Advanced Imaging


Advanced Imaging Magazine

Updated: July 8th, 2008 05:26 PM CDT

It's a Divide and Conquer World

MVTec's Halcon 7.1 is one example of a new approach to processing.
Olaf Munkelt, Managing Director of MVTec.
The MathWorks
The MathWorks develops software for surveillance and unmanned aerial vehicle (UAV) applications.
Lambda Research Corp.
Lambda Research Corp.'s TracePro (shown here) and OSLO are based on geometrical ray tracing, and are used in optical lens design.

Larry Adams By Larry Adams

In the past, machine vision was dominated by cameras, frame grabbers—image-acquisition devices in general—and less attention was paid to software. Innovations still abound in image acquisition today, but a multi-tasking renaissance of sorts is happening in image processing and manipulation. We can acquire just about any image possible. Now we’re discovering all the things we can do with the acquired image. And as we shall see, software is the harbinger of a new era in electronic imaging—not just for processing captured data in multiple ways, but also for design purposes.

Improving The Images

While it’s true that almost anything can be imaged, the results of acquisition vary widely. “We rely on the images that we get from image acquisition hardware,” says Olaf Munkelt, president of MVTech (Munich). “But, in many circumstances, these images are not that good.”

Often images are taken in areas that have poor illumination, such as an assembly line. A manufacturing environment is not only noisy and dirty, it offers challenges like aligning the target object, centering the object for best imaging, and lighting it for best results. Because assembly-line imaging is literally a moving target, imaging software must shift images left, right, up, or down. And some parts produced in a factory, particularly metal objects, can be problematic because of variation in gray values.

Today’s software compensates well. “That is where the flexibility of the software comes into play,” says Munkelt. “Today’s software can implement shading correction or do matching algorithms. We have implemented many segmentation algorithms and we can read characters under different conditions.”

Because imaging professionals rely so heavily on perfecting an image post-acquisition, customers now expect more functionality and flexibility. The good news is they’re getting it. This is why many of today’s programs are capable of blob analysis, pattern matching, OCR, 3-D, and other features and advanced algorithms. “Today, people expect plug and play products and seamless integration of imaging hardware and software,” Munkelt continues. “There are huge numbers of frame grabbers and image acquisition devices. We offer a uniform view of these different image acquisition devices. The canned version of these functions allows us to access that hardware.” MVTec’s HALCON 7.1, includes PDF417, 3-D positioning, data code readers and 64-bit technology under Windows (the latter feature reducing processing times by 30 percent, according to MVTec).

1 2 3 4 5 next

Subscribe to our RSS Feeds