OCR scanned forms

PDF-X OCR SDK is a New product from us and intended to compliment our existing PDF and Imaging Tools to provide the Developer with an expanding set of professional tools for Optical Character Recognition tasks

Moderators: TrackerSupp-Daniel, Tracker Support, Vasyl-Tracker Dev Team, Chris - Tracker Supp, Sean - Tracker, Tracker Supp-Stefan

Post Reply
apx
User
Posts: 25
Joined: Tue Sep 12, 2017 1:43 pm

OCR scanned forms

Post by apx »

We have some forms as scanned PDF, which we would like to read using the OCR component. However, this also includes form elements such as checkboxes and other things. Are there any concrete plans for extensions that can support us in our project?
sample.png
I would also be happy to send you an example by e-mail.

Greetings
Alex
Sasha - Tracker Dev Team
User
Posts: 5522
Joined: Fri Nov 21, 2014 8:27 am
Contact:

Re: OCR scanned forms

Post by Sasha - Tracker Dev Team »

Hello Alex,

Do you want to recognize the form fields themselves, not only the text?

Cheers,
Alex
Subscribe at:
https://www.youtube.com/channel/UC-TwAMNi1haxJ1FX3LvB4CQ
apx
User
Posts: 25
Joined: Tue Sep 12, 2017 1:43 pm

Re: OCR scanned forms

Post by apx »

That's right. I want to find the check mark on the screenshot.
Sasha - Tracker Dev Team
User
Posts: 5522
Joined: Fri Nov 21, 2014 8:27 am
Contact:

Re: OCR scanned forms

Post by Sasha - Tracker Dev Team »

Hello Alex,

Sadly, we do not have such an algorithm as of now.

Cheers,
Alex
Subscribe at:
https://www.youtube.com/channel/UC-TwAMNi1haxJ1FX3LvB4CQ
apx
User
Posts: 25
Joined: Tue Sep 12, 2017 1:43 pm

Re: OCR scanned forms

Post by apx »

Okay,
Is one of these functions already under development or what will happen with the OCR module in the future?
  • Complex objects such as tables, embedded images, etc.
  • Bar-code recognition
  • Scan Image/Paper Forms to fill-able PDF forms
src: https://www.pdf-xchange.com/pdfxocrmod

tia
Alex
User avatar
Tracker Supp-Stefan
Site Admin
Posts: 17822
Joined: Mon Jan 12, 2009 8:07 am
Location: London
Contact:

Re: OCR scanned forms

Post by Tracker Supp-Stefan »

Hello Alex,

Just spoke with one of the OCR devs, and he told me that these are the next things on the agenda:
1. preOCR clearing of dirty images
2. tables extraction (from images)
3. Forms detection

Regards,
Stefan
apx
User
Posts: 25
Joined: Tue Sep 12, 2017 1:43 pm

Re: OCR scanned forms

Post by apx »

Tracker Supp-Stefan wrote:Hello Alex,

Just spoke with one of the OCR devs, and he told me that these are the next things on the agenda:
1. preOCR clearing of dirty images
2. tables extraction (from images)
3. Forms detection

Regards,
Stefan
Hello Stefan,
thank you for your quick answer. What is the timeframe for implementation? Or when is the release of the features planned? This quarter?
User avatar
Tracker Supp-Stefan
Site Admin
Posts: 17822
Joined: Mon Jan 12, 2009 8:07 am
Location: London
Contact:

Re: OCR scanned forms

Post by Tracker Supp-Stefan »

Hello Alex,

I don't have a time frame for those features. This is just the order in which we will work on them and each will be included in the final products as soon as it is ready!

Cheers,
Stefan
Post Reply