C# va .NET-da o'zbek OCR

Updated: 2026년 4월 23일

Ushbu hujjatning boshqa versiyalari:

IronOCR - bu C# dasturiy ta'minoti .NET kodlovchilariga rasm va PDF hujjatlaridagi matnlarni 126 tilda, shu jumladan o'zbek tilida o'qish imkonini beradi.

Bu faqat .NET ishlab chiqaruvchilari uchun qurilgan va boshqa Tesseract dvigatellaridan tezligi va aniqligi bo'yicha muntazam ravishda ustun bo'lib turadigan rivojlangan Tesseract vilkasi.

IronOcr.Languages.Uzbek tilining mazmuni

Ushbu paketda .NET uchun 102 ta OCR tili mavjud:

O'zbek
UzbekBest
UzbekFast
O'zbek Kirillcha
UzbekCyrillicBest
O'zbekCyrillicFast

Yuklab olish

O'zbek tili to'plami [O'zbek]
* Download as Zip
* Install with https://www.nuget.org/packages/IronOcr.Languages.Uzbek/ NuGet

O'rnatish

Biz qilishimiz kerak bo'lgan birinchi narsa - .NET loyihangizga o'zbek OCR paketini o'rnatish.

PM> Install-Package IronOcr.Languages.Uzbek

Kod namunasi

Ushbu C# kod misoli o'zbekcha matnni Image yoki PDF hujjatidan o'qiydi.

// PM> Install-Package IronOcr.Languages.Uzbek
using IronOcr;

var Ocr = new IronTesseract();
// Select Uzbek language for OCR
Ocr.Language = OcrLanguage.Uzbek;

using (var Input = new OcrInput(@"images\Uzbek.png"))
{
    // Read the text from the image
    var Result = Ocr.Read(Input);
    // Store the recognized text
    var AllText = Result.Text;
}

// PM> Install-Package IronOcr.Languages.Uzbek
using IronOcr;

var Ocr = new IronTesseract();
// Select Uzbek language for OCR
Ocr.Language = OcrLanguage.Uzbek;

using (var Input = new OcrInput(@"images\Uzbek.png"))
{
    // Read the text from the image
    var Result = Ocr.Read(Input);
    // Store the recognized text
    var AllText = Result.Text;
}

' PM> Install-Package IronOcr.Languages.Uzbek
Imports IronOcr

Private Ocr = New IronTesseract()
' Select Uzbek language for OCR
Ocr.Language = OcrLanguage.Uzbek

Using Input = New OcrInput("images\Uzbek.png")
	' Read the text from the image
	Dim Result = Ocr.Read(Input)
	' Store the recognized text
	Dim AllText = Result.Text
End Using

' PM> Install-Package IronOcr.Languages.Uzbek
Imports IronOcr

Private Ocr = New IronTesseract()
' Select Uzbek language for OCR
Ocr.Language = OcrLanguage.Uzbek

Using Input = New OcrInput("images\Uzbek.png")
	' Read the text from the image
	Dim Result = Ocr.Read(Input)
	' Store the recognized text
	Dim AllText = Result.Text
End Using

Nega IronOCR ni tanlash kerak?

IronOCR - o'rnatilishi oson, to'liq va yaxshi hujjatlashtirilgan .NET dasturiy ta'minoti.

Hech qanday tashqi veb-xizmatlardan, doimiy to'lovlardan yoki Internet orqali maxfiy hujjatlarni jo'natmasdan 99,8% + OCR aniqligiga erishish uchun IronOCR-ni tanlang.

Nima uchun C# ishlab chiquvchilari IronOCR-ni Vanilla Tesseract o'rniga tanlashadi:

Bitta DLL yoki NuGet sifatida o'rnating
Tesseract 5, 4 va 3 dvigatellari qutidan tashqarida.
Aniqlik darajasi 99,8% odatdagi Tesseract-dan sezilarli darajada ustundir.
Yonuvchan tezlik va MultiThreading
MVC, WebApp, Desktop, Console & Server dasturi mos keladi
Exes yoki C++ kodlari bilan ishlash mumkin emas
To'liq PDF OCR-quvvatlash
OCR-ni deyarli har qanday rasm fayli yoki PDF-ni bajarish uchun
To'liq .NET Core, Standard va FrameWork-ni qo'llab-quvvatlash
Windows, Mac, Linux, Azure, Docker, Lambda, AWS-da joylashtiring
Shtrixli kodlar va QR kodlarni o'qing
OCR-ni XHTML formatida eksport qiling
OCR-ni qidiriladigan PDF-hujjatlarga eksport qiling
Ko'p ishlov berishni qo'llab-quvvatlash
126 xalqaro tillarning barchasi NuGet yoki OcrData fayllari orqali boshqariladi
Tasvirlar, koordinatalar, statistika va shriftlarni ajratib oling. Faqat matn emas.
Tesseract OCR-ni tijorat va xususiy dasturlarda qayta tarqatish uchun foydalanish mumkin.

IronOCR haqiqiy dunyo tasvirlari va fotosuratlar kabi nomukammal hujjatlar yoki raqamli shovqin yoki nomukammallikka ega bo'lishi mumkin bo'lgan past aniqlikdagi skanerlar bilan ishlashda porlaydi.

.NET platformasi uchun boshqa bepul OCR kutubxonalari, boshqa .NET Tesseract API va veb-xizmatlari ushbu haqiqiy foydalanish holatlarida unchalik yaxshi ishlamaydi.

