Tek-Tips is the largest IT community on the Internet today!

Members share and learn making Tek-Tips Forums the best source of peer-reviewed technical information on the Internet!

  • Congratulations IamaSherpa on being selected by the Tek-Tips community for having the most helpful posts in the forums last week. Way to Go!

OCR recognition

Status
Not open for further replies.

KH7210

Technical User
Oct 17, 2005
47
US
Does any one know what the optimum size of type and dpi setting is for adobe scanned recognition system?

I will be scanning large amounts of document and need a good method of retrieval.

Thanks
kh7210
 
...dpi at 300 to 600dpi, 600 yields slightly better accuracy than 300dpi, however 300dpi is sufficient...

...downsample after OCR (if required) is recommended, not before...

...scan in lineart (1bit) or greyscale to keep file size down, color will increase document size and slower processing...

...i've only come across point sizes as low as 7 point in documents i have scanned and OCR'd, not experienced yet with anything lower...

...7 point worked OK here...

Andrew

 
If your documents are all good quality - black type on white background, paper not torn or crumpled, you're in good shape. If you have to go to grayscale, your file size will increase by 6 or 8 times, and system response will be that much slower. Get a really good scanner - nothing under $500. No need of SCSI connection, the new ones connect via USB 2.0. Check out products from for running the scanner and capturing the data to your back end data store.

Fred Wagner
 
Status
Not open for further replies.

Part and Inventory Search

Sponsor

Back
Top