TheLab/ocr-tesseract
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

Initial commit

Browse Source
This commit is contained in:
Ray 2024-05-24 11:55:28 +01:00
commit 4aa1edb842
12 changed files with 355 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
#research/New Text Document.txt Normal file
View File

@ -0,0 +1,2 @@
https://github.com/charlesw/tesseract/
https://github.com/charlesw/tesseract-samples/tree/master

BIN
#research/tessdata-main.zip Normal file
View File

Binary file not shown.

BIN
#research/tesseract-samples-master.zip Normal file
View File

Binary file not shown.

4
.gitignore vendored Normal file
View File

@ -0,0 +1,4 @@
/.git
/.vs
/bin
/obj

59
Form1.Designer.cs generated Normal file
View File

@ -0,0 +1,59 @@
namespace WinFormsApp3
{
partial class Form1
{
/// <summary>
/// Required designer variable.
/// </summary>
private System.ComponentModel.IContainer components = null;
/// <summary>
/// Clean up any resources being used.
/// </summary>
/// <param name="disposing">true if managed resources should be disposed; otherwise, false.</param>
protected override void Dispose(bool disposing)
{
if (disposing && (components != null))
{
components.Dispose();
}
base.Dispose(disposing);
}
#region Windows Form Designer generated code
/// <summary>
/// Required method for Designer support - do not modify
/// the contents of this method with the code editor.
/// </summary>
private void InitializeComponent()
{
button1 = new Button();
SuspendLayout();
//
// button1
//
button1.Location = new Point(574, 237);
button1.Name = "button1";
button1.Size = new Size(75, 23);
button1.TabIndex = 0;
button1.Text = "button1";
button1.UseVisualStyleBackColor = true;
button1.Click += button1_Click;
//
// Form1
//
AutoScaleDimensions = new SizeF(7F, 15F);
AutoScaleMode = AutoScaleMode.Font;
ClientSize = new Size(800, 450);
Controls.Add(button1);
Name = "Form1";
Text = "Form1";
ResumeLayout(false);
}
#endregion
private Button button1;
}
}

89
Form1.cs Normal file
View File

@ -0,0 +1,89 @@
using System.Diagnostics;
using Tesseract;
namespace WinFormsApp3
{
public partial class Form1 : Form
{
public Form1()
{
InitializeComponent();
}
private void button1_Click(object sender, EventArgs e)
{
var basePath = Path.GetFullPath(Path.GetDirectoryName(Application.ExecutablePath) + "\\..\\..\\..\\");
var testImagePath = Path.Combine(basePath, "Scan_ADFPA_Letter_page-0001.jpg");
try
{
using (var engine = new TesseractEngine(@"./tessdata", "eng", EngineMode.Default))
{
using (var img = Pix.LoadFromFile(testImagePath))
{
using (var page = engine.Process(img))
{
//var tt1 = page.GetLSTMBoxText(0);
//var tt1 = page.GetAltoText(0);
//var tt1 = page.GetBoxText(0);
//var tt1 = page.GetHOCRText(0);
//var tt1 = page.GetMeanConfidence();
//var tt1 = page.GetText();
var tt1 = page.GetUNLVText();
//Console.WriteLine("Mean confidence: {0}", page.GetMeanConfidence());
//Console.WriteLine("Text (GetText): \r\n{0}", text);
//Console.WriteLine("Text (iterator):");
//using (var iter = page.GetIterator())
//{
// iter.Begin();
// do
// {
// do
// {
// do
// {
// do
// {
// if (iter.IsAtBeginningOf(PageIteratorLevel.Block))
// {
// Console.WriteLine("<BLOCK>");
// }
// Console.Write(iter.GetText(PageIteratorLevel.Word));
// Console.Write(" ");
// if (iter.IsAtFinalOf(PageIteratorLevel.TextLine, PageIteratorLevel.Word))
// {
// Console.WriteLine();
// }
// } while (iter.Next(PageIteratorLevel.TextLine, PageIteratorLevel.Word));
// if (iter.IsAtFinalOf(PageIteratorLevel.Para, PageIteratorLevel.TextLine))
// {
// Console.WriteLine();
// }
// } while (iter.Next(PageIteratorLevel.Para, PageIteratorLevel.TextLine));
// } while (iter.Next(PageIteratorLevel.Block, PageIteratorLevel.Para));
// } while (iter.Next(PageIteratorLevel.Block));
//}
}
}
}
}
catch (Exception exc)
{
Trace.TraceError(exc.ToString());
Console.WriteLine("Unexpected Error: " + exc.Message);
Console.WriteLine("Details: ");
Console.WriteLine(exc.ToString());
}
}
}
}

