Advanced Imaging

AdvancedImagingPro.com

   

Advanced Imaging Magazine

Updated: January 12th, 2011 10:01 AM CDT

MV Software Becoming Integral Part of Color Imaging

Component Integration
True color format
Stemmer Imaging
By using a Bayer filter, images can be switched into a true color format.
Intuitive interpretation of colors
Euresys
By separating the achromatic black and white component (Intensity) from the chromatic components (Saturation and Hue) results in a more intuitive interpretation of colors.
Landscape image
MVTec Software
This merging of seven channels breaks down this landscape image.
Advertisement

By Barry Hochfelder

As color machine vision slowly, but steadily, evolves (see page 10), software naturally begins to play a more integral role. Today’s computers are processing color’s much larger data signals increasingly faster. Many software manufacturers are developing new algorithms and tailoring existing libraries to more efficiently meet the need.

Stemmer Imaging’s Common Vision Blox software, for example, is being used in a variety of applications. One example: inspecting oranges in Spain. To meet the need, a number of issues had to be solved.

  • The movement of the oranges is linear and they cannot be rotated.
  • Between 80 and 90 percent of the fruit’s surface had to be inspected.
  • The minimum resolution for the calibration was 1mm.
  • The customer defined the “sample” colors to determine differences.
  • The oranges were 70mm apart.

To meet the need, Stemmer’s Common Vision Blox Image Manager was used with two JAI cameras (M77 color and A11 monochromatic), a Dalsa PC2-Vision frame grabber and StockerYale illumination to identify the color, size and shape of the oranges.

In the system, two cameras are placed in two different positions on the line. Angled mirrors are placed in the field of both cameras to image three sides of each orange. The first camera is an RGB color model that uses an external trigger to capture the image. This camera determines the color of each piece of fruit, with four oranges captured on each image. The second camera is a monochrome model that also acquires four oranges per image and is used to calibrate the fruit.

“With the growing availability of software tools for both the analysis and processing of color images, as well as affordable yet high-quality color cameras, the color information becomes more and more noticed by the user,” says Volker Gimple, Group Manager, Software Development, at Stemmer Imaging. “Color now is an integral part of the image information. As a matter of fact, state-of-the-art algorithms for classification and object recognition like Common Vision Blox, utilize color as a decision criterion equivalent to geometric or brightness information.”

1 2 3 next


Subscribe to our RSS Feeds