Tesseract 5 bilan OCR - C#-da kodlashni boshlang

Quyidagi kod namunasi C# yoki VB.NET yordamida rasmdagi matnni o'qish qanchalik osonligini ko'rsatadi.

OneLiner

// Read text from an image in a single line
string Text = new IronTesseract().Read(@"img\Screenshot.png").Text;

// Read text from an image in a single line
string Text = new IronTesseract().Read(@"img\Screenshot.png").Text;

' Read text from an image in a single line
Dim Text As String = (New IronTesseract()).Read("img\Screenshot.png").Text

' Read text from an image in a single line
Dim Text As String = (New IronTesseract()).Read("img\Screenshot.png").Text

Salom dunyo sozlanishi

// PM> Install-Package IronOcr.Languages.Uzbek
using IronOcr;

var Ocr = new IronTesseract();
Ocr.Language = OcrLanguage.Uzbek;

using (var Input = new OcrInput())
{
    // Add an image to the OCR input
    Input.AddImage("images/sample.jpeg");
    //... siz istalgan sonli rasmlarni qo'shishingiz mumkin

    // Perform OCR on the input
    var Result = Ocr.Read(Input);
    Console.WriteLine(Result.Text);
}

// PM> Install-Package IronOcr.Languages.Uzbek
using IronOcr;

var Ocr = new IronTesseract();
Ocr.Language = OcrLanguage.Uzbek;

using (var Input = new OcrInput())
{
    // Add an image to the OCR input
    Input.AddImage("images/sample.jpeg");
    //... siz istalgan sonli rasmlarni qo'shishingiz mumkin

    // Perform OCR on the input
    var Result = Ocr.Read(Input);
    Console.WriteLine(Result.Text);
}

Imports IronOcr

Dim Ocr As New IronTesseract()
Ocr.Language = OcrLanguage.Uzbek

Using Input As New OcrInput()
    ' Add an image to the OCR input
    Input.AddImage("images/sample.jpeg")
    '... siz istalgan sonli rasmlarni qo'shishingiz mumkin

    ' Perform OCR on the input
    Dim Result = Ocr.Read(Input)
    Console.WriteLine(Result.Text)
End Using

Imports IronOcr

Dim Ocr As New IronTesseract()
Ocr.Language = OcrLanguage.Uzbek

Using Input As New OcrInput()
    ' Add an image to the OCR input
    Input.AddImage("images/sample.jpeg")
    '... siz istalgan sonli rasmlarni qo'shishingiz mumkin

    ' Perform OCR on the input
    Dim Result = Ocr.Read(Input)
    Console.WriteLine(Result.Text)
End Using

C# PDF OCR

Xuddi shu yondashuvdan har qanday PDF-hujjatdan matn chiqarish uchun ham foydalanish mumkin.

using IronOcr;

var Ocr = new IronTesseract();
Ocr.Language = OcrLanguage.Uzbek;

using (var input = new OcrInput())
{
    // Add a PDF to the OCR input
    input.AddPdf("example.pdf", "password");
    // Bundan tashqari, OCR-ga PDF-sahifaning aniq raqamlarini tanlashimiz mumkin

    var Result = Ocr.Read(input);

    Console.WriteLine(Result.Text);
    Console.WriteLine($"{Result.Pages.Count()} Pages");
    // PDF-ning har bir sahifasi uchun 1 ta sahifa
}

using IronOcr;

var Ocr = new IronTesseract();
Ocr.Language = OcrLanguage.Uzbek;

using (var input = new OcrInput())
{
    // Add a PDF to the OCR input
    input.AddPdf("example.pdf", "password");
    // Bundan tashqari, OCR-ga PDF-sahifaning aniq raqamlarini tanlashimiz mumkin

    var Result = Ocr.Read(input);

    Console.WriteLine(Result.Text);
    Console.WriteLine($"{Result.Pages.Count()} Pages");
    // PDF-ning har bir sahifasi uchun 1 ta sahifa
}

Imports IronOcr

Private Ocr = New IronTesseract()
Ocr.Language = OcrLanguage.Uzbek

Using input = New OcrInput()
	' Add a PDF to the OCR input
	input.AddPdf("example.pdf", "password")
	' Bundan tashqari, OCR-ga PDF-sahifaning aniq raqamlarini tanlashimiz mumkin

	Dim Result = Ocr.Read(input)

	Console.WriteLine(Result.Text)
	Console.WriteLine($"{Result.Pages.Count()} Pages")
	' PDF-ning har bir sahifasi uchun 1 ta sahifa
End Using

Imports IronOcr

Private Ocr = New IronTesseract()
Ocr.Language = OcrLanguage.Uzbek

Using input = New OcrInput()
	' Add a PDF to the OCR input
	input.AddPdf("example.pdf", "password")
	' Bundan tashqari, OCR-ga PDF-sahifaning aniq raqamlarini tanlashimiz mumkin

	Dim Result = Ocr.Read(input)

	Console.WriteLine(Result.Text)
	Console.WriteLine($"{Result.Pages.Count()} Pages")
	' PDF-ning har bir sahifasi uchun 1 ta sahifa
End Using

MultiPage TIFF-lar uchun OCR

OCR Reading TIFF fayl formati, shu jumladan bir nechta sahifali hujjatlar. TIFF-ni to'g'ridan-to'g'ri qidirish mumkin bo'lgan matnli PDF-faylga aylantirish mumkin.

