You are here: Start » Program Examples » Tablets

Tablets

Aim

The aim of the program is to inspect a conveyor of a production line detecting missing or damaged tablets.

Input

A series of images from the conveyor of a production line. The image below is one of them.

Output

Detected missing or damaged tablets:

Hints

To detect damaged tablets it is recommended to consider using a DetectMultipleCircles filter together with a CheckPresence_Intensity filter to verify object presence by analysing pixel intensities. To ensure that the inspection is performed once for an every batch of tablets, you can specify a Region Of Interest, where the inspection should be performed, as an input of CheckPresence_EdgeAmount filter.

Solution (FIS)

Add an EnumerateImages filter to get load consecutive images of some disk directory..
Add a CheckPresence_EdgeAmount filter.
- Connect outImage from previous filter with inImage of the current one.
- In Properties window in the lower left corner set inEdgeScale to 2.
- In Properties window in the lower left corner set inMinAmount to 0.27.
- Right-click on inRoi and select Expand structure fields. In inRoi.Frame mark the ROI.
In Project Explorer find a "Create New Global Parameter" icon and click it. Set name to Roi and type to Region.
Now create a new Variant Step Macrofilter and name it AnalyzeTablets. Define forking port of Bool data type and name the input inTabletsPresent.
- Connect outImage to newly-created macrofilter.
- Connect outIsPresent with inTabletsPresent.
Now step into the AnalyzeTablets macrofilter. In "False" variant no changes should be made.
In variant "True" add a DetectMultipleCircles filter.
- Connect macrofilter input inImage with inImage.
- Connect global parameter Roi to inRoi.
- Set inRadius to 7, inMaxOverlap to 0, inMinScore to 15 and inEdgeThreshold to 6.
Add CircleBoundingBox filter. Connect outCircles.Circle with inCircle.
Add CheckPresence_Intensity filter.
- Connect macrofilter input inImage with inImage.
- Right-click on inRoi and select Expand structure fields.
- Connect outBoundingBox with inRoi.Frame.
- Set inMinContrast to 18.
Add DrawCircles_TwoColors filter.
- Connect macrofilter's input inImage with inImage.
- Connect outCircles.Circle with inCircles.
- Connect outIsPresent from previous filter with inConditions of the current one.
- Set inColorIfTrue to green, inColorIfFalse to red.
- Set inDrawingStyle.Opacity to 0.3.
- Set inDrawingStyle.Filled to True.
Add CropImage filter.
- Connect outImage with inImage.
- In inSelection choose the area to be cropped. If there is no reference image available, try to run the program first.
Connect outImage with macrofilter output.
Go back to Main and add LastNotNil filter (click "Choose later" while generic filter choosing) and connect macrofilter's output outImage with inObject.
Now create HMI by clicking on HMI Designer in the upper toolbar.
- Add videoBox and connect outImage to its input inImage. It is going to display the images from the production line.
- Add other videoBox and connect outImage from AnalyzeTablets to its input inImage.

Macrofilter Main

Macrofilter AnalyzeTablets(True) performs inspection when the pills caret is position.

Macrofilter AnalyzeTablets(False)

Used Filters

Icon	Name	Description
	EnumerateImages	Emulates image acquisition with images stored on disk.
	DetectMultipleCircles	Detection of circular or close-to-circular objects like holes, pins, pills, particles.
	CropImage	Reduction of the amount of image data to be stored in memory.
	CheckPresence_EdgeAmount	Quick and easy presence verification, e.g. for missing caps, screws, labels.
	CircleBoundingBox	Computes the smallest box containing a circle.
	CheckPresence_Intensity	Quick and easy presence verification, e.g. for missing caps, screws, labels.
	LastNotNil	Returns the last value passed that existed.