Link Search Menu Expand Document

Extract Text From Areas - VB.NET

Text Recognition SDK sample in VB.NET demonstrating ‘Extract Text From Areas’

Module1.vb
Imports System.Drawing
Imports Bytescout.TextRecognition

Module Module1

    Sub Main()

        Dim inputDocument As String = ".\areas-sample.pdf"
        Dim pageIndex As Integer = 0
        Dim outputDocument As String = ".\result.txt"

        ' Create and activate TextRecognizer instance
        Using textRecognizer As TextRecognizer = New TextRecognizer("demo", "demo")

            Try
                ' Load document (image or PDF)
                textRecognizer.LoadDocument(inputDocument)

                ' Set the location of OCR language data files
                textRecognizer.OCRLanguageDataFolder = "c:\Program Files\ByteScout Text Recognition SDK\ocrdata_best\"

                ' Set OCR language.
                ' "eng" for english, "deu" for German, "fra" for French, "spa" for Spanish, etc. - according to files in "ocrdata" folder
                ' Find more language files at https://github.com/bytescout/ocrdata
                textRecognizer.OCRLanguage = "eng" 
                
                ' Get page size (in pixels). Size of PDF document is computed from PDF Points 
                ' and the rendering resoultion specified by `textRecognizer.PDFRenderingResolution` (default 300 DPI)
                Dim pageSize As Size = textRecognizer.GetPageSize(pageIndex)

                ' Add area of interest as a rectangle at the top-right corner of the page
                textRecognizer.RecognitionAreas.Add(pageSize.Width / 2, 0, pageSize.Width / 2, 300)
                ' Add area of interest as a rectangle at the bottom-left corner of the page,
                ' and indicate it should be rotated at 90 deg
                textRecognizer.RecognitionAreas.Add(0, pageSize.Height / 2, 300, pageSize.Height / 2, AreaRotation.Rotate90FlipNone)

                ' Now you can get recognized text for further analysis as a list of objects 
                ' containing coordinates, object kind, confidence.
                Dim ocrObjectList As OCRObjectList = textRecognizer.GetOCRObjects(pageIndex)
                For Each ocrObject As OCRObject In ocrObjectList
                    Console.WriteLine(ocrObject.ToString())
                Next

                ' ... or you can save recognized text pieces to file
                textRecognizer.KeepTextFormatting = False ' save without formatting
                textRecognizer.SaveText(outputDocument, pageIndex, pageIndex)


                ' Open the result file in default associated application (for demo purposes)
                Process.Start(outputDocument)

            Catch exception As Exception

                Console.WriteLine(exception)

            End Try

        End Using

    End Sub

End Module

Resources.Designer.vb
'------------------------------------------------------------------------------
' <auto-generated>
'     This code was generated by a tool.
'     Runtime Version:4.0.30319.42000
'
'     Changes to this file may cause incorrect behavior and will be lost if
'     the code is regenerated.
' </auto-generated>
'------------------------------------------------------------------------------

Option Strict On
Option Explicit On


Namespace My.Resources
    
    'This class was auto-generated by the StronglyTypedResourceBuilder
    'class via a tool like ResGen or Visual Studio.
    'To add or remove a member, edit your .ResX file then rerun ResGen
    'with the /str option, or rebuild your VS project.
    '''<summary>
    '''  A strongly-typed resource class, for looking up localized strings, etc.
    '''</summary>
    <Global.System.CodeDom.Compiler.GeneratedCodeAttribute("System.Resources.Tools.StronglyTypedResourceBuilder", "4.0.0.0"), _
     Global.System.Diagnostics.DebuggerNonUserCodeAttribute(), _
     Global.System.Runtime.CompilerServices.CompilerGeneratedAttribute(), _
     Global.Microsoft.VisualBasic.HideModuleNameAttribute()> _
    Friend Module Resources

