Welcome Guest! To enable all features, please Login or Register.



Last Go to last post Unread Go to first unread post
#1 Posted : Tuesday, March 21, 2006 4:49:57 PM(UTC)


Groups: Registered
Posts: 1


We are developing an application extension from our .Net based catering system to enable the scanning of menu information into our application for ordering of meals for these patients.

The nature of our system is very dynamic and so there are potentially an unlimited number of menu templates which each have the text and tick boxes in different positions.

We envisage having the patient ID and menu template bar code at the top of the printed menu for each patient.  The layout information for where the information is needs to be loaded therefore for each scanned page as we have to assume that each page layout is different.

This requirement is quite different to the normal fixed layout requirement that are typical for OMR/OCR applications.

If anyone is out there who is prepared to assist then please reply!




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 accountor Register a new forum account.

#2 Posted : Thursday, March 23, 2006 9:47:19 AM(UTC)


Groups: Manager, Tech Support
Posts: 367

Was thanked: 1 time(s) in 1 post(s)

I assume you have the following:
There's a group of text strings (maybe large, but anyway limited).

A custom menu will contain a sub-group of these strings, and next to each of them there will be a checkbox (either empty or ticked).

Any particular string may or may not exist, and if it exists, it could
be anywhere. However, if it exists, the location of its checkbox is fixed relative to it.

If these assumptions are correct, you could perform your recognition in 2 stages as follows:

1. Perform text recognition to obtain all text strings. Isolate all the
strings that exist in the page and get their locations from the recognition result.

2. Create custom zones for the check boxes based on the locations of the text strings, then perform marks recognition using these zones.

Could this work?

Amin Dodin

Senior Support Engineer
LEAD Technologies, Inc.
You cannot post new topics in this forum.
You cannot reply to topics in this forum.
You cannot delete your posts in this forum.
You cannot edit your posts in this forum.
You cannot create polls in this forum.
You cannot vote in polls in this forum.

Powered by YAF.NET | YAF.NET © 2003-2024, Yet Another Forum.NET
This page was generated in 0.062 seconds.