Document identification

[Guest]

Hello to you all

In my .Net application, I want to import document images (Tiff images),
having same format, in a batch,

For e.g. I have a document folder containing mixed images like 'Participant
Registration forms', 'Team Registration Forms', 'Event Details', etc.

I want to process each type of documents in separate batches

i.e. The Batch of importing 'Participant Registration forms' should import
only Participant Registration forms by identifying them from the source folder

The identification would be based on the identification mark or specific
word printed on the documents. This Identification reference will be
pre-defined for each document type before any processing.

Is there any DLL/ActiveX component available to achieve this?

The Identification mark may have shifted little from its pre-defined
position due to scan problem, document size changes, tilted scans, etc.

Also the Identification mark may be distorted due to distorted or bad
scanned documents
So the component should resolve these issues while identifying the document.

Thanks
Jeetendra

 

[Peter Rilling]

What you are looking for are basically OCR (Optical Character Recognition)
libraries. Do you need it to be free?

 

[Guest]

Hello Peter,

Thanks for the reply
Actually, I gone through specifications of so many third pary OCR components
but none of it giving the document identification feature.
The component library should be saticfying my requirements then no matter
whether it is freeware or I have to buy it.

Regards
Jeetendra


"Peter Rilling" ने लिखा: