Transputer-based feature extraction and shape analysis

https://doi.org/10.1016/0141-9331(93)90054-BGet rights and content

Abstract

This paper describes computer vision software for a project, the aim of which is to develop a prototype of a fast, low-cost machine vision system for the inspection of surface mount electronic assemblies and solder joints. The system uses advanced edge detection and shape description software to analyse the board, taking data from a simple optical platform. This platform is used as opposed to more complex alternatives such as laser range-finding/profiling, structured light, thermal or X-ray techniques. Hence the sophistication of this system lies in the software and not in the data capture technology. Transputers are used to provide an economical means of attaining the necessary computational power for the image analysis. This leads to a low cost solution that would be attractive to surface mount manufacturers. This paper describes the software modules required to perform feature extraction and shape analysis for inspection and how the modules are parallelized to run on a transputer network.

References (11)

  • S Marshall

    Review of shape coding techniques

    Image Vision Comput.

    (November 1989)
  • W Richards et al.

    Codon constraints on closed 2D shapes

  • P Barnwell

    Alternative interconnection technology — a personal view

  • F Lilley et al.

    Visual inspection of surface mounted solder joints

    Circ. World

    (1990)
  • J Adams

    Inspection and data measurements for solder quality process control

    Circ. World

    (1988)
There are more references available in the full text version of this article.

Cited by (1)

  • Parallel implementations of convolution and moments algorithms on a multi-transputer system

    1995, Microprocessors and Microsystems
a

After graduating with a BSc in computer science from Kingston Polytechnic in 1989, Paul Netherwood remained with the School of Computer Science and Electronic Systems at Kingston, researching transputer-based machine vision systems for the inspection of surface mount assemblies. This work is currently in its third year and is towards a PhD. He also lectures on the computer science degree course on advanced architectures.

b

Peter Forte obtained his doctorate at the University of Sussex for his work in computer vision and shape analysis. He is currently at Kingston University in the School of Computer Science and Electronic Systems, where he lectures on software engineering and image processing.

c

Peter Barnwell is Professor of Electronics Manufacturing Technology at the University of Plymouth, UK. He is also a director of Custom Interconnect Ltd, a company working in the design and manufacture of surface mount and hybrid electronic circuits. He has a long-standing involvement in the microelectronics industry and was appointed an MBE on the New Year's Honours List, 1989, for his services to industry. Current research interests include hybrid and surface mount technologies, particularly for high power and high density applications.

View full text
Copyright © 1993 Published by Elsevier B.V.