Code snippet demo for step 2.

Test.java

import java.awt.image.BufferedImage;
import java.io.File;
import java.io.IOException;
import java.nio.file.Path;
import java.nio.file.Paths;
import java.util.List;
import net.sourceforge.tess4j.Tesseract;
import net.sourceforge.tess4j.TesseractException;
import org.apache.pdfbox.Loader;
import org.apache.pdfbox.multipdf.Splitter;
import org.apache.pdfbox.pdmodel.PDDocument;
import org.apache.pdfbox.rendering.ImageType;
import org.apache.pdfbox.rendering.PDFRenderer;

public class Test {
    public static void main(String[] args) {
        Tesseract instance = new Tesseract();
        int imageDPI = 300;
        Path currentRelativePath = Paths.get("");
        String s = currentRelativePath.toAbsolutePath().toString();
        File dataDir = new File(s, "tessdata");

        if(dataDir.exists()) {
            instance.setDatapath(dataDir.getAbsolutePath());
            /* START TO DO LOGIC HERE*/
            instance.setLanguage("eng+osd+equ");
            /*
            OCR engine modes (oem)
            0. Legacy engine only
            1. Neural nets LSTM engine only
            2. Legacy + LSTM engines
            3. Default, based on what is available
            */
            instance.setOcrEngineMode(1);
            instance.setTessVariable("user_defined_dpi", imageDPI+"");
            
            /* [START] Extract Text from PDF */
            try {
                File selectedFile = new File("sample.pdf");
                PDDocument document = Loader.loadPDF(selectedFile);
                int totalNoOfPages=document.getNumberOfPages();
                Splitter splitter = new Splitter();
                List<PDDocument> pages = splitter.split(document);
                PDDocument page = null;
                for (int p = 0; p < totalNoOfPages; p++) { // FOR-EACH FILE
                    page = pages.get(p);
                    PDFRenderer pdfRenderer = new PDFRenderer(page);
                    BufferedImage tempPageImg = pdfRenderer.renderImageWithDPI(0, imageDPI, ImageType.RGB);
                    String text = instance.doOCR(tempPageImg);
                    
                    System.out.println("[Start] Page "+(p+1)+" ----------------------------------------------");
                    System.out.println(text);
                    System.out.println("[End] Page "+(p+1)+" ------------------------------------------------");
                }
                /* //END TO DO LOGIC HERE*/
                // String text = instance.doOCR(new File("bday_card.jpg"));
                // System.out.print(text);
            /* [END] Extract Text from PDF */
              
            } catch (TesseractException | IOException ex) {
                ex.printStackTrace();
            }
        }      
    }
}