using IronOcr;

var Ocr = new IronTesseract();
Ocr.Language = OcrLanguage.Uzbek;

using (var Input = new OcrInput())
{
    // Add a multi-frame TIFF image to the OCR input
    Input.AddMultiFrameTiff("multi-frame.tiff");
    var Result = Ocr.Read(Input);
    Console.WriteLine(Result.Text);
}

using IronOcr;

var Ocr = new IronTesseract();
Ocr.Language = OcrLanguage.Uzbek;

using (var Input = new OcrInput())
{
    // Add a multi-frame TIFF image to the OCR input
    Input.AddMultiFrameTiff("multi-frame.tiff");
    var Result = Ocr.Read(Input);
    Console.WriteLine(Result.Text);
}

Imports IronOcr

Private Ocr = New IronTesseract()
Ocr.Language = OcrLanguage.Uzbek

Using Input = New OcrInput()
	' Add a multi-frame TIFF image to the OCR input
	Input.AddMultiFrameTiff("multi-frame.tiff")
	Dim Result = Ocr.Read(Input)
	Console.WriteLine(Result.Text)
End Using

Imports IronOcr

Private Ocr = New IronTesseract()
Ocr.Language = OcrLanguage.Uzbek

Using Input = New OcrInput()
	' Add a multi-frame TIFF image to the OCR input
	Input.AddMultiFrameTiff("multi-frame.tiff")
	Dim Result = Ocr.Read(Input)
	Console.WriteLine(Result.Text)
End Using

Shtrixli kodlar va QR

IronOCR-ning o'ziga xos xususiyati shundaki, u matnni skanerlash paytida hujjatlardagi shtrix kodlari va QR kodlarini o'qiy oladi. OcrResult.OcrBarcode sinfining OcrResult.OcrBarcode ishlab chiquvchiga har bir skaner qilingan shtrix-kod haqida batafsil ma'lumot beradi.

using IronOcr;

var Ocr = new IronTesseract();
// Enable reading of barcodes
Ocr.Configuration.ReadBarCodes = true;

using (var input = new OcrInput())
{
    // Add an image containing a barcode to the OCR input
    input.AddImage("img/Barcode.png");
    var Result = Ocr.Read(input);

    // Iterate through the barcodes found in the image
    foreach (var Barcode in Result.Barcodes)
    {
        Console.WriteLine(Barcode.Value);
        // Additional properties like type and location are available
    }
}

using IronOcr;

var Ocr = new IronTesseract();
// Enable reading of barcodes
Ocr.Configuration.ReadBarCodes = true;

using (var input = new OcrInput())
{
    // Add an image containing a barcode to the OCR input
    input.AddImage("img/Barcode.png");
    var Result = Ocr.Read(input);

    // Iterate through the barcodes found in the image
    foreach (var Barcode in Result.Barcodes)
    {
        Console.WriteLine(Barcode.Value);
        // Additional properties like type and location are available
    }
}

Imports IronOcr

Private Ocr = New IronTesseract()
' Enable reading of barcodes
Ocr.Configuration.ReadBarCodes = True

Using input = New OcrInput()
	' Add an image containing a barcode to the OCR input
	input.AddImage("img/Barcode.png")
	Dim Result = Ocr.Read(input)

	' Iterate through the barcodes found in the image
	For Each Barcode In Result.Barcodes
		Console.WriteLine(Barcode.Value)
		' Additional properties like type and location are available
	Next Barcode
End Using

Imports IronOcr

Private Ocr = New IronTesseract()
' Enable reading of barcodes
Ocr.Configuration.ReadBarCodes = True

Using input = New OcrInput()
	' Add an image containing a barcode to the OCR input
	input.AddImage("img/Barcode.png")
	Dim Result = Ocr.Read(input)

	' Iterate through the barcodes found in the image
	For Each Barcode In Result.Barcodes
		Console.WriteLine(Barcode.Value)
		' Additional properties like type and location are available
	Next Barcode
End Using

Tasvirlarning aniq yo'nalishlari bo'yicha OCR

IronOCR-ning barcha skanerlash va o'qish usullari biz sahifaning yoki sahifalarning qaysi qismidan matnni o'qishni xohlayotganimizni aniq ko'rsatib beradi. Bu standartlashtirilgan shakllarni ko'rib chiqishda juda foydalidir va juda ko'p vaqtni tejash va samaradorlikni oshirishi mumkin.

Hosil viloyatlariga foydalanish uchun, biz uchun bir tizim mos yozuvlar kiritish kerak bo'ladi System.Drawing biz foydalanishingiz mumkin, shunday qilib, System.Drawing.Rectangle ob'ektni.

using IronOcr;
using System.Drawing; // Add a reference to the assembly

var Ocr = new IronTesseract();
Ocr.Language = OcrLanguage.Uzbek;

using (var Input = new OcrInput())
{
    // Define the content area for OCR
    var ContentArea = new Rectangle() { X = 215, Y = 1250, Height = 280, Width = 1335 };
    // Dimensions in pixels

    // Add the specific region of the image to the OCR input
    Input.Add("document.png", ContentArea);

    var Result = Ocr.Read(Input);
    Console.WriteLine(Result.Text);
}

using IronOcr;
using System.Drawing; // Add a reference to the assembly

var Ocr = new IronTesseract();
Ocr.Language = OcrLanguage.Uzbek;

using (var Input = new OcrInput())
{
    // Define the content area for OCR
    var ContentArea = new Rectangle() { X = 215, Y = 1250, Height = 280, Width = 1335 };
    // Dimensions in pixels

