OCR avec vision par ordinateur (Tutoriel d'exemple)

FindTextRegion Method

The FindTextRegion method is used to identify a single text region within an image. The method takes several optional parameters, including Scale, DilationAmount, Binarize, and Invert:

• Scale adjusts the size of the image for better text recognition.
• DilationAmount increases the thickness of the text to enhance visibility.
• Binarize converts the image into black and white, improving contrast.
• Invert inverts the colors of the image, which can be useful for certain types of images.

using IronOcr;
using System;

// Initialize the IronTesseract OCR engine
var ocr = new IronTesseract();

// Create an OcrInput object for the image
using (var inputOCR = new OcrInput("test.jpg")) 
{
    // Identify a text region within the image
    inputOCR.FindTextRegion();

    // Perform OCR on the identified text region
    OcrResult result = ocr.Read(inputOCR);

    // Extract and print the recognized text
    string resultText = result.Text;
    Console.WriteLine(resultText);
}

using IronOcr;
using System;

// Initialize the IronTesseract OCR engine
var ocr = new IronTesseract();

// Create an OcrInput object for the image
using (var inputOCR = new OcrInput("test.jpg")) 
{
    // Identify a text region within the image
    inputOCR.FindTextRegion();

    // Perform OCR on the identified text region
    OcrResult result = ocr.Read(inputOCR);

    // Extract and print the recognized text
    string resultText = result.Text;
    Console.WriteLine(resultText);
}

Imports IronOcr
Imports System

' Initialize the IronTesseract OCR engine
Private ocr = New IronTesseract()

' Create an OcrInput object for the image
Using inputOCR = New OcrInput("test.jpg")
	' Identify a text region within the image
	inputOCR.FindTextRegion()

	' Perform OCR on the identified text region
	Dim result As OcrResult = ocr.Read(inputOCR)

	' Extract and print the recognized text
	Dim resultText As String = result.Text
	Console.WriteLine(resultText)
End Using

Note: After running the code, you'll see that it extracts text from the text region using a machine-learning process. The output result appears in the console with high text recognition accuracy.

The Console results from the text extraction process

FindMultipleTextRegions Method

The FindMultipleTextRegions method is similar to FindTextRegion, but it is used when there are multiple text regions in an image. It returns a list of CropRectangle objects that define the location of each text region. This method is useful when you want to extract text from an image that contains multiple sections of text.

using IronOcr;

// Initialize the IronTesseract OCR engine
var ocr = new IronTesseract();

// Create an OcrInput object for the image
using (var input = new OcrInput("test.jpg"))
{
    // Identify multiple text regions within the image
    input.FindMultipleTextRegions(Scale: 2.0, DilationAmount: -1, Binarize: true, Invert: false);

    // Perform OCR on the pre-processed image
    OcrResult result = ocr.Read(input);

    // Extract and print the recognized text
    string resultText = result.Text;
    Console.WriteLine(resultText);
}

using IronOcr;

// Initialize the IronTesseract OCR engine
var ocr = new IronTesseract();

// Create an OcrInput object for the image
using (var input = new OcrInput("test.jpg"))
{
    // Identify multiple text regions within the image
    input.FindMultipleTextRegions(Scale: 2.0, DilationAmount: -1, Binarize: true, Invert: false);

    // Perform OCR on the pre-processed image
    OcrResult result = ocr.Read(input);

    // Extract and print the recognized text
    string resultText = result.Text;
    Console.WriteLine(resultText);
}

Imports IronOcr

' Initialize the IronTesseract OCR engine
Private ocr = New IronTesseract()

' Create an OcrInput object for the image
Using input = New OcrInput("test.jpg")
	' Identify multiple text regions within the image
	input.FindMultipleTextRegions(Scale:= 2.0, DilationAmount:= -1, Binarize:= True, Invert:= False)

	' Perform OCR on the pre-processed image
	Dim result As OcrResult = ocr.Read(input)

	' Extract and print the recognized text
	Dim resultText As String = result.Text
	Console.WriteLine(resultText)
End Using

Explanation: The code snippet provided above is an example of how to use the IronOCR library to perform OCR on an image file. It first imports the IronOCR library and creates a new instance of the IronTesseract class. Then, it initializes an OcrInput object with the path of the input image file and applies some pre-processing techniques for image correction using the FindMultipleTextRegions method.

OCR License Plate Recognition

License plate recognition plays a significant role in automating traffic management, parking systems, and law enforcement activities. By implementing OCR computer vision in C#, developers can create applications that quickly and accurately identify license plates from images or live video feeds. This technology can be used to:

• Monitor traffic violations and identify vehicles involved in criminal activities.
• Automate the parking systems, facilitating entry and exit management and streamlining the billing process.
• Enhance security measures by tracking and monitoring vehicle movement in restricted areas.

Extracting Text from Invoices

OCR computer vision in C# can be utilized to develop OCR applications that automate the extraction of text from invoices and other financial documents. This process can drastically reduce manual data entry errors and streamline accounting tasks. Key benefits include:

• Increased productivity by automating the data entry process.
• Improved accuracy, as OCR reduces the likelihood of human errors.
• Seamless integration with accounting software and systems for efficient data management.

OCR Subtitles Generation

Creating subtitles for videos can be time-consuming and labor-intensive. OCR computer vision in C# can simplify this process by automatically detecting and transcribing the on-screen text, enabling developers to:

• Create accurate subtitles for movies, TV shows, and online videos.
• Enhance accessibility for individuals with hearing impairments or those who speak different languages.
• Boost SEO efforts by providing searchable, indexable content for the video platform

OCR PDF Processing

PDFs are widely used for sharing and storing documents, but extracting text from them can be challenging. OCR computer vision in C# can help developers build OCR applications that effortlessly process PDF files and extract their content, facilitating:

• Easy conversion of PDFs into editable file formats like Word, Excel, or plain text.
• Efficient data extraction for analysis, indexing, or further processing.
• Improved accessibility by converting scanned PDFs into searchable, readable text.

Digitizing Printed Text

OCR software is widely used to digitize printed text from document images. OCR tools can extract text from scanned digital documents, PDFs, and images in various formats. This is particularly useful in document management, where you can easily search, store, and share text-based documents.

Data Extraction

OCR technology is widely used to extract data from input data such as invoices, receipts, and forms. OCR models can recognize and extract key data fields such as names, addresses, dates, and amounts. This eliminates the need for manual data entry and reduces errors in the data processing.

Image Search

OCR technology is also used for image search, where you can search for images based on the text contained within them. This is particularly useful for large image libraries, where manual searching would be time-consuming.

Translation

OCR software can be used to extract text from documents in one language and translate it into another language. This is particularly useful for international businesses, where documents need to be translated quickly and accurately.