KYOcapture's Optical Character Recognition (OCR) component, powered by ABBYY FineReader, will read the content of the document image and automatically convert it to a searchable PDF file. Now even if you don't select index fields at the time of scan you can still search documents that have been scanned as searchable PDF's.
The base package for OCR is included with KYOcapture. However users can upgrade to a more robust OCR package that includes Zone OCR. Zone OCR allows you to define one or multiple zones on your document and extract the value of that zone.
For example: if invoices that are being scanned always have an invoice number in the top right hand corner the Zone OCR can be set-up to read and extract this data from all scanned invoices. The extracted data is then used to index the scanned documents.
|