Comparison Profile

Enhancements

Standardize text

The Standardize text selection in i-net PDFC normalizes recognized text characters before comparison. It provides the following three values:

  • Off performs no additional text normalization.
  • Simplify complex characters performs the basic normalization of complex characters.
  • Equalize common OCR mistakes includes the basic normalization and additionally corrects typical character confusions from text recognition.

The strongest mode is not an alias for the middle mode; it performs both processing steps. The concrete characters that are normalized depend on the recognition and document data available. Enable the setting only when this normalization is appropriate for the comparison.