120
Form1.resx Normal file
View File

@ -0,0 +1,120 @@
<?xml version="1.0" encoding="utf-8"?>
<root>
<!--
Microsoft ResX Schema
Version 2.0
The primary goals of this format is to allow a simple XML format
that is mostly human readable. The generation and parsing of the
various data types are done through the TypeConverter classes
associated with the data types.
Example:
... ado.net/XML headers & schema ...
<resheader name="resmimetype">text/microsoft-resx</resheader>
<resheader name="version">2.0</resheader>
<resheader name="reader">System.Resources.ResXResourceReader, System.Windows.Forms, ...</resheader>
<resheader name="writer">System.Resources.ResXResourceWriter, System.Windows.Forms, ...</resheader>
<data name="Name1"><value>this is my long string</value><comment>this is a comment</comment></data>
<data name="Color1" type="System.Drawing.Color, System.Drawing">Blue</data>
<data name="Bitmap1" mimetype="application/x-microsoft.net.object.binary.base64">
<value>[base64 mime encoded serialized .NET Framework object]</value>
</data>
<data name="Icon1" type="System.Drawing.Icon, System.Drawing" mimetype="application/x-microsoft.net.object.bytearray.base64">
<value>[base64 mime encoded string representing a byte array form of the .NET Framework object]</value>
<comment>This is a comment</comment>
</data>
There are any number of "resheader" rows that contain simple
name/value pairs.
Each data row contains a name, and value. The row also contains a
type or mimetype. Type corresponds to a .NET class that support
text/value conversion through the TypeConverter architecture.
Classes that don't support this are serialized and stored with the
mimetype set.
The mimetype is used for serialized objects, and tells the
ResXResourceReader how to depersist the object. This is currently not
extensible. For a given mimetype the value must be set accordingly:
Note - application/x-microsoft.net.object.binary.base64 is the format
that the ResXResourceWriter will generate, however the reader can
read any of the formats listed below.
mimetype: application/x-microsoft.net.object.binary.base64
value : The object must be serialized with
: System.Runtime.Serialization.Formatters.Binary.BinaryFormatter
: and then encoded with base64 encoding.
mimetype: application/x-microsoft.net.object.soap.base64
value : The object must be serialized with
: System.Runtime.Serialization.Formatters.Soap.SoapFormatter
: and then encoded with base64 encoding.
mimetype: application/x-microsoft.net.object.bytearray.base64
value : The object must be serialized into a byte array
: using a System.ComponentModel.TypeConverter
: and then encoded with base64 encoding.
-->
<xsd:schema id="root" xmlns="" xmlns:xsd="http://www.w3.org/2001/XMLSchema" xmlns:msdata="urn:schemas-microsoft-com:xml-msdata">
<xsd:import namespace="http://www.w3.org/XML/1998/namespace" />
<xsd:element name="root" msdata:IsDataSet="true">
<xsd:complexType>
<xsd:choice maxOccurs="unbounded">
<xsd:element name="metadata">
<xsd:complexType>
<xsd:sequence>
<xsd:element name="value" type="xsd:string" minOccurs="0" />
</xsd:sequence>
<xsd:attribute name="name" use="required" type="xsd:string" />
<xsd:attribute name="type" type="xsd:string" />
<xsd:attribute name="mimetype" type="xsd:string" />
<xsd:attribute ref="xml:space" />
</xsd:complexType>
</xsd:element>
<xsd:element name="assembly">
<xsd:complexType>
<xsd:attribute name="alias" type="xsd:string" />
<xsd:attribute name="name" type="xsd:string" />
</xsd:complexType>
</xsd:element>
<xsd:element name="data">
<xsd:complexType>
<xsd:sequence>
<xsd:element name="value" type="xsd:string" minOccurs="0" msdata:Ordinal="1" />
<xsd:element name="comment" type="xsd:string" minOccurs="0" msdata:Ordinal="2" />
</xsd:sequence>
<xsd:attribute name="name" type="xsd:string" use="required" msdata:Ordinal="1" />
<xsd:attribute name="type" type="xsd:string" msdata:Ordinal="3" />
<xsd:attribute name="mimetype" type="xsd:string" msdata:Ordinal="4" />
<xsd:attribute ref="xml:space" />
</xsd:complexType>
</xsd:element>
<xsd:element name="resheader">
<xsd:complexType>
<xsd:sequence>
<xsd:element name="value" type="xsd:string" minOccurs="0" msdata:Ordinal="1" />
</xsd:sequence>
<xsd:attribute name="name" type="xsd:string" use="required" />
</xsd:complexType>
</xsd:element>
</xsd:choice>
</xsd:complexType>
</xsd:element>
</xsd:schema>
<resheader name="resmimetype">
<value>text/microsoft-resx</value>
</resheader>
<resheader name="version">
<value>2.0</value>
</resheader>
<resheader name="reader">
<value>System.Resources.ResXResourceReader, System.Windows.Forms, Version=4.0.0.0, Culture=neutral, PublicKeyToken=b77a5c561934e089</value>
</resheader>
<resheader name="writer">
<value>System.Resources.ResXResourceWriter, System.Windows.Forms, Version=4.0.0.0, Culture=neutral, PublicKeyToken=b77a5c561934e089</value>
</resheader>
</root>

