Detection for Pickup Errors by Artificial Neural Networks

  • Authors:

  • Hirotake Esaki;Taizo Umezaki;Tetsumi Horikoshi

  • Affiliations:

  • Graduate School of Engineering, Nagoya Institute of Technology, Nagoya, Japan 466-8555;Graduate School of Engineering, Nagoya Institute of Technology, Nagoya, Japan 466-8555;Graduate School of Engineering, Nagoya Institute of Technology, Nagoya, Japan 466-8555

  • Venue:
  • Neural Information Processing
  • Year:
  • 2008

Quantified Score

Hi-index 0.00

Visualization

Abstract

Taping machines, chip mounters and surface mount device (SMD) inspection systems use image processing techniques for the positioning of SMDs. The improvement of the production quality as well as the productivity is strongly requested in these systems. The image processing system in these systems have inspection functions to improve production quality. Generally, images of the part being picked up by the nozzle are acquired in a horizontal direction, and pickup errors are detected by processing these images. The aim of this paper is to develop a system for detecting pickup errors by processing images of parts acquired from the bottom. By using our proposed method, the detection rate of pickup errors is 99.3%.