Leadtools Forms Recognition on vectorial PDF

#1 Posted : Tuesday, May 25, 2021 3:36:33 AM(UTC)

username77

Groups: Registered
Posts: 40

Thanks: 5 times

Hi,
how Forms Recognition works on vectorial pdf files?

It rasterize the file and then try to read with ocr or try to read the text directly without using ocr engine?

Try the latest version of LEADTOOLS for free for 60 days by downloading the evaluation: https://www.leadtools.com/downloads

Wanna join the discussion? Login to your LEADTOOLS Support account or Register a new forum account.

#2 Posted : Tuesday, May 25, 2021 10:42:31 AM(UTC)

Nick

Groups: Registered, Tech Support, Administrators
Posts: 161

Was thanked: 9 time(s) in 9 post(s)

We have more information regarding the Forms Recognition toolkit and its workflow available in our online documentation.
https://www.leadtools.co...processing-workflow.html

Note part of the forms recognition process is comparing the input document against a repository of templates to determine the appropriate template to use. This process requires rasterization of the input image without regard to its original format - this process discards any SVG information present in the document. Once the document is matched against the corresponding form, OCR is used to extract the areas of interest defined in the template.

If you're explicitly using SVG documents which will all have the same layout, consider using the GetText() method. This method retrieves the SVG content from the specified boundary (if present) but applies OCR otherwise.
https://www.leadtools.com/help/sdk/v21/dh/dox/documentpage-gettext().html

Edited by user Wednesday, May 26, 2021 7:41:18 AM(UTC) | Reason: Fixing link

Nick Crook
Developer Support Engineer
LEAD Technologies, Inc.

1 user thanked Nick for this useful post.

username77 on 5/26/2021(UTC)

Notification

Leadtools Forms Recognition on vectorial PDF