Questions of dealing with seal-covered documents: Question #1 - What preprocessing is currently being done on the DU side? Question #2 - Regarding text obscured by seal covering, are there any recommended handling methods on DU?
- Regarding text obscured by seal covering, are there any recommended handling methods on DU?
[Answer] There is no way to remove/ignore the stamp from within the Document Manager import flow, that would require external preprocessing of the file before the import is done.
- What preprocessing is currently being done on the DU side?
[Answer] When the PDF file gets imported to data labeling session, it tries to digitize the document into machine readable format either using the Digitizer or OCR based on the type of document (whether it is a scanned document or a native document) and this is the only thing done by DU side before labeling the fields.