Imagine a situation, where you need to process a set of documents. Data are being extracted from the first page and the rest of the pages are attachments and their count varies. Everything runs fine and smooth until you receive a bunch of such document sets in one file.
No barcode, no blank pages at disposal to use as a separator. Also, separation after fixed page count is not usable in this case, as the page count varies from document set to document set. We have resolved this seemingly inconclusive situation by adding a new feature called 'OCR separation'.
OCR separation allows defining a separation template, which will be compared to each page of the file containing the various documents. Once matched with the template, the document will be separated. It is even possible to use the separation template name to populate an indexing field to have separated documents classified in case of multiple separation templates.