle swarm optimization (SPSO) is applied to the multi-template matching (MTM) process. To test its performance, the proposed Chaotic SPSO based MTM algorithm is compared with other approaches by using real captured PCB images. The Chaotic SPSO based MTM method is proven to be superior to other methods in both efficiency and effectiveness.