Hi all,
i want to recognize text from different documents with not-defined Layouts. So, is there a way to use the described Layout Analysis in Cloud-OCR-SDK to get some Infos about the document and after processing this Information recognize some textfields from the document?
https://abbyy.technology/en:features:ocr:document_analysis
Thanks for a Response!
Comments
1 comment
Hi Bernie,
Unfortunately there is no way for you to analyze page without processing in Cloud OCR SDK.
It should be mentioned, that you can process your page and set .xml as output format. This way you will have the coordinates of blocks of text/images/tables on the page in the .xml result. Unfortunately this will also decrease your page counter, as the processing was performed.
You can perform layout analysis without decreasing page counter in FineReader Engine, moreover, there you can work with Layout object directly.
Please sign in to leave a comment.