ByteScout Text Recognition SDK is the software development kit for automatic text recognition and OCR from pdf documents and images. Can recognize English and non-English languages.
On-demand (REST Web API) version:
Web API (on-demand version)
On-premise offline SDK for Windows:
60 Day Free Trial (on-premise)
Imports System
Imports System.Diagnostics
Imports Bytescout.TextRecognition
Module Module1
Sub Main()
Dim inputDocument As String = ".\ocr-sample.pdf"
Dim outputDocument As String = ".\result.json"
' 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"
' Recognize text from page and save objects as word to json file
textRecognizer.SaveOCRObjectsAsJSON(outputDocument, 0, OCRObjectType.Word)
' 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
60 Day Free Trial or Visit ByteScout Text Recognition SDK Home Page
Explore ByteScout Text Recognition SDK Documentation
Explore Samples
Sign Up for ByteScout Text Recognition SDK Online Training
Get Your API Key
Explore Web API Docs
Explore Web API Samples
<?xml version="1.0" encoding="utf-8"?>
<Project ToolsVersion="4.0" DefaultTargets="Build" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<PropertyGroup>
<Configuration Condition=" '$(Configuration)' == '' ">Debug</Configuration>
<Platform Condition=" '$(Platform)' == '' ">AnyCPU</Platform>
<ProductVersion>
</ProductVersion>
<SchemaVersion>
</SchemaVersion>
<ProjectGuid>{E5339352-1EBE-4547-B281-88D9FEEF92D7}</ProjectGuid>
<OutputType>Exe</OutputType>
<StartupObject>SaveOcrObjectAsJson.Module1</StartupObject>
<RootNamespace>SaveOcrObjectAsJson</RootNamespace>
<AssemblyName>SaveOcrObjectAsJson</AssemblyName>
<FileAlignment>512</FileAlignment>
<MyType>Console</MyType>
<TargetFrameworkVersion>v4.0</TargetFrameworkVersion>
<TargetFrameworkProfile>Client</TargetFrameworkProfile>
</PropertyGroup>
<PropertyGroup>
<OptionExplicit>On</OptionExplicit>
</PropertyGroup>
<PropertyGroup>
<OptionCompare>Binary</OptionCompare>
</PropertyGroup>
<PropertyGroup>
<OptionStrict>Off</OptionStrict>
</PropertyGroup>
<PropertyGroup>
<OptionInfer>On</OptionInfer>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)|$(Platform)' == 'Debug|AnyCPU'">
<DebugSymbols>true</DebugSymbols>
<DefineDebug>true</DefineDebug>
<DefineTrace>true</DefineTrace>
<OutputPath>bin\Debug\</OutputPath>
<DocumentationFile>SaveOcrObjectAsJson.xml</DocumentationFile>
<NoWarn>42016,41999,42017,42018,42019,42032,42036,42020,42021,42022</NoWarn>
<DebugType>full</DebugType>
<PlatformTarget>AnyCPU</PlatformTarget>
</PropertyGroup>
<PropertyGroup Condition="'$(Configuration)|$(Platform)' == 'Release|AnyCPU'">
<DefineTrace>true</DefineTrace>
<OutputPath>bin\Release\</OutputPath>
<DocumentationFile>SaveOcrObjectAsJson.xml</DocumentationFile>
<Optimize>true</Optimize>
<NoWarn>42016,41999,42017,42018,42019,42032,42036,42020,42021,42022</NoWarn>
<DebugType>pdbonly</DebugType>
<PlatformTarget>AnyCPU</PlatformTarget>
</PropertyGroup>
<ItemGroup>
<Reference Include="ByteScout.TextRecognition">
<HintPath>C:\Program Files\ByteScout Text Recognition SDK\net4.00\ByteScout.TextRecognition.dll</HintPath>
</Reference>
<Reference Include="System" />
<Reference Include="System.Core" />
<Reference Include="System.Drawing" />
<Reference Include="System.Xml.Linq" />
<Reference Include="System.Data" />
<Reference Include="System.Xml" />
</ItemGroup>
<ItemGroup>
<Compile Include="Module1.vb" />
</ItemGroup>
<ItemGroup>
<Content Include="..\..\ocr-sample.pdf">
<Link>ocr-sample.pdf</Link>
<CopyToOutputDirectory>Always</CopyToOutputDirectory>
</Content>
</ItemGroup>
<Import Project="$(MSBuildToolsPath)\Microsoft.VisualBasic.targets" />
<!-- To modify your build process, add your task inside one of the targets below and uncomment it.
Other similar extension points exist, see Microsoft.Common.targets.
<Target Name="BeforeBuild">
</Target>
<Target Name="AfterBuild">
</Target>
-->
</Project>
60 Day Free Trial or Visit ByteScout Text Recognition SDK Home Page
Explore ByteScout Text Recognition SDK Documentation
Explore Samples
Sign Up for ByteScout Text Recognition SDK Online Training
Get Your API Key
Explore Web API Docs
Explore Web API Samples
60 Day Free Trial or Visit ByteScout Text Recognition SDK Home Page
Explore ByteScout Text Recognition SDK Documentation
Explore Samples
Sign Up for ByteScout Text Recognition SDK Online Training
Get Your API Key
Explore Web API Docs
Explore Web API Samples