    // Add the specific region of the image to the OCR input
    Input.Add("document.png", ContentArea);

    var Result = Ocr.Read(Input);
    Console.WriteLine(Result.Text);
}

Imports IronOcr
Imports System.Drawing ' Add a reference to the assembly

Private Ocr = New IronTesseract()
Ocr.Language = OcrLanguage.Uzbek

Using Input = New OcrInput()
	' Define the content area for OCR
	Dim ContentArea = New Rectangle() With {
		.X = 215,
		.Y = 1250,
		.Height = 280,
		.Width = 1335
	}
	' Dimensions in pixels

	' Add the specific region of the image to the OCR input
	Input.Add("document.png", ContentArea)

	Dim Result = Ocr.Read(Input)
	Console.WriteLine(Result.Text)
End Using

Imports IronOcr
Imports System.Drawing ' Add a reference to the assembly

Private Ocr = New IronTesseract()
Ocr.Language = OcrLanguage.Uzbek

Using Input = New OcrInput()
	' Define the content area for OCR
	Dim ContentArea = New Rectangle() With {
		.X = 215,
		.Y = 1250,
		.Height = 280,
		.Width = 1335
	}
	' Dimensions in pixels

	' Add the specific region of the image to the OCR input
	Input.Add("document.png", ContentArea)

	Dim Result = Ocr.Read(Input)
	Console.WriteLine(Result.Text)
End Using

Past sifatli skanerlash uchun OCR

IronOCR OcrInput klassi oddiy Tesseract o'qiy olmaydigan skanerlarni tuzatishi mumkin.

using IronOcr;

var Ocr = new IronTesseract();
Ocr.Language = OcrLanguage.Uzbek;

using (var Input = new OcrInput(@"img\Potter.LowQuality.tiff"))
{
    // Correct digital noise and bad scanning
    Input.DeNoise();
    // Correct rotation and perspective
    Input.Deskew();
    var Result = Ocr.Read(Input);
    Console.WriteLine(Result.Text);
}

using IronOcr;

var Ocr = new IronTesseract();
Ocr.Language = OcrLanguage.Uzbek;

using (var Input = new OcrInput(@"img\Potter.LowQuality.tiff"))
{
    // Correct digital noise and bad scanning
    Input.DeNoise();
    // Correct rotation and perspective
    Input.Deskew();
    var Result = Ocr.Read(Input);
    Console.WriteLine(Result.Text);
}

Imports IronOcr

Private Ocr = New IronTesseract()
Ocr.Language = OcrLanguage.Uzbek

Using Input = New OcrInput("img\Potter.LowQuality.tiff")
	' Correct digital noise and bad scanning
	Input.DeNoise()
	' Correct rotation and perspective
	Input.Deskew()
	Dim Result = Ocr.Read(Input)
	Console.WriteLine(Result.Text)
End Using

Imports IronOcr

Private Ocr = New IronTesseract()
Ocr.Language = OcrLanguage.Uzbek

Using Input = New OcrInput("img\Potter.LowQuality.tiff")
	' Correct digital noise and bad scanning
	Input.DeNoise()
	' Correct rotation and perspective
	Input.Deskew()
	Dim Result = Ocr.Read(Input)
	Console.WriteLine(Result.Text)
End Using

OCR natijalarini qidiriladigan PDF sifatida eksport qiling

Ko'chiriladigan matn satrlari bilan PDF-ga rasm. Qidiruv tizimlari va ma'lumotlar bazalari tomonidan indekslash mumkin.

using IronOcr;

var Ocr = new IronTesseract();
Ocr.Language = OcrLanguage.Uzbek;

using (var Input = new OcrInput())
{
    Input.Title = "Quarterly Report";
    Input.AddImage("image1.jpeg");
    Input.AddImage("image2.png");
    Input.AddImage("image3.gif");

    var Result = Ocr.Read(Input);
    Result.SaveAsSearchablePdf("searchable.pdf");
}

using IronOcr;

var Ocr = new IronTesseract();
Ocr.Language = OcrLanguage.Uzbek;

using (var Input = new OcrInput())
{
    Input.Title = "Quarterly Report";
    Input.AddImage("image1.jpeg");
    Input.AddImage("image2.png");
    Input.AddImage("image3.gif");

    var Result = Ocr.Read(Input);
    Result.SaveAsSearchablePdf("searchable.pdf");
}

Imports IronOcr

Private Ocr = New IronTesseract()
Ocr.Language = OcrLanguage.Uzbek

Using Input = New OcrInput()
	Input.Title = "Quarterly Report"
	Input.AddImage("image1.jpeg")
	Input.AddImage("image2.png")
	Input.AddImage("image3.gif")

	Dim Result = Ocr.Read(Input)
	Result.SaveAsSearchablePdf("searchable.pdf")
End Using

Imports IronOcr

Private Ocr = New IronTesseract()
Ocr.Language = OcrLanguage.Uzbek

Using Input = New OcrInput()
	Input.Title = "Quarterly Report"
	Input.AddImage("image1.jpeg")
	Input.AddImage("image2.png")
	Input.AddImage("image3.gif")

	Dim Result = Ocr.Read(Input)
	Result.SaveAsSearchablePdf("searchable.pdf")
End Using

PDF formatida qidirish uchun TIFF

TIFF hujjatini (yoki rasm fayllarining biron bir guruhini) to'g'ridan-to'g'ri intranet, veb-sayt va Google qidiruv tizimlari tomonidan indeksatsiya qilinishi mumkin bo'lgan qidiriladigan PDF-ga o'tkazing.

