Here's how it works: Logikcull will use the existing text metadata for documents that arrive with a text layer (for example, a Microsoft Word document) or production uploads that have imported text. If a document does not have a text layer, Logikcull will send it through an Optical Character Recognition (OCR) process.

ℹ️ All documents that Logikcull OCRs will receive the QC Tag: OCRed

  1. Click on the "OCRed" QC Tag to filter on documents Logikcull OCRed

  2. Examine the text of the OCR by clicking on the Text button in the document action bar.

Logikcull uses Tesseract to OCR and will only OCR in English. OCR is not an exact science, so its best practice to not rely on exact keyword searching within OCRed sets of data.

Did this answer your question?