17
Program.cs Normal file
View File

@ -0,0 +1,17 @@
namespace WinFormsApp3
{
internal static class Program
{
/// <summary>
/// The main entry point for the application.
/// </summary>
[STAThread]
static void Main()
{
// To customize application configuration such as set high DPI settings or default font,
// see https://aka.ms/applicationconfiguration.
ApplicationConfiguration.Initialize();
Application.Run(new Form1());
}
}
}

BIN
Scan_ADFPA_Letter_page-0001.jpg Normal file
View File

Binary file not shown.
Side by Side

After

Width:  |  Height:  |  Size: 692 KiB

31
WinFormsApp3.csproj Normal file
View File

@ -0,0 +1,31 @@
<Project Sdk="Microsoft.NET.Sdk">
<PropertyGroup>
<OutputType>WinExe</OutputType>
<TargetFramework>net8.0-windows</TargetFramework>
<Nullable>enable</Nullable>
<UseWindowsForms>true</UseWindowsForms>
<ImplicitUsings>enable</ImplicitUsings>
</PropertyGroup>
<ItemGroup>
<PackageReference Include="Tesseract" Version="5.2.0" />
</ItemGroup>
<ItemGroup>
<None Remove="C:\Users\rxl\.nuget\packages\tesseract\5.2.0\build\\..\x64\leptonica-1.82.0.dll" />
</ItemGroup>
<ItemGroup>
<None Remove="C:\Users\rxl\.nuget\packages\tesseract\5.2.0\build\\..\x64\tesseract50.dll" />
</ItemGroup>
<ItemGroup>
<None Remove="C:\Users\rxl\.nuget\packages\tesseract\5.2.0\build\\..\x86\leptonica-1.82.0.dll" />
</ItemGroup>
<ItemGroup>
<None Remove="C:\Users\rxl\.nuget\packages\tesseract\5.2.0\build\\..\x86\tesseract50.dll" />
</ItemGroup>
</Project>

8
WinFormsApp3.csproj.user Normal file
View File

@ -0,0 +1,8 @@
<?xml version="1.0" encoding="utf-8"?>
<Project ToolsVersion="Current" xmlns="http://schemas.microsoft.com/developer/msbuild/2003">
<ItemGroup>
<Compile Update="Form1.cs">
<SubType>Form</SubType>
</Compile>
</ItemGroup>
</Project>

25
WinFormsApp3.sln Normal file
View File

@ -0,0 +1,25 @@

Microsoft Visual Studio Solution File, Format Version 12.00
# Visual Studio Version 17
VisualStudioVersion = 17.9.34728.123
MinimumVisualStudioVersion = 10.0.40219.1
Project("{FAE04EC0-301F-11D3-BF4B-00C04F79EFBC}") = "WinFormsApp3", "WinFormsApp3.csproj", "{3BF8E366-F9EF-484B-8FAF-F2ADB8854C41}"
EndProject
Global
GlobalSection(SolutionConfigurationPlatforms) = preSolution
Debug|Any CPU = Debug|Any CPU
Release|Any CPU = Release|Any CPU
EndGlobalSection
GlobalSection(ProjectConfigurationPlatforms) = postSolution
{3BF8E366-F9EF-484B-8FAF-F2ADB8854C41}.Debug|Any CPU.ActiveCfg = Debug|Any CPU
{3BF8E366-F9EF-484B-8FAF-F2ADB8854C41}.Debug|Any CPU.Build.0 = Debug|Any CPU
{3BF8E366-F9EF-484B-8FAF-F2ADB8854C41}.Release|Any CPU.ActiveCfg = Release|Any CPU
{3BF8E366-F9EF-484B-8FAF-F2ADB8854C41}.Release|Any CPU.Build.0 = Release|Any CPU
EndGlobalSection
GlobalSection(SolutionProperties) = preSolution
HideSolutionNode = FALSE
EndGlobalSection
GlobalSection(ExtensibilityGlobals) = postSolution
SolutionGuid = {0EC31419-9703-4A29-BB28-FCE8A78193F6}
EndGlobalSection
EndGlobal