using IronOcr;

var Ocr = new IronTesseract();
Ocr.Language = OcrLanguage.Uzbek;

using (var Input = new OcrInput())
{
    Input.AddMultiFrameTiff("example.tiff");
    var Result = Ocr.Read(Input).SaveAsSearchablePdf("searchable.pdf");
}

using IronOcr;

var Ocr = new IronTesseract();
Ocr.Language = OcrLanguage.Uzbek;

using (var Input = new OcrInput())
{
    Input.AddMultiFrameTiff("example.tiff");
    var Result = Ocr.Read(Input).SaveAsSearchablePdf("searchable.pdf");
}

Imports IronOcr

Private Ocr = New IronTesseract()
Ocr.Language = OcrLanguage.Uzbek

Using Input = New OcrInput()
	Input.AddMultiFrameTiff("example.tiff")
	Dim Result = Ocr.Read(Input).SaveAsSearchablePdf("searchable.pdf")
End Using

Imports IronOcr

Private Ocr = New IronTesseract()
Ocr.Language = OcrLanguage.Uzbek

Using Input = New OcrInput()
	Input.AddMultiFrameTiff("example.tiff")
	Dim Result = Ocr.Read(Input).SaveAsSearchablePdf("searchable.pdf")
End Using

OCR natijalarini HTML sifatida eksport qiling

OCR tasvirini XHTML formatiga o'tkazish.

using IronOcr;

var Ocr = new IronTesseract();
Ocr.Language = OcrLanguage.Uzbek;

using (var Input = new OcrInput())
{
    Input.Title = "Html Title";
    Input.AddImage("image1.jpeg");
    var Result = Ocr.Read(Input);
    Result.SaveAsHocrFile("results.html");
}

using IronOcr;

var Ocr = new IronTesseract();
Ocr.Language = OcrLanguage.Uzbek;

using (var Input = new OcrInput())
{
    Input.Title = "Html Title";
    Input.AddImage("image1.jpeg");
    var Result = Ocr.Read(Input);
    Result.SaveAsHocrFile("results.html");
}

Imports IronOcr

Private Ocr = New IronTesseract()
Ocr.Language = OcrLanguage.Uzbek

Using Input = New OcrInput()
	Input.Title = "Html Title"
	Input.AddImage("image1.jpeg")
	Dim Result = Ocr.Read(Input)
	Result.SaveAsHocrFile("results.html")
End Using

Imports IronOcr

Private Ocr = New IronTesseract()
Ocr.Language = OcrLanguage.Uzbek

Using Input = New OcrInput()
	Input.Title = "Html Title"
	Input.AddImage("image1.jpeg")
	Dim Result = Ocr.Read(Input)
	Result.SaveAsHocrFile("results.html")
End Using

OCR tasvirni yaxshilash filtrlari

IronOCR OCR ishlashini yaxshilash uchun OcrInput moslamalari uchun noyob filtrlarni taqdim etadi.

Rasmni yaxshilash kodi misoli

OCR natijalarini yaxshiroq va tezroq chiqarish uchun OCR kirish tasvirlarini yuqori sifatga keltiradi.

using IronOcr;

var Ocr = new IronTesseract();
Ocr.Language = OcrLanguage.Uzbek;

using (var Input = new OcrInput(@"LowQuality.jpeg"))
{
    Input.DeNoise(); // Correct digital noise and bad scanning
    Input.Deskew();  // Correct rotation and perspective
    var Result = Ocr.Read(Input);
    Console.WriteLine(Result.Text);
}

using IronOcr;

var Ocr = new IronTesseract();
Ocr.Language = OcrLanguage.Uzbek;

using (var Input = new OcrInput(@"LowQuality.jpeg"))
{
    Input.DeNoise(); // Correct digital noise and bad scanning
    Input.Deskew();  // Correct rotation and perspective
    var Result = Ocr.Read(Input);
    Console.WriteLine(Result.Text);
}

Imports IronOcr

Private Ocr = New IronTesseract()
Ocr.Language = OcrLanguage.Uzbek

Using Input = New OcrInput("LowQuality.jpeg")
	Input.DeNoise() ' Correct digital noise and bad scanning
	Input.Deskew() ' Correct rotation and perspective
	Dim Result = Ocr.Read(Input)
	Console.WriteLine(Result.Text)
End Using

Imports IronOcr

Private Ocr = New IronTesseract()
Ocr.Language = OcrLanguage.Uzbek

Using Input = New OcrInput("LowQuality.jpeg")
	Input.DeNoise() ' Correct digital noise and bad scanning
	Input.Deskew() ' Correct rotation and perspective
	Dim Result = Ocr.Read(Input)
	Console.WriteLine(Result.Text)
End Using

OCR tasvir filtrlari ro'yxati

IronOCR-ga o'rnatilgan OCR ishlashini yaxshilash uchun kirish filtrlariga quyidagilar kiradi.

