• We’re currently investigating an issue related to the forum theme and styling that is impacting page layout and visual formatting. The problem has been identified, and we are actively working on a resolution. There is no impact to user data or functionality, this is strictly a front-end display issue. We’ll post an update once the fix has been deployed. Thanks for your patience while we get this sorted.

OCR from jpeg files

KayGee

Senior member
hi, i have a bunch of jpegs containing ONLY numerical data which i need to extract and use. i've tried converting the jpegs to pdfs and using some shareware programs, but had no luck. i also tried printing the jpegs and then scanning them and then using the OCR tool in microsoft scanning, but that didn't work either. it'll be really painful having to type all those numbers manually, so i was hoping someone might have a suggestion.

any help is appreciated. thanks in advance

here's a sample file : http://i72.photobucket.com/alb...e_13/Digtem-Tran05.jpg

edit : apparently, photobucket resizes images, the actual images are much, much bigger and clearer.
 
Originally posted by: KayGee
hi, i have a bunch of jpegs containing ONLY numerical data which i need to extract and use. i've tried converting the jpegs to pdfs and using some shareware programs, but had no luck. i also tried printing the jpegs and then scanning them and then using the OCR tool in microsoft scanning, but that didn't work either. it'll be really painful having to type all those numbers manually, so i was hoping someone might have a suggestion.

any help is appreciated. thanks in advance

here's a sample file : http://i72.photobucket.com/alb...e_13/Digtem-Tran05.jpg

edit : apparently, photobucket resizes images, the actual images are much, much bigger and clearer.

Good news, OCR software from folks like scansoft should be able to handle it. Bad news, its only 90 something percent accurate which means you still need to double check all of those numbers (unless your process can handle some amount of error)....

This seems like a perfect Amazon Turk job 🙂
 
I do a regular checkup on this fella's computer.

He has lots of pages to scan/proofread.
So, I put him onto OCR, set it up for him etc (latest versions), clean scanner screen etc...

Most of the time, it works out quicker for him to type the page out from scratch.

 
Scansoft is now Nuance. The product, OmniPage Pro 15 will do the job and is worth every penny.

OPP15
 
bsobel, montag451, corkyg, thanks for the tips guys. i really appreciate it. i have 9 pages just like the one in the link, so i think i might have to give omnipage a shot. thanks again.
 
I still use Textbridge OCR and it is free that come with my other old scanner works great with office 2007
 
I've used AbbyyFine OCR software to do what you want.

I first learned about AbbyyFine when it came bundled with a Lexmark priner I bought many years ago.

So there's another alternative for you.
 
thanks for the help guys, omnipage worked like a charm. Rottie and scott, thanks for the suggestions, i'll keep those two names in mind.
 
Back
Top