Machine vision eyes the future

Friday, 14 May, 2004


Image processing is becoming an ever more important area for production and assembly. Industrial image processing is enjoying above-average growth. High innovations potential and sector-specific developments are further promoting this boom.

Four out of five companies expect that demand for industrial image processing systems will continue to increase. This was shown recently in a survey of over 500 companies conducted by a number of universities throughout Germany and further confirmed the boom in image processing technology.

Developments in the vision sector are making themselves felt in above-average rates of growth. Last year, on a worldwide basis, the field of industrial image processing grew by around 15 per cent and turnover in the sector was AU$1.35 trillion.

Joachim Rohwedder, Chairman of the Robotics and Automation Section of Germany's engineering federation, the VDMA, said: "This innovative technology is thus the 'shooting star' in the various sections of this trade grouping." He is not the only one expecting this trend to continue throughout this year, and for turnover in the sector to eventually reach the AU$2 trillion mark.

These expectations find further support from another survey carried out by the Fraunhofer Institute for Systems Technology and Innovations Research, based in Karlsruhe.

It came to the conclusion that automatic image processing is the best example of future standard technologies. This technology is spreading rapidly within companies and there is application for it in almost all companies. Experts claim that at present only 15 to 20 per cent of potential applications for industrial image processing systems are currently being implemented.

It was also found that demand for industrial image processing systems is rising in practically all branches of industry. And the requirements placed on these systems are very diverse. The suppliers have recognised this and are providing a range of products from simple optical sensors and cameras with integrated processors to compact measuring systems and compact PCs specifically made for image-processing applications.

It has been a fact for some time that image processing technology can make an important contribution to quality control.

Optical sensors enable a high degree of accuracy and reliability in identifying details that would escape the human eye. All sectors of industry are affected, but demands for reliable, accurate quality control are most evident in the food and pharmaceuticals industries. In many other areas, too, the quality criteria are far too rigorous to be able to rely on manual inspections.

In mass production processes, manual checking of individual items is of course not possible, given the high volumes. An example here would be quality control of eggs: the 95 billion eggs that are produced and consumed each year in the European Union alone for example can only be inspected using high-tech image processing. Any hairline cracks, damage or dirt has to be detected - conditions that easily find their equivalent in industrial production. Cameras with image-processing functions can easily and reliably identify hairline cracks in a cylinder head, for example. An important aspect of reliability is the proper setting up and co-ordination of all the elements involved: camera, lens, lighting, electronic analysis, interfaces and evaluation programs.

Automated controls enable large quantities to be checked, while keeping inspection quality at a constant high level. A good example of this is quality control techniques in the production of bottles. Any problems, such as glass splinters in the neck of the bottle, must be avoided. An image-processing system used to detect these has to be able to deliver reliable quality data and eject faulty products from the process. To be able to carry out this kind of task with standard systems, the suppliers of such systems are developing freely configurable user-interfaces for inspection systems designed to work with individual work pieces.

'Eye tracking' is a development that enables a glimpse of what is to come in the future. The basic principle behind this technology for machine vision is based on a high-performance camera tracking where the human eye looks.

In the first step, this enables an analysis of what's happening when we look at something like a web page, for example (where do we look first, and for how long?).

The 'processing' of this information goes far beyond this - as an 'artificial glance' can now be employed to control many technical systems simultaneously.

For further information contact Automatica or visit www.automatica-munich.com

Related Articles

Collaborative robots: the smarter way forward

Robots that can work side by side with humans are changing the way manufacturing is done.

AOG bringing the best of the best to Perth in 2015

With more than 620 companies queuing up to participate in this year's annual Australasian Oil...

Understanding data storage technologies

With the growing amounts of data being stored by industrial organisations today, understanding...


  • All content Copyright © 2024 Westwick-Farrow Pty Ltd