Release date: October 22, 2020


pdfOCR 1.0.2 is already the third release of our newest product.

It brings some important improvements which allow you to process documents more precisely. These are:

  1. Refinement of the symbol position based on the HOCR data that fixes output for Thai and some CJK fonts. This is especially important for our pdfCalligraph customers.
    You can turn it on with: 
    tesseract4OcrEngineProperties.setUseTxtToImproveHocrParsing(true);


  2. Possibility for configuration of image preprocessing.  That allows smoothing out fluctuations in a document's brightness to give you better results in cases of images taken by a camera.
    You can pass the parameters which are described on http://www.leptonica.org/binarization.html using 
    tesseract4OcrEngineProperties.setImagePreprocessingOptions


Improvements

  • Combine HOCR and TXT outputs for more precise text recognition

  • Add possibility to set image preprocessing properties (adaptive threshold tile size, threshold smoothing)

Installation Instructions

Examples (latest ones)

FAQ (latest ones)