OCRSample.java

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

public class TestOCR {
  
  public void performOCR() throws TesseractException {
    
    Tesseract instance = Tesseract.getInstance();

    File pdfDoc = new File("/my/file/location/doc.pdf");
    File pngImageFiles[] = PdfUtilities.convertPdf2Png(pdfDoc);

    for (int i = 0; i < pngImageFiles.length; i++) {
      String ocrResult = instance.doOCR(pngImageFiles[i]);
    }
  }
}