Slashdot Mirror

1. http://www.sharpics.com/tabletop-monopod-p-28.html
2. Digital camera with a remote switch option (i.e. Poweshot G10)
3. Black Surface
4. Bright Lights
5. http://www.i2s-bookscanner.com/produits.asp?gamme=1011&sX_Menu_selectedID=path_1011_GEN (To 3d deskew text)
6. http://finereader.abbyy.com/ (to straighten up text a bit more in the 2d realm, and OCR the book)

Via this method it's about as fast as you can flip the pages. (Use the remote switch with your foot.)

Unfortunately you can't buy this convenient device any more:
http://hughsung.com/blog/index.php?itemid=61

While we are on the topic, anyone seen a good solution to scan, OCR, and reconvert existing crappy pdfs to improve them?

I've tried quite a few free and proprietary OCR's and the best available right now, imho, is ABBYY Finereader. Other than fonts, it also easily recognizes tables, diagrams and illustrations. But most of all, it can read and render 189 languages (including Chinese and Cyrillic) accurately. A free trial version is available.

Also, those scanners are VERY expensive. Using a camera would be MUCH better, if the problems can be solved. It doesn't matter how big the camera images are, since the ABBYY FineReader PDF-making software we use OCRs the image and makes searchable PDFs.

The Fujitsu fi-6230 Sheet-Fed and Flatbed Scanner gets good reviews and the flatbed scanner is fast, but it costs $1,200, and the sheet-fed and flatbed scanners are weirdly and unnecessarily connected.

Less expensive Fujitsu scanners lack TWAIN or ISIS driver support. Fujitsu uses proprietary drivers for the less expensive scanners, meaning that it can make them obsolete for some future operating system merely by not providing drivers.

The Fujitsu ScanSnap S1500 Instant PDF Sheet-Fed Scanner is excellent for what it does, we have one, but it doesn't do books, of course.

Err what are you talking about? The issue isn't processing speed, it's bloated OS code consuming unnecessary resources.

As for your task, it may not have been done on single machine in a reasonable timeframe and certainly not in a point and click fashion. However you could have easily integrated the ABBY engine into a networked batch OCR solution and then hired the capacity to run it (eg: a renderfarm).

Just to add to all the above posts refuting the claim that pirated CDs are "infected" - I live in Russia, and I've bought plenty of those here - and not a single time there was a virus, trojan, or anything of a kind on such a CD.

I would reccommend taking a look of Abbyy's offerings. Particulary FormReader 6.5 Family which is intented for OCRing forms and semi-structured documents.

http://www.abbyy.com/formreader/

Nuance's (formerly Scansoft) Omnipage

and then a number of smaller players like SimpleOCR

In the open source world, some places to start looking are:

GOCR

and GNU's OCRAD

Both Nuance and Abbyy offer an SDK for OCR integration at a code level which might suit depending on your budget. Certainly the price (probably between $500 and $5000 for a license) represent a good deal if you look at the costs and time it would take to write anything that does serious OCR work yourself.

BTW, if anyone out there knows of any good document layout analysis code available to have a look at, I would be particularly interested. I am looking into document layout analysis for a personal project and although there is a fair bit of academic research available at Citeseer, I actually haven't found much in the way of good sample code that I can use as a starting point for some of my own ideas.

ABBYY FineReader is great OCR software. However it's not free, and is for Windows only I believe.

I have done once almost the work you have to do. I put all the paper into sheetfeed scanner (friend of mine in "another" department had one), got jpegs with 300dpi resolution and burned them all on a CD. Then I run them all through OCR on my PC and finally through (a translation software Promt ) Later on I would eyeball the translation and correct it manually, but you do not need this step at all as you do not need any translation.

The whole setup worked just fine for me. Well, if I had no friend with a scanner solution I would probably just buy myself one and use a document management software. My favorite one is Fine-reader Macintosh version is also available.

PDF is good if you want to package the images as books, but I believe jpegs can be processed on almost any system. We actually used these HP digital senders, but not that much.

This claims hardwriting recognition. (Although it requires some sort of structure in the OCR'd page I think)/

www.expervision.com/webtr6.htm

http://docmorph.nlm.nih.gov/docmorph/ here are some OCR programs

http://www.scansoft.com/omnipage/

http://www.abbyy.com/

more ocr links than you really want http://web3.humboldt1.com/~jiva/ocr/_ocr_resource. htm

You can try FineReader from ABBYY

I've tested and compared OmniPage Pro to Abby FineReader

You can also download a fully functional demo version that will run 15 times. So it couldn't hurt to give it a try.

I'm pretty sure that Abby FineReader has language modules, so you can scan works in many languages

I'll say, in fact it supports the following: Armenian (Eastern), Armenian (Grabar), Armenian (Western), Bulgarian, Catalan, Croatian, Czech, Danish, Dutch, Dutch (Belgian), Estonian, Finnish, French, German, German (new spelling), Greek, Hungarian, Italian, Latvian, Lithuanian, Norwegian (Bokmal), Norwegian (Nynorsk), Polish, Portuguese, Portuguese (Brazilian), Romanian, Russian, Slovak, Spanish, Swedish, Tatar, Turkish, and Ukrainian. Only European languages, but still impressive.

In regards to accuracy: I've tested and compared OmniPage Pro to Abby FineReader and Abby is much, much better at text recognition. It doesn't offer as many export formats as OmniPage Pro does, but it does include an SDK, so if you can get your hands on some programmers you might be able to fiddle with it some. Abby is definitely a step up from OmniPage.

dealing with multiple languages such as Spanish and French

I'm pretty sure that Abby FineReader has language modules, so you can scan works in many languages.

Bad news: it costs money (so you can use 30-day trial version) and it made for Windows.