asposeocrjava 0.0.1

data/lib/asposeocrjava/OCR/ignorenontextualblocks.rb

@@ -0,0 +1,22 @@
+module Asposeocrjava
+  module IgnoreNonTextualBlocks
+    def initialize()
+        data_dir = File.dirname(File.dirname(File.dirname(File.dirname(__FILE__)))) + '/data/'
+                
+        # Initialize an instance of OcrEngine
+        ocr_engine = Rjb::import('com.aspose.ocr.OcrEngine').new
+
+        # Set the Image property by loading the image from file path location
+        ocr_engine.setImage(Rjb::import('com.aspose.ocr.ImageStream').fromFile(data_dir + 'ocr.png'))
+
+        # Set the RemoveNonText to true
+        ocr_engine.getConfig().setRemoveNonText(true)
+
+        # Process the image
+        if ocr_engine.process()
+            # Display the result
+            puts "Text: " + ocr_engine.getText().to_string
+        end
+    end
+  end
+end

data/lib/asposeocrjava/OCR/loadimagefromurl.rb

@@ -0,0 +1,17 @@
+module Asposeocrjava
+  module LoadImageFromUrl
+    def initialize()        
+        # Initialize an instance of OcrEngine
+        ocr_engine = Rjb::import('com.aspose.ocr.OcrEngine').new
+
+        # Set the Image property by loading the image from remote location
+        ocr_engine.setImage(Rjb::import('com.aspose.ocr.ImageStream').fromUrl("http://cdn.aspose.com/tmp/ocr-sample.bmp"))
+
+        # Process the image
+        if ocr_engine.process()
+            # Display the recognized text
+            puts "Text: " + ocr_engine.getText().to_string
+        end
+    end
+  end
+end

data/lib/asposeocrjava/OCR/multipagetiff.rb

@@ -0,0 +1,25 @@
+module Asposeocrjava
+  module MultipageTiff
+    def initialize()    
+        data_dir = File.dirname(File.dirname(File.dirname(File.dirname(__FILE__)))) + '/data/'
+
+        # Initialize an instance of OcrEngine
+        ocr_engine = Rjb::import('com.aspose.ocr.OcrEngine').new
+
+        # Set the Image property by loading the image from file path location
+        ocr_engine.setImage(Rjb::import('com.aspose.ocr.ImageStream').fromFile(data_dir + 'multipage.tiff'))
+
+        # Set OcrEngine.ProcessAllPages to true in order to process all pages of TIFF in single run
+        ocr_engine.setProcessAllPages(true)
+
+        # Process the image
+        if ocr_engine.process()
+            # Retrieve the list of Pages
+            pages = ocr_engine.getPages()
+            pages.each do |page|
+                puts "Text: " + page.getPageText().to_string
+            end
+        end
+    end
+  end
+end

data/lib/asposeocrjava/OCR/readpartinformationoftext.rb

@@ -0,0 +1,34 @@
+module Asposeocrjava
+  module ReadPartInformationOfText
+    def initialize()
+        data_dir = File.dirname(File.dirname(File.dirname(File.dirname(__FILE__)))) + '/data/'
+                
+        # Initialize an instance of OcrEngine
+        ocr_engine = Rjb::import('com.aspose.ocr.OcrEngine').new
+
+        # Set the Image property by loading the image from file path location
+        ocr_engine.setImage(Rjb::import('com.aspose.ocr.ImageStream').fromFile(data_dir + 'ocr.png'))
+
+        # Process the image
+        if ocr_engine.process()
+            # Display the recognized text
+            puts "Text: " + ocr_engine.getText().to_string
+
+            # Retrieve an array of recognized text by parts
+            text = ocr_engine.getText().getPartsInfo()
+            # Iterate over the text parts
+            i = 0
+            while i < text.length
+                symbol = text[i]
+                # Display part information
+                puts "isItalic : " + symbol.getItalic().to_s
+                puts "isUnderline : " + symbol.getUnderline().to_s
+                puts "isBold : " + symbol.getBold().to_s
+                puts "Text Color : " + symbol.getTextColor().to_string
+                puts "Quality : " + symbol.getCharactersQuality().to_s
+                i +=1
+            end
+        end
+    end
+  end
+end

