Born-digital document conversion
PDF · DOCX · ODT · ODS · XLSX · RTF · DOC · XLS → the document record
Digital-born documents transformed into JSON records, and page content information for the pages that still need OCR.
The born-digital route's first stage: reads the text layer, flags the pages that need OCR.
Where this sits in the pipeline
- page-classification
- →
- ocr-postprocess
- →
- translator
- →
- nlp-enrich
- →
- keyword-extract
- →
- digital-convert