Comparison Profile

OCR and text recognition

Document language

The Document language option is shown only when OCR-assisted processing is active and more than one matching language resource is available. No language selector is displayed when OCR-assisted processing is disabled or only one language is available.

With Detect, i-net PDFC derives the document language from the document and the available resources. The selector also lists the language resources that are actually installed and registered. The list is not maintained as a static list in the documentation; it is built at runtime from the available analysis and OCR resources. This keeps the documentation maintenance-friendly, and an erroneous entry such as "Land" is not shown.

The selected language affects text recognition, similar-character recognition, and correction of typical OCR errors. A language that does not match the document can produce additional comparison differences.

For related information, see OCR-assisted processing and the combined OCR selection.