data/lib/asposeocrjava/OCR/recognizetext.rb

@@ -0,0 +1,19 @@
+module Asposeocrjava
+  module RecognizeText
+    def initialize()
+        data_dir = File.dirname(File.dirname(File.dirname(File.dirname(__FILE__)))) + '/data/'
+                
+        # Initialize an instance of OcrEngine
+        ocr_engine = Rjb::import('com.aspose.ocr.OcrEngine').new
+
+        # Set the Image property by loading the image from file path location
+        ocr_engine.setImage(Rjb::import('com.aspose.ocr.ImageStream').fromFile(data_dir + 'ocr.png'))
+
+        # Process the image
+        if ocr_engine.process()
+            # Display the recognized text
+            puts "Text: " + ocr_engine.getText().to_string
+        end
+    end
+  end
+end

data/lib/asposeocrjava/OCR/recognizewhitelistedcharacters.rb

@@ -0,0 +1,38 @@
+module Asposeocrjava
+  module RecognizeWhiteListedCharacters
+    def initialize()
+        data_dir = File.dirname(File.dirname(File.dirname(File.dirname(__FILE__)))) + '/data/'
+                
+        # Initialize an instance of OcrEngine
+        ocr_engine = Rjb::import('com.aspose.ocr.OcrEngine').new
+
+        # Retrieve the OcrConfig of the OcrEngine object
+        ocr_config = ocr_engine.getConfig()
+
+        # Set the Whitelist property to recognize numbers only
+        #ocr_config.setWhitelist(['1', '2', '3', '4', '5', '6', '7', '8', '9', '0'])
+
+        # Set the Image property by loading the image from file path location
+        ocr_engine.setImage(Rjb::import('com.aspose.ocr.ImageStream').fromFile(data_dir + 'ocr.png'))
+
+        # Set the RemoveNonText to true
+        ocr_engine.getConfig().setRemoveNonText(true)
+
+        # Process the image
+        if ocr_engine.process()
+            text = ocr_engine.getText()
+            puts "Text: " + text.to_string
+             
+            expression = "(\\d+)"
+            # Create a Pattern object
+            pattern = Rjb::import('java.util.regex.Pattern').compile(expression)
+
+            # Now create matcher object
+            matcher = pattern.matcher(text.toString())
+            if matcher.find()
+                puts "Found value: " + matcher.group(0).to_string
+            end
+        end
+    end
+  end
+end

data/lib/asposeocrjava/OCR/workwithdifferentlanguages.rb

@@ -0,0 +1,25 @@
+module Asposeocrjava
+  module WorkWithDifferentLanguages
+    def initialize()
+        data_dir = File.dirname(File.dirname(File.dirname(File.dirname(__FILE__)))) + '/data/'
+                
+        # Initialize an instance of OcrEngine
+        ocr_engine = Rjb::import('com.aspose.ocr.OcrEngine').new
+
+        # Set the Image property by loading the image from file path location
+        ocr_engine.setImage(Rjb::import('com.aspose.ocr.ImageStream').fromFile(data_dir + 'spanish.png'))
+
+        # Clear the default language (English)
+        ocr_engine.getLanguageContainer().clear()
+
+        # Load the resources of the language from file path location or an instance of InputStream
+        ocr_engine.getLanguageContainer().addLanguage(Rjb::import('com.aspose.ocr.LanguageFactory').load(data_dir + "SpanishLanguageResources.zip"))
+
+        # Process the image
+        if ocr_engine.process()
+            # Display the recognized text
+            puts "Text: " + ocr_engine.getText().to_string
+        end
+    end
+  end
+end

data/lib/asposeocrjava/OMR/detectimageresolution.rb

@@ -0,0 +1,48 @@
+module Asposeocrjava
+  module DetectImageResolution
+    def initialize()
+        data_dir = File.dirname(File.dirname(File.dirname(File.dirname(__FILE__)))) + '/data/'
+                
+        # Initialize a string with template file location
+        template_file = data_dir + "template.amr"
+        
+        # Initialize a string with scanned image file location
+        image_file = data_dir + "sample_omr.jpg"
+        
+        # Create an instance of OmrTemplate class and load the template using the factory method Load
+        template = Rjb::import('com.aspose.omr.OmrTemplate').load(template_file)
+        
+        # Create an instance of OmrImage class and load the template using the factory method Load
+        image = Rjb::import('com.aspose.omr.OmrImage').load(image_file)
+
+        # Set the auto image resolution detection property
+        image.setAutoDetectResolution(true)
+
+        # Create an instance of OmrEngine class
+        engine = Rjb::import('com.aspose.omr.OmrEngine').new(template)
+        
+        # Extract the OMR data
+        result = engine.extractData(Array[image])
+        
+        # Get page data of extracted data
+        pages = result.getPageData()
+
+        index = 0
+        # Iterate over the pages and display the data
+        pages.each do |page|
+            index +=1
+            puts "------Page: " + index.to_s
+            keys = page.keySet()
+            keys = keys.to_string
+            keys = keys[1, keys.length - 2]
+            
+            keys = keys.split(",")
+            keys.each do |key|
+                value = page.get(key)
+                puts "key: " + key.to_s
+                puts "value: " + value.to_s
+            end
+        end
+    end
+  end
+end

