We are investigating the Cloud OCR SDK to see if it fits our requirements. We have the following questions:
Is there a tool or graphical interface in which I can specify the XML Parameters of Field Recognition based on an example scan? For example a tool in which I can drag squares that represent recognition fields and which produces (exports) the xml that is used to submit to the service API?
We would like to add metadata (for example subject) to a document based on the appearance/frequency of certain terms/words/text or combination of terms/words/text in a document that has beeen OCR processed. Has the Cloud OCR service options to perform these kind of (advanced) document/text analyses?
Thank you in advance!
asked 04 May '15, 11:45
ABBYY Cloud OCR SDK does not have the described options. You cannot change the export format, it has certain structure and you cannot add or remove anything. Your scenario should be implemented on your side and the recognition service can be used only for getting OCR result in one of the supported export formats.
answered 06 May '15, 13:56
Oksana Serdyuk ♦♦