OcrInput.Rotate (double degrees) - Tasvirlarni soat yo'nalishi bo'yicha bir necha darajaga aylantiradi. Soatning teskari yo'nalishi bo'yicha salbiy raqamlardan foydalaning.
OcrInput.Binarize () - Ushbu rasm filtri har bir pikselni qora yoki oq rangga aylantirib, o'rtasini ochmaydi. Matnning fon bilan kontrasti juda past bo'lgan OCR ishlashini yaxshilashi mumkin.
OcrInput.ToGrayScale () - Ushbu rasm filtri har bir pikselni kulrang rang soyasiga aylantiradi. OCR aniqligini oshirish ehtimoldan yiroq, ammo tezlikni oshirishi mumkin.
OcrInput.Contrast () - kontrastni avtomatik ravishda oshiradi. Ushbu filtr ko'pincha past kontrastli skanerlarda OCR tezligini va aniqligini yaxshilaydi.
OcrInput.DeNoise () - Raqamli shovqinni olib tashlaydi. Ushbu filtr faqat shovqin kutilgan joyda ishlatilishi kerak.
OcrInput.Invert () - har qanday rangni teskari tomonga o'zgartiradi. Masalan, Oq qora rangga aylanadi: qora oq rangga ega bo'ladi.
OcrInput.Dilate () - kengaytirilgan morfologiya. Dilatatsiya tasvirdagi ob'ektlar chegaralariga piksellar qo'shadi. Erodening qarshisida
OcrInput.Erode () - kengaytirilgan morfologiya. Eroziya ob'ekt chegaralaridagi piksellarni olib tashlaydi. Opposite of Dilate
OcrInput.Deskew () - Rasmni yuqoriga ko'tarish va to'g'ri burchakli qilib aylantiradi. Bu OCR uchun juda foydali, chunki skess skanerlash uchun Tesseract bardoshliligi 5 darajagacha bo'lishi mumkin.
OcrInput.DeepCleanBackgroundNoise () - Og'ir fonni shovqinlarni yo'qotish. Ushbu filtrdan faqat hujjatning orqa fonidagi shovqin ma'lum bo'lgan taqdirda foydalaning, chunki bu filtr toza hujjatlarning OCR aniqligini pasayishiga olib keladi va protsessor juda qimmatga tushadi.
OcrInput.EnhanceResolution - past sifatli tasvirlarning o'lchamlarini yaxshilaydi. Ushbu filtr tez-tez talab qilinmaydi, chunki OcrInput.MinimumDPI va OcrInput.TargetDPI avtomatik ravishda past aniqlikdagi yozuvlarni ushlaydi va hal qiladi.

CleanBackgroundNoise. Bu biroz vaqt talab qiladigan parametr; ammo, bu kutubxonani raqamli tasvir ichidagi raqamli shovqinlarni, qog'oz burmalarni va boshqa kamchiliklarni avtomatik ravishda tozalashga imkon beradi, aks holda uni boshqa OCR kutubxonalari o'qiy olmaydi.

EnhanceContrast - bu IronOCR-ning rasm fonida matn kontrastini avtomatik ravishda oshirishi, OCR aniqligini oshirishi va umuman OCR tezligi va ishlash tezligini oshiradigan parametr.

EnhanceResolution - bu past aniqlikdagi rasmlarni avtomatik ravishda aniqlaydigan (275 dpi dan past bo'lgan) rasmni avtomatik ravishda yuqori darajaga ko'taradigan va keyin OCR kutubxonasi tomonidan mukammal o'qilishi uchun barcha matnni keskinlashtiradigan sozlama. Ushbu operatsiyaning o'zi ko'p vaqt talab qiladigan bo'lsa-da, odatda rasmdagi OCR operatsiyasining umumiy vaqtini qisqartiradi.

Til IronOCR 22 xalqaro til paketlarini qo'llab-quvvatlaydi, va til sozlamalari bir OCR operatsiya uchun qo'llanilishi uchun bir yoki bir necha bir necha tilni tanlash uchun foydalanish mumkin.

Strategy IronOCR ikkita strategiyani qo'llab-quvvatlaydi. Hujjatni tez va aniqroq skanerdan o'tkazishga yoki jumlada so'zlarning bir-biriga statistik bog'liqligiga qarab, OCR matnining aniqligini avtomatik ravishda yaxshilash uchun ba'zi sun'iy intellekt modellaridan foydalanadigan rivojlangan strategiyadan foydalanishni tanlashimiz mumkin. .

ColorSpace - bu biz OCR-ni kul rang yoki rangda tanlashimiz mumkin bo'lgan parametr. Odatda, kul rang eng yaxshi variant. Biroq, ba'zida o'xshash rangga ega bo'lgan, lekin juda boshqacha rangdagi matnlar yoki fonlar mavjud bo'lganda, to'liq rangli bo'shliq yaxshi natijalarni beradi.

DetectWhiteTextOnDarkBackgrounds. Odatda, barcha OCR kutubxonalari oq fonda qora matnni ko'rishni kutishadi. Ushbu parametr IronOCR-ga negativlarni yoki oq matnli quyuq sahifalarni avtomatik ravishda aniqlash va ularni o'qish imkonini beradi.

InputImageType. Ushbu parametr ishlab chiquvchiga OCR kutubxonasini to'liq hujjatni yoki skrinshot kabi parchani ko'rib chiqayotganligi to'g'risida ko'rsatma berishiga imkon beradi.

RotateAndStraighten - bu temir OCR-ga nafaqat aylantiriladigan, balki matnli hujjatlarning fotosuratlari kabi istiqbolga ega bo'lgan hujjatlarni o'qishning noyob qobiliyatini ta'minlaydigan rivojlangan sozlama.

ReadBarcodes - bu IronOCR-ga avtomatik ravishda shtrix-kodlarni va QR-kodlarni sahifalarda o'qish imkonini beradigan, shuningdek, qo'shimcha vaqt yukini qo'shmasdan matnni o'qiydigan foydali xususiyatdir.

Rang chuqurligi. Ushbu parametr OCR kutubxonasi rangning chuqurligini aniqlash uchun pikselga qancha bit ishlatishini aniqlaydi. Rangning yuqori chuqurligi OCR sifatini oshirishi mumkin, ammo OCR ishini bajarish uchun zarur bo'lgan vaqtni ko'paytiradi.

