Skip to main content

Setting Up Automatic Text Recognition (OCR)

The Automatic Text Recognition (OCR) feature lets the software automatically read text content from scanned pages, turning image files into text that can be searched and copied.

1. Text recognition modes​

VHDoc supports 2 text recognition modes:

  1. Standard mode (Tesseract):
    • Pre-installed with the software; supports Vietnamese and English.
    • Very fast recognition; ordinary office computers run it smoothly.
  2. Advanced mode (PaddleOCR):
    • Recommended for old documents, blurry photocopies, or small print.
    • Higher accuracy when reading Vietnamese with diacritics.

2. How to choose the recognition mode in the software​

  1. Open the software and click Settings at the bottom of the left menu bar.
  2. Select the Text Recognition (OCR) section.
  3. In the Default recognition engine field, choose the mode you want to use:
    • Choose Standard if you prioritize fast scanning.
    • Choose Advanced if you need accurate recognition of faint text.
  4. Click Save settings.