data/lib/asposeocrjava/OMR/extractomrdatafromimage.rb

@@ -0,0 +1,45 @@
+module Asposeocrjava
+  module ExtractOmrDataFromImage
+    def initialize()
+        data_dir = File.dirname(File.dirname(File.dirname(File.dirname(__FILE__)))) + '/data/'
+                
+        # Initialize a string with template file location
+        template_file = data_dir + "template.amr"
+        
+        # Initialize a string with scanned image file location
+        image_file = data_dir + "sample_omr.jpg"
+        
+        # Create an instance of OmrTemplate class and load the template using the factory method Load
+        template = Rjb::import('com.aspose.omr.OmrTemplate').load(template_file)
+        
+        # Create an instance of OmrImage class and load the template using the factory method Load
+        image = Rjb::import('com.aspose.omr.OmrImage').load(image_file)
+
+        # Create an instance of OmrEngine class
+        engine = Rjb::import('com.aspose.omr.OmrEngine').new(template)
+        
+        # Extract the OMR data
+        result = engine.extractData(Array[image])
+        
+        # Get page data of extracted data
+        pages = result.getPageData()
+
+        index = 0
+        # Iterate over the pages and display the data
+        pages.each do |page|
+            index +=1
+            puts "------Page: " + index.to_s
+            keys = page.keySet()
+            keys = keys.to_string
+            keys = keys[1, keys.length - 2]
+            
+            keys = keys.split(",")
+            keys.each do |key|
+                value = page.get(key)
+                puts "key: " + key.to_s
+                puts "value: " + value.to_s
+            end
+        end
+    end
+  end
+end

data/lib/asposeocrjava/OMR/setimageresolution.rb

@@ -0,0 +1,20 @@
+module Asposeocrjava
+  module SetImageResolution
+    def initialize()
+        data_dir = File.dirname(File.dirname(File.dirname(File.dirname(__FILE__)))) + '/data/'
+                
+        # Initialize a string with template file location
+        image_file = data_dir + "sample_omr.jpg"
+
+        # Create an instance of OmrImage class and load the template using the factory method Load
+        image = Rjb::import('com.aspose.omr.OmrImage').load(image_file)
+        
+        # Define new value of image resolution in double format
+        image.setResolution(210.0) # overwrites the old DPI value
+
+        # Do processing
+
+        puts "Set image resolution."
+    end
+  end
+end

