This year's Vision 2011 conference in Stuttgart, Germany, featured a Medical Discovery Tour throughout the show. The showcase will include exhibits by several suppliers of hardware and software aimed at medical applications, a growing area for machine vision.
This exhibit represents a homecoming of sorts. The relationship between machine vision and medical imaging is complex. Many nondestructive technologies now used in industrial inspection originated in medical imaging. Some of these technologies are now being used to inspect medical products on the assembly line, including products with vision capabilities, and to identify different classes of objects in automated medical laboratories.
The rapid growth in the number and variety of medical devices -- from handheld patient monitors to large instruments -- has meant a big jump in the use of machine vision for inspection during their manufacturing. It has also meant more machine vision hardware inside imaging devices used in doctor's offices, hospitals, and labs.
For instance, computed tomography (CT) and X-ray technologies are now recognized parts of high-end electronics and industrial inspection. CT inspection has been used for years in aerospace manufacturing to identify things such as cracks in engine turbine blades, and more recently it came to circuit board inspection. Now it's becoming an adjunct to 2D X-ray and optical inspection techniques for its ability to perform 3D inspection. Another technology that began in medical imaging is amorphous silicon X-ray detection, which has recently moved into inline circuit board inspection.
Several vision technologies are being deployed to inspect medical products during manufacturing. CT imaging provides many images of an object taken at different angles. These images can be combined into a single 3D image that serves as a model of the component, which is then analyzed via software for defects. CT imaging is especially helpful for inspecting the internal structures of complex manufactured shapes.
In the production of high-value components or products in fields that require a zero-defect quality level, such as medical, automotive, aerospace, and electronics, every single part must be inspected. That means throughput must be high, or the whole line gets slowed down. In the past, CT X-ray technology has been subject to inadequate processing power and slow camera frame rates, lowering throughput. CMOS image sensors are helping to change this by boosting camera frame rates and increasing sensitivity to light. For example, in the Shad-o-Box 1280 HS X-ray camera from Teledyne Dalsa's Rad-icon Imaging division, the CMOS sensor's resolution is 1.6 megapixels at 30fps, the image acquisition speed needed in high-speed, high-volume production lines.
Smart cameras such as those made by Vision Components already inspect medical devices on the production line and sort blood samples in automated medical laboratories by reading and analyzing their color codes and barcodes. Now, as part of desktop vision systems, the cameras are identifying surgical instruments in operating rooms by reading and analyzing their data matrix codes.
Just as color cameras have become more important in industrial machine vision for identifying different colored parts, so have color-recognition abilities in machine vision software. Color recognition in image processing software used for medical imaging, such as MVTec Software's HALCON 10, is especially important. Color classifier algorithms are key elements in the vision software used in automated labs for cytology, cell biology diagnostics, and tissue identification.
Interesting that technology that started out in medical equipment and made its way to manufacturing is now being tapped to improve the quality of manufacturing that equipment. Another great example of how technology travels full circle. Given the amount of imaging that's utilized in medical equipment, it stands to reason there's much more opportunity to apply machine vision equipment for garnering efficiencies and working out quality kinks on the production floor.
I visited a production line yesterday at a plant that does a lot of precision assembly using adhesives and laminates, and machine vision is utilized heavily to ensure quality (check tolerances, etc.) I was particularly struck by how robust the MV equipment has to be to handle the production rate, temp, vibration, etc. A tall order for such precision equipment.
Yes, machine vision is extremely rugged hardware compared to even consumer equipment, which is one of several reasons it's always been a lot more expensive. That's started to change recently with the use of more open platforms, but it's still got to be highly durable.
It makes sense that medical would be a great growth area for this technology, given the fact that handling is an issue for many medical parts. With cost coming down and electronic performance rising, though, it's natural that it would find new applications in a variety of other industries, such as aerospace and defense.
Machine vision has come a long way in both quality and price. With off the shelf components and Windows based software, the abiilty to include vision on most products as a quality check has never been more accessible.
Although several of the vision technologies mentioned in the article started in the medical industry, the origin of machine vision in inspection began in electronics. As the electronics content in other industries has risen, the need for more and better inspection has gone up. That's also happened as the need for higher quality of the end product has risen, even when electronics aren't a major part of the end product, such as consumer food containers.
Machine vision is becoming so ubiquitous in so many different types of products that a new organization, the Embedded Vision Alliance, formed recently to help unite some of these far-flung industries and development silos:
http://www.embedded-vision.com/
Unlike previous vision trade associations, it's not limited either by industry or geography.
Off the shelf components like NI modules for machine vision reduces time to develop machne vision considerbly for modern applications . This is a domain that will make waves in healthcare applications
might be a prime candidate for integrated machine vision. The vision components would have to be extremely small to fit on a heart-crawling robot like this one, but cameras are getting tinier all the time. And the integration of machine vision with robots is definitely a growing trend on the factory floor. Seeing them in surgery may not be far behind.
As energy efficiency becomes more and more a concern for makers of electronics devices, researchers are coming up with new ways to harvest energy from sound vibration, footsteps, and even electromagnetic fields in the air.
The government wants to study your brain, and DARPA wants to use similar information to give robots true autonomy beyond any artificial intelligence developed to date. Sound like science fiction? It's not.
By refining topologies and using new fluid technology, Moog's new peak sine drive controller increases available power without increasing controller volume.
From Dell / Intel® New Paradigms in Design Work Scott Hamilton, vertical market strategist for Dell Precision workstations, 5/2/2013 3
Early in my career, I worked as a draftsman and remember the days of drawing on vellum with numbered pencils and Mylar with plastic lead. This was a fun experience in the sense that I ...
I've been using workstations for more than 10 years and love finding ways to get more performance from my system. With demanding professional applications that require more power each ...
A lasting memory from my first job as an engineer in an auto assembly plant is standing on hard concrete at six in the morning, vending-machine coffee clutched in hand, listening to ...
A quick look into the merger of two powerhouse 3D printing OEMs and the new leader in rapid prototyping solutions, Stratasys. The industrial revolution is now led by 3D printing and engineers are given the opportunity to fully maximize their design capabilities, reduce their time-to-market and functionally test prototypes cheaper, faster and easier. Bruce Bradshaw, Director of Marketing in North America, will explore the large product offering and variety of materials that will help CAD designers articulate their product design with actual, physical prototypes. This broadcast will dive deep into technical information including application specific stories from real world customers and their experiences with 3D printing. 3D Printing is
To save this item to your list of favorite Design News content so you can find it later in your Profile page, click the "Save It" button next to the item.
If you found this interesting or useful, please use the links to the services below to share it with other readers. You will need a free account with each service to share an item via that service.
Tweet This
1 