126 ta til to'plami

IronOCR ushbu veb-saytdan yoki NuGet Package Manager- dan yuklab olish mumkin bo'lgan DLL sifatida tarqatiladigan til paketlari orqali 126 ta xalqaro tillarni qo'llab-quvvatlaydi.

Tillarga nemis, frantsuz, ingliz, xitoy, yapon va boshqa tillar kiradi. MRZ, MICR pasportlari, moliyaviy ma'lumotlar, avtoulov raqamlari va boshqa ko'plab narsalar uchun maxsus til paketlari mavjud. Siz har qanday Tesseract ".traineddata" faylidan foydalanishingiz mumkin, shu jumladan o'zingiz yaratgan fayllardan.

Til misoli

Boshqa OCR tillaridan foydalanish.

using IronOcr;

// PM> Install-Package IronOcr.Languages.Arabic

var Ocr = new IronTesseract();
Ocr.Language = OcrLanguage.Arabic;

using (var input = new OcrInput())
{
    input.AddImage("img/arabic.gif");

    // Agar kerak bo'lsa, rasm filtrlarini qo'shing
    // Bunday holda, hatto o'ylangan kiritish juda past sifatga ega
    // IronTesseract an'anaviy Tesseract qila olmaydigan narsalarni o'qiy oladi.

    var Result = Ocr.Read(input);

    // Konsol arab tilini Windows-da osongina chop eta olmaydi.
    // Buning o'rniga diskka saqlaylik.
    Result.SaveAsTextFile("arabic.txt");
}

using IronOcr;

// PM> Install-Package IronOcr.Languages.Arabic

var Ocr = new IronTesseract();
Ocr.Language = OcrLanguage.Arabic;

using (var input = new OcrInput())
{
    input.AddImage("img/arabic.gif");

    // Agar kerak bo'lsa, rasm filtrlarini qo'shing
    // Bunday holda, hatto o'ylangan kiritish juda past sifatga ega
    // IronTesseract an'anaviy Tesseract qila olmaydigan narsalarni o'qiy oladi.

    var Result = Ocr.Read(input);

    // Konsol arab tilini Windows-da osongina chop eta olmaydi.
    // Buning o'rniga diskka saqlaylik.
    Result.SaveAsTextFile("arabic.txt");
}

Imports IronOcr

' PM> Install-Package IronOcr.Languages.Arabic

Private Ocr = New IronTesseract()
Ocr.Language = OcrLanguage.Arabic

Using input = New OcrInput()
	input.AddImage("img/arabic.gif")

	' Agar kerak bo'lsa, rasm filtrlarini qo'shing
	' Bunday holda, hatto o'ylangan kiritish juda past sifatga ega
	' IronTesseract an'anaviy Tesseract qila olmaydigan narsalarni o'qiy oladi.

	Dim Result = Ocr.Read(input)

	' Konsol arab tilini Windows-da osongina chop eta olmaydi.
	' Buning o'rniga diskka saqlaylik.
	Result.SaveAsTextFile("arabic.txt")
End Using

Imports IronOcr

' PM> Install-Package IronOcr.Languages.Arabic

Private Ocr = New IronTesseract()
Ocr.Language = OcrLanguage.Arabic

Using input = New OcrInput()
	input.AddImage("img/arabic.gif")

	' Agar kerak bo'lsa, rasm filtrlarini qo'shing
	' Bunday holda, hatto o'ylangan kiritish juda past sifatga ega
	' IronTesseract an'anaviy Tesseract qila olmaydigan narsalarni o'qiy oladi.

	Dim Result = Ocr.Read(input)

	' Konsol arab tilini Windows-da osongina chop eta olmaydi.
	' Buning o'rniga diskka saqlaylik.
	Result.SaveAsTextFile("arabic.txt")
End Using

Ko'p tilli misol

Bir vaqtning o'zida bir nechta tillardan foydalanib OCR qilish ham mumkin. Bu haqiqatan ham ingliz tilidagi metadata va Unicode hujjatlaridagi urllarni olishga yordam beradi.

using IronOcr;

// PM> Install-Package IronOcr.Languages.ChineseSimplified

var Ocr = new IronTesseract();
Ocr.Language = OcrLanguage.ChineseSimplified;
// Add a secondary language for OCR
Ocr.AddSecondaryLanguage(OcrLanguage.Uzbek);

// Biz istalgan tilni qo'shishimiz mumkin

using (var input = new OcrInput())
{
    input.Add("multi-language.pdf");
    var Result = Ocr.Read(input);
    Result.SaveAsTextFile("results.txt");
}

using IronOcr;

// PM> Install-Package IronOcr.Languages.ChineseSimplified

var Ocr = new IronTesseract();
Ocr.Language = OcrLanguage.ChineseSimplified;
// Add a secondary language for OCR
Ocr.AddSecondaryLanguage(OcrLanguage.Uzbek);

// Biz istalgan tilni qo'shishimiz mumkin

using (var input = new OcrInput())
{
    input.Add("multi-language.pdf");
    var Result = Ocr.Read(input);
    Result.SaveAsTextFile("results.txt");
}

Imports IronOcr

' PM> Install-Package IronOcr.Languages.ChineseSimplified

Private Ocr = New IronTesseract()
Ocr.Language = OcrLanguage.ChineseSimplified
' Add a secondary language for OCR
Ocr.AddSecondaryLanguage(OcrLanguage.Uzbek)

' Biz istalgan tilni qo'shishimiz mumkin

Using input = New OcrInput()
	input.Add("multi-language.pdf")
	Dim Result = Ocr.Read(input)
	Result.SaveAsTextFile("results.txt")
End Using