data/lib/asposeocrjava/OMR/setmarkthreshold.rb

@@ -0,0 +1,74 @@
+module Asposeocrjava
+  module SetMarkThreshold
+    def initialize()
+        # Setting Global Threshold
+        set_global_threshold()
+
+        # Setting Page Level Threshold
+        set_page_level_threshold()
+    end
+
+    def set_global_threshold()
+        data_dir = File.dirname(File.dirname(File.dirname(File.dirname(__FILE__)))) + '/data/'
+                
+        # Initialize a string with template file location
+        template_file = data_dir + "template.amr"
+        
+        # Initialize a string with scanned image file location
+        image_file = data_dir + "sample_omr.jpg"
+        
+        # Create an instance of OmrTemplate class and load the template using the factory method Load
+        template = Rjb::import('com.aspose.omr.OmrTemplate').load(template_file)
+        
+        # Create an instance of OmrImage class and load the template using the factory method Load
+        image = Rjb::import('com.aspose.omr.OmrImage').load(image_file)
+
+        # Create an instance of OmrEngine class
+        engine = Rjb::import('com.aspose.omr.OmrEngine').new(template)
+
+        # Get the configurations of OmrEngine
+        config = engine.getConfiguration()
+
+        # Set fill threshold
+        config.setFillThreshold(0.12)
+
+        # Extract the OMR data
+        result = engine.extractData(Array[image])
+
+        puts "Set global threshold."
+    end
+
+    def set_page_level_threshold()
+        data_dir = File.dirname(File.dirname(File.dirname(File.dirname(__FILE__)))) + '/data/'
+                
+        # Initialize a string with template file location
+        template_file = data_dir + "template.amr"
+        
+        # Initialize a string with scanned image file location
+        image_file = data_dir + "sample_omr.jpg"
+        
+        # Create an instance of OmrTemplate class and load the template using the factory method Load
+        template = Rjb::import('com.aspose.omr.OmrTemplate').load(template_file)
+        
+        # Create an instance of OmrImage class and load the template using the factory method Load
+        image = Rjb::import('com.aspose.omr.OmrImage').load(image_file)
+
+        # Get the first page of the template
+        page = template.getPages().getItem(0)
+
+        # Create page configurations
+        page.setConfiguration(Rjb::import('com.aspose.omr.OmrConfig').new)
+
+        # Set fill threshold
+        page.getConfiguration().setFillThreshold(0.21)
+
+        # Create an instance of OmrEngine class
+        engine = Rjb::import('com.aspose.omr.OmrEngine').new(template)
+
+        # Extract the OMR data
+        result = engine.extractData(Array[image])
+
+        puts "Set page level threshold."
+    end
+  end
+end

data/lib/asposeocrjava/asposeocr.rb

@@ -0,0 +1,2 @@
+require_relative 'ocr'
+require_relative 'omr'

data/lib/asposeocrjava/ocr.rb

@@ -0,0 +1,13 @@
+require_relative 'OCR/recognizetext'
+require_relative 'OCR/readpartinformationoftext'
+require_relative 'OCR/extracttextfrompartofimage'
+require_relative 'OCR/loadimagefromurl'
+require_relative 'OCR/multipagetiff'
+require_relative 'OCR/gettextparthierarchyoftext'
+require_relative 'OCR/applycorrectionfilters'
+require_relative 'OCR/correctspellings'
+require_relative 'OCR/detectreading'
+require_relative 'OCR/detecttextblocks'
+require_relative 'OCR/ignorenontextualblocks'
+require_relative 'OCR/recognizewhitelistedcharacters'
+require_relative 'OCR/workwithdifferentlanguages'

data/lib/asposeocrjava/omr.rb

@@ -0,0 +1,4 @@
+require_relative 'OMR/extractomrdatafromimage'
+require_relative 'OMR/setmarkthreshold'
+require_relative 'OMR/setimageresolution'
+require_relative 'OMR/detectimageresolution'

data/lib/asposeocrjava/version.rb

@@ -0,0 +1,3 @@
+module Asposeocrjava
+  VERSION = '0.0.1'
+end

data/samples/ocr.rb

@@ -0,0 +1,21 @@
+=begin
+	Please uncomment the code which you want to execute.
+=end
+
+require '../lib/asposeocrjava'
+include Asposeocrjava
+#include Asposeocrjava::RecognizeText
+#include Asposeocrjava::ReadPartInformationOfText
+#include Asposeocrjava::ExtractTextFromPartOfImage
+#include Asposeocrjava::LoadImageFromUrl
+#include Asposeocrjava::MultipageTiff
+#include Asposeocrjava::GetTextPartHierarchyOfText
+#include Asposeocrjava::ApplyCorrectionFilters
+#include Asposeocrjava::CorrectSpellings
+#include Asposeocrjava::DetectReading
+#include Asposeocrjava::DetectTextBlocks
+#include Asposeocrjava::IgnoreNonTextualBlocks
+#include Asposeocrjava::RecognizeWhiteListedCharacters
+#include Asposeocrjava::WorkWithDifferentLanguages
+
+initialize_aspose_ocr

data/samples/omr.rb

@@ -0,0 +1,12 @@
+=begin
+	Please uncomment the code which you want to execute.
+=end
+
+require '../lib/asposeocrjava'
+include Asposeocrjava
+#include Asposeocrjava::ExtractOmrDataFromImage
+#include Asposeocrjava::SetMarkThreshold
+#include Asposeocrjava::SetImageResolution
+#include Asposeocrjava::DetectImageResolution
+
+initialize_aspose_ocr