Java Sample Code to Recognize (OCR) and Add Text to a PDF Document

// Load a PDF that contains scanned pages needing to be OCRed
PDFDocument pdfDoc = new PDFDocument("C:/test/test.pdf", null);
// initialize the OCR bridge with the Tesseract libpath and the datapath
OCRBridge.initialize("C:/test/tess", "C:/test/tess/tessdata");
// start OCR
TessJNI ocr = new TessJNI();
// loop through all pages
for (int count = 0; count < pdfDoc.getPageCount(); ++count)
{
  // perform OCR on the current PDF page
  // 300 is the DPI resolution parameter at which to render the page 
  // when sending it to the OCR engine
  String pageOCR = ocr.performOCR("eng", pdfDoc.getPage(count), 300);
  // insert OCR text into the current PDF page
  pdfDoc.getPage(count).insert_hOCR(pageOCR, true);
}
// Save the OCRed PDF document
pdfDoc.saveDocument("C:/test/test_ocr.pdf");

// Load a PDF that contains scanned pages needing to be OCRed PDFDocument pdfDoc = new PDFDocument("C:/test/test.pdf", null); // initialize the OCR bridge with the Tesseract libpath and the datapath OCRBridge.initialize("C:/test/tess", "C:/test/tess/tessdata"); // start OCR TessJNI ocr = new TessJNI(); // loop through all pages for (int count = 0; count < pdfDoc.getPageCount(); ++count) { // perform OCR on the current PDF page // 300 is the DPI resolution parameter at which to render the page // when sending it to the OCR engine String pageOCR = ocr.performOCR("eng", pdfDoc.getPage(count), 300); // insert OCR text into the current PDF page pdfDoc.getPage(count).insert_hOCR(pageOCR, true); } // Save the OCRed PDF document pdfDoc.saveDocument("C:/test/test_ocr.pdf");