Imports IronOcr

' PM> Install-Package IronOcr.Languages.ChineseSimplified

Private Ocr = New IronTesseract()
Ocr.Language = OcrLanguage.ChineseSimplified
' Add a secondary language for OCR
Ocr.AddSecondaryLanguage(OcrLanguage.Uzbek)

' Biz istalgan tilni qo'shishimiz mumkin

Using input = New OcrInput()
	input.Add("multi-language.pdf")
	Dim Result = Ocr.Read(input)
	Result.SaveAsTextFile("results.txt")
End Using

OCR natijalarining batafsil ob'ektlari

IronOCR har bir OCR ishlashi uchun OCR natijasi ob'ektini qaytaradi. Odatda, dasturchilar ushbu ob'ektning matn xususiyatidan faqat rasmdan skaner qilingan matnni olish uchun foydalanadilar. Biroq, OCR natijalari DOM bundan ancha rivojlangan.

using IronOcr;
using System.Drawing; // Add a reference to the assembly

var Ocr = new IronTesseract();
Ocr.Language = OcrLanguage.Uzbek;
Ocr.Configuration.EngineMode = TesseractEngineMode.TesseractAndLstm;
// Additional barcode reading capability
Ocr.Configuration.ReadBarCodes = true;

using (var Input = new OcrInput(@"images\sample.tiff"))
{
    OcrResult Result = Ocr.Read(Input);
    // Access detailed results
    var Pages = Result.Pages;
    var Words = Pages[0].Words;
    var Barcodes = Result.Barcodes;

    // Explore for a comprehensive, detailed API:
    // - Pages, blocks, paragraphs, lines, words, characters
    // - Export images, fonts coordinates, statistics
}

using IronOcr;
using System.Drawing; // Add a reference to the assembly

var Ocr = new IronTesseract();
Ocr.Language = OcrLanguage.Uzbek;
Ocr.Configuration.EngineMode = TesseractEngineMode.TesseractAndLstm;
// Additional barcode reading capability
Ocr.Configuration.ReadBarCodes = true;

using (var Input = new OcrInput(@"images\sample.tiff"))
{
    OcrResult Result = Ocr.Read(Input);
    // Access detailed results
    var Pages = Result.Pages;
    var Words = Pages[0].Words;
    var Barcodes = Result.Barcodes;

    // Explore for a comprehensive, detailed API:
    // - Pages, blocks, paragraphs, lines, words, characters
    // - Export images, fonts coordinates, statistics
}

Imports IronOcr
Imports System.Drawing ' Add a reference to the assembly

Private Ocr = New IronTesseract()
Ocr.Language = OcrLanguage.Uzbek
Ocr.Configuration.EngineMode = TesseractEngineMode.TesseractAndLstm
' Additional barcode reading capability
Ocr.Configuration.ReadBarCodes = True

Using Input = New OcrInput("images\sample.tiff")
	Dim Result As OcrResult = Ocr.Read(Input)
	' Access detailed results
	Dim Pages = Result.Pages
	Dim Words = Pages(0).Words
	Dim Barcodes = Result.Barcodes

	' Explore for a comprehensive, detailed API:
	' - Pages, blocks, paragraphs, lines, words, characters
	' - Export images, fonts coordinates, statistics
End Using

Imports IronOcr
Imports System.Drawing ' Add a reference to the assembly

Private Ocr = New IronTesseract()
Ocr.Language = OcrLanguage.Uzbek
Ocr.Configuration.EngineMode = TesseractEngineMode.TesseractAndLstm
' Additional barcode reading capability
Ocr.Configuration.ReadBarCodes = True

Using Input = New OcrInput("images\sample.tiff")
	Dim Result As OcrResult = Ocr.Read(Input)
	' Access detailed results
	Dim Pages = Result.Pages
	Dim Words = Pages(0).Words
	Dim Barcodes = Result.Barcodes

	' Explore for a comprehensive, detailed API:
	' - Pages, blocks, paragraphs, lines, words, characters
	' - Export images, fonts coordinates, statistics
End Using

Ishlash

IronOCR qutidan tashqarida ishlaydi, kirish tasvirlarini sozlash yoki qattiq o'zgartirish zaruriyati yo'q.

Tezlik yonmoqda: IronOCR.2020 + 10 baravar tezroq va oldingi tuzilishlarga qaraganda 250% kamroq xatolarga yo'l qo'yadi.

Ko'proq ma'lumot olish

C#, VB, F# yoki boshqa har qanday .NET tilidagi OCR haqida ko'proq bilish uchun, iltimos, temir OCR dan qanday foydalanish mumkinligi haqida haqiqiy dunyo misollarini keltiradigan jamoat qo'llanmalarimizni o'qing va undan qanday qilib eng yaxshi natijalarga erishish kerakligini bilib oling ushbu kutubxona.

.NET ishlab chiquvchilari uchun to'liq mos yozuvlar mavjud.

Curtis Chau

지금 바로 엔지니어링 팀과 채팅하세요

기술 문서 작성자

커티스 차우는 칼턴 대학교에서 컴퓨터 과학 학사 학위를 취득했으며, Node.js, TypeScript, JavaScript, React를 전문으로 하는 프론트엔드 개발자입니다. 직관적이고 미적으로 뛰어난 사용자 인터페이스를 만드는 데 열정을 가진 그는 최신 프레임워크를 활용하고, 잘 구성되고 시각적으로 매력적인 매뉴얼을 제작하는 것을 즐깁니다.

...

더 읽어보기