ओसीआर टेक्स्ट निष्कर्षण और दस्तावेज़ विश्लेषण के लिए निःशुल्क जावा लाइब्रेरी

Tess4J के लिए मावेन निर्भरता

<dependencies>
	<dependency>
	<groupId>net.sourceforge.tess4j</groupId>
	<artifactId>tess4j;/artifactId>
	<version>X.X.X</version>
    </dependency>
</dependencies>

GitHub के माध्यम से Tess4J इंस्टॉल करें

 git clone https://github.com/nguyenq/tess4j.git  

You can also install it manually; download the latest release files directly from GitHub repository.

जावा ओसीआर लाइब्रेरी का उपयोग करके सामग्री निष्कर्षण करें

import net.sourceforge.tess4j.Tesseract;
import net.sourceforge.tess4j.TesseractException;

public class ContentExtractionExample {
    public static void main(String[] args) {
        // Path to the Tesseract OCR installation directory
        String tessDataPath = "path/to/tesseract";

        // Initialize Tesseract instance
        Tesseract tesseract = new Tesseract();
        tesseract.setDatapath(tessDataPath);

        try {
            // Set the language for OCR (e.g., "eng" for English)
            tesseract.setLanguage("eng");

            // Path to the image file for content extraction
            String imagePath = "path/to/image.jpg";

            // Perform content extraction
            String extractedText = tesseract.doOCR(new File(imagePath));
            System.out.println(extractedText);
        } catch (TesseractException e) {
            e.printStackTrace();
        }
    }
}

मौजूदा पीडीएफ फाइल को सादे टेक्स्ट में कैसे बदलें?

import net.sourceforge.tess4j.Tesseract;
import net.sourceforge.tess4j.TesseractException;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.text.PDFTextStripper;

import java.io.File;
import java.io.IOException;

public class PDFToTextConverter {
    public static void main(String[] args) {
        // Path to the PDF file
        String filePath = "path/to/your/pdf/file.pdf";

        try {
            // Load the PDF document
            PDDocument document = PDDocument.load(new File(filePath));

            // Create an instance of Tesseract OCR engine
            Tesseract tesseract = new Tesseract();

            // Set the path to the tessdata directory (containing language data)
            tesseract.setDatapath("path/to/your/tessdata/directory");

            // Iterate over each page of the PDF document
            for (int pageIndex = 0; pageIndex < document.getNumberOfPages(); pageIndex++) {
                // Extract the text from the current page
                PDFTextStripper stripper = new PDFTextStripper();
                stripper.setStartPage(pageIndex + 1);
                stripper.setEndPage(pageIndex + 1);
                String pageText = stripper.getText(document);

                // Perform OCR on the extracted text
                String ocrText = tesseract.doOCR(pageText);

                // Output the OCR result
                System.out.println("Page " + (pageIndex + 1) + " OCR Result:");
                System.out.println(ocrText);
                System.out.println("--------------------------------------");
            }

            // Close the PDF document
            document.close();
        } catch (IOException | TesseractException e) {
            e.printStackTrace();
        }
    }
}