You are here: Start » Program Examples » Blister Inspection (NET GmbH)

Blister Inspection (NET GmbH)

Aim

The task is to detect missing and broken pills in a blister.

Input

An image of a blister. The position of the object is variable, but limited.

Output

Detected missing and broken pills:

Hints

As variations of the object positions are limited, it can be located accurately with a very standard and fast Shape Fitting approach. With the two FitSegmentToEdges filters it is possible to locate the top and the left edges. The found rectangle can be used as a reference for further inspections.

In this case pills can be easily found using high level tools for color analysis like the CheckPresence_PixelAmount.

Labeling connections is explained in this article.

Solution (AVS)

  1. Create a variant macrofilter GrabImage with forking port inSource of type String.

  2. Add two variants Files and Camera. And create an output of type Image.

  3. To the variant Files add the EnumerateImages to get images from a directory. Connect a filter output to the GrabImage macrofilter output.

  4. To the variant Camera add the GigEVision_GrabImage filter to get images from your camera. If your camera does not support GigE Vision standard, use the other filter. Connect a filter output to the GrabImage macrofilter output.

  5. To find blister, horizontal and vertical edges must be found using a Shape Fitting technique. Add the two FitSegmentToEdges filters and setup scanning paths like on the image below. Set the inEdgeScanParams.EdgeTransition to DarkToBright.

  6. To find a top-left point of blister, the segments must be converted to lines. The top-left point will be the intersection of lines created from the found segments. Add the LineLineIntersection and connect found segments.

  7. To create the reference CoordinateSystem2D add the CreateCoordinateSystemFromPoint and connect its inPoint to it the previously created the LineLineIntersection output and its inAngle to the outSegment.Direction of the upper found segment.

  8. Label the outCoordinateSystem as the CoordinateSystem.

  9. When a reference system was found, places containing pills should be set. Create a new global parameter of type Circle2DArray and name it Circles.

  10. Set theCircles value like on the image below. Circles will be used to determine whether marked pill is damaged or not.

    Remember to set the CoordinateSystem output as the Coordinate system in the Circle Editor.

  11. To improve color analysis, the input image should be blurred. Blurring makes colors on the image more uniform. Add filter SmoothImage_Gauss and set inStdDevX to 3.0.

  12. Check presence of the pill using filter CheckPresence_PixelAmount.

    Selected colors can be found in the outForeground output. Result is showed on the image below.

  13. To CheckPresence_PixelAmount.inRoi connect Circles and to CheckPresence_PixelAmount.inRoiAlignment connect, earlier created, CoordinateSystem

  14. Using filter DrawShapeRegions_MultiColor draw results. Use data from the outIsPresent and outAlignedRoi.

Macrofilter Main

Macrofilter GrabImage(Files) loads images from a directory.

Macrofilter GrabImage(Camera) gets images from the camera using the GigEVision interface.

Used Filters

Icon Name Description
CreateCoordinateSystemFromPoint Most often used to define an object alignment from results of 1D Edge Detection or Blob Analysis.
CheckPresence_PixelAmount Quick and easy presence verification, e.g. for missing caps, screws, labels.
SmoothImage_Gauss Removal of gaussian noise from images.
EnumerateImages Emulates image acquisition with images stored on disk.
GigEVision_GrabImage The most recommended filter for working with GigE Vision devices.
DrawShapeRegions_MultiColor Draws shape regions on an image with multiple colors.
FitSegmentToEdges Precise detection of a straight edge, whose rough location is known beforehand.
LineLineIntersection Computes a common point of two lines.

Further Readings