Steps to get ShapeLogic working from within ImageJ, from binary distribution

• Install ImageJ
• Download shapelogicplugin1.6.zip
• Unzip it
• This will create a directory named shapelogicplugin1.6/shapelogicplugin
• Inside this there are 2 dirs: ShapeLogic and ShapeLogicOld and 6 jar files
• Take these 2 dirs and all the jar files from this directory and copy it into ./ImageJ/plugins/

Testing ShapeLogic particle counter or particle analyzer from within ImageJ

• Open a particle image
• Under the shapelogic plugin menu select Particle Counter or Color Particle Analyzer
• Enter input parameters in dialog
• A result table with geometric information for each particle will be displayed

For more information see Particle Counter and Analyzer page.

Testing ShapeLogic letter matching from within ImageJ

• Open ImageJ
• Create a new image, 100 x 100 pixels works well
• Draw a letter in black on white background

Go to the shapelogic menu and select the macro CapitalLettersMatch, which does the following

• Convert the image to a binary image
• Call ImageJ's build in Skeletonize
• Call the ShapeLogic plugin Stream Vectorizer

If you already have a skeletonized lines you can also call Stream Vectorizer directly, which does the following

• Vectorize into bitmap into polygon
• Clean up the vectorized polygon
• Then annotate the polygon
• Then match the polygon against all the rules for all the capital letters
• With a little luck you will see a dialog box saying what letter was matched
• If more than one letter matches, the match will fail
• If the match fails then all the properties of the polygon will be written to the console for debugging

Input dialog

When you press CapitalLettersMatch or Stream Vectorizer an input dialog will prompt you for input:

DisplayInputDialog: If you uncheck this next time run CapitalLettersMatch this menu will not show up

DisplayResultTable: If this is checked you will see a result table with geometric features for each polygon

DisplayInternalInfo: Print out polygon, points and their annotations

UseNeuralNetwork: Use neural network for classification otherwise a rule set will be used

ShowFileDialog: If this is checked the user will be prompted with a file dialog to select categorizer setup file

CategorizerSetupFile: File path to the categorizer setup file containing neural networks, rules or column selection list

Result of match

Dialog with results of match

Vectorized M with skeletonized letter in black and polygon in gray

For more information see Letter Match page.

Steps to get ShapeLogic working from within ImageJ manually

If you need a different version of shapelogic_-1.6.jar, e.g. one compiled for JDK 1.7.

• Create a ShapeLogic dir under ImageJ: ./ImageJ/plugins/ShapeLogic
• Take the jar file for ShapeLogic: shapelogic_-1.6.jar, and move it to that directory
• Add the jar files that ShapeLogic is dependent on to the ImageJ/plugin dir:
  • antlr-runtime-3.0.jar
  • commons-collections-3.2.jar
  • commons-jexl-1.1.jar
  • commons-logging-1.0.4.jar
  • commons-math-1.1.jar
  • guice-1.0.jar

These jar file can be found on any Maven 2 repository:

E.g. commons-math-1.1.jar can be found here: http://repo1.maven.org/maven2/commons-math/commons-math/1.1/

Or they can be taken out of the shapelogicplugin1.6.zip

When you open ImageJ there will be a ShapeLogic menu containing commands.

You can get the binary distribution from the download page or compile it yourself.

How user can change Letter Matcher to recognize numbers instead

Until ShapeLogic 1.5 this demanded programming. Now you just load the categorizer setup file src/test/resources/data/neuralnetwork/polygon_digit_recognizer_with_rules_print.txt containing some simple rules:

========== def 0
holeCount == 1
tJunctionCount == 0
endPointCount == 0
multiLineCount == 1
curveArchCount > 0
hardPointCount == 0
softPointCount > 0

========== def 1
holeCount == 0
tJunctionLeftCount == 0
tJunctionRightCount == 0
endpointBottomPointCount == 1
horizontalLineCount == 0
verticalLineCount == 1
endPointCount == 2
multiLineCount == 0
softPointCount == 0
aspectRatio < 0.4


========== PRINTS
Category
Points
lineCount
holeCount

========== 

Future plans for user defined rules in ShapeLogic

Add the ability of the user to define lazy data stream in the categorizer setup file.

The rule sets and neural networks that are now defined in categorizer setup file could just as well be defined in a database.