        Private resourceMan As Global.System.Resources.ResourceManager

        Private resourceCulture As Global.System.Globalization.CultureInfo

        '''<summary>
        '''  Returns the cached ResourceManager instance used by this class.
        '''</summary>
        <Global.System.ComponentModel.EditorBrowsableAttribute(Global.System.ComponentModel.EditorBrowsableState.Advanced)> _
        Friend ReadOnly Property ResourceManager() As Global.System.Resources.ResourceManager
            Get
                If Object.ReferenceEquals(resourceMan, Nothing) Then
                    Dim temp As Global.System.Resources.ResourceManager = New Global.System.Resources.ResourceManager("TextRecognitionExample.Resources", GetType(Resources).Assembly)
                    resourceMan = temp
                End If
                Return resourceMan
            End Get
        End Property

        '''<summary>
        '''  Overrides the current thread's CurrentUICulture property for all
        '''  resource lookups using this strongly typed resource class.
        '''</summary>
        <Global.System.ComponentModel.EditorBrowsableAttribute(Global.System.ComponentModel.EditorBrowsableState.Advanced)> _
        Friend Property Culture() As Global.System.Globalization.CultureInfo
            Get
                Return resourceCulture
            End Get
            Set(ByVal value As Global.System.Globalization.CultureInfo)
                resourceCulture = value
            End Set
        End Property
    End Module
End Namespace

Settings.Designer.vb
'------------------------------------------------------------------------------
' <auto-generated>
'     This code was generated by a tool.
'     Runtime Version:4.0.30319.42000
'
'     Changes to this file may cause incorrect behavior and will be lost if
'     the code is regenerated.
' </auto-generated>
'------------------------------------------------------------------------------

Option Strict On
Option Explicit On


Namespace My

    <Global.System.Runtime.CompilerServices.CompilerGeneratedAttribute(), _
     Global.System.CodeDom.Compiler.GeneratedCodeAttribute("Microsoft.VisualStudio.Editors.SettingsDesigner.SettingsSingleFileGenerator", "10.0.0.0"), _
     Global.System.ComponentModel.EditorBrowsableAttribute(Global.System.ComponentModel.EditorBrowsableState.Advanced)> _
    Partial Friend NotInheritable Class MySettings
        Inherits Global.System.Configuration.ApplicationSettingsBase

        Private Shared defaultInstance As MySettings = CType(Global.System.Configuration.ApplicationSettingsBase.Synchronized(New MySettings), MySettings)

#Region "My.Settings Auto-Save Functionality"
#If _MyType = "WindowsForms" Then
        Private Shared addedHandler As Boolean

        Private Shared addedHandlerLockObject As New Object

        <Global.System.Diagnostics.DebuggerNonUserCodeAttribute(), Global.System.ComponentModel.EditorBrowsableAttribute(Global.System.ComponentModel.EditorBrowsableState.Advanced)> _
        Private Shared Sub AutoSaveSettings(ByVal sender As Global.System.Object, ByVal e As Global.System.EventArgs)
            If My.Application.SaveMySettingsOnExit Then
                My.Settings.Save()
            End If
        End Sub
#End If
#End Region

        Public Shared ReadOnly Property [Default]() As MySettings
            Get

#If _MyType = "WindowsForms" Then
                   If Not addedHandler Then
                        SyncLock addedHandlerLockObject
                            If Not addedHandler Then
                                AddHandler My.Application.Shutdown, AddressOf AutoSaveSettings
                                addedHandler = True
                            End If
                        End SyncLock
                    End If
#End If
                Return defaultInstance
            End Get
        End Property
    End Class
End Namespace

Namespace My
    
    <Global.Microsoft.VisualBasic.HideModuleNameAttribute(),  _
     Global.System.Diagnostics.DebuggerNonUserCodeAttribute(),  _
     Global.System.Runtime.CompilerServices.CompilerGeneratedAttribute()>  _
    Friend Module MySettingsProperty
        
        <Global.System.ComponentModel.Design.HelpKeywordAttribute("My.Settings")>  _
        Friend ReadOnly Property Settings() As Global.TextRecognitionExample.My.MySettings
            Get
                Return Global.TextRecognitionExample.My.MySettings.Default
            End Get
        End Property
    End Module
End Namespace

Download Source Code (.zip)

Return to the previous page Explore Text Recognition SDK