theBrownfury asks:
"I work at a lab on a university campus that provides services for disabled students. One of the main functions of this lab is to convert printed materials such as books, reading packets, etc. into electronic text(RTF or Word) that is either going to be fed to a text-to-speech synthesizer or going to be further processed for use in braille devices. Ideally we'd like to be able to process 1000 pages a week. However our current solution (a Bell&Howell 4040D scanner coupled to a mid-level PC workstation with OmniPage Pro 11 and 2-3 proofing stations) is limited to an average of 10-11 (16 on a good day) pages per hour because of the constant hand holding the OCR process requires. We've already made sure we're feeding the OCR engine good quality scans. Also it should be clarified that the variety of materials we deal with is so varied that a majority of it cannot be defined by any types of 'general' scanning or OCR templates."
"Do any of you know of a solution which can exploit our current scanner, which we're rather happy with, but bring in a better OCR method to improve our efficiency? It should be noted that the solution should be financially reasonable (as ni less than US$10K).
Our biggest bottlenecks:
- software's terrific inability to accurately pick up the areas of text on the scanned page to OCR
- marking words as possibly erroneous without checking against dictionary elongating the proofing process
- stability of OCR software
Bonuses:
- dealing with multiple languages such as Spanish and French
- capability to OCR matematical texts and papers. Currently we hand type math textbooks for students."
There is no perfect OCR software (Score:2, Insightful)
Re:There is no perfect OCR software (Score:1)
Re:There is no perfect OCR software (Score:2)
I have the solution ... wait ... (Score:1, Troll)
I don't think we'll ever have near-perfect OCR. 90% is as good as it gets.
Re:I have the solution ... wait ... (Score:2)
How handwriting recognition is easier (Score:2, Insightful)
one would imagine that recognizing much more readable printed words would be easier than my inconsistent and messy handwriting.
However, with handwriting on a pda screen, the software gets additional information the order of the strokes. For instance, if you always write one letter clockwise and another counterclockwise, the software can use that to help distinguish the letters. Print can't do that.
Re:I have the solution ... wait ... (Score:2)
text-to-speech math stuff? (Score:5, Funny)
reading packets, etc. into electronic text(RTF or Word) that is either going to be fed to a text-to-speech synthesizer or going to be further processed for use in braille devices.
- capability to OCR matematical texts and papers. Currently we hand type math textbooks for students."
I pity the kids who are going to have to listen to "fluid dynamics on tape":
"Partial rho partial t plus rho times left parenthesis partial u partial x plus partial v partial y plus partial w partial z right parenthesis equals zero".GMD
US Postal Service (Score:3, Insightful)
Re:US Postal Service (Score:4, Informative)
If there is more than a slight chance of a misread, then the machines automatically send the envelope to a human reader, who keys in the zip.
Re:US Postal Service (Score:1)
I think that the US post office has 9 digit post codes for cities in outher countries and I am looking for someone in the US to verify this by sending me a properly bar coded letter. If your game, email me.
Re:US Postal Service (Score:1)
But he just replaces components when they break. All the research, etc. is done by exterior companies.
Re:US Postal Service (Score:1)
Here's a few suggestions (Score:4, Insightful)
Another solution might be stretching your budget by doing your proof-reading offshore.
Re:Here's a few suggestions (Score:2)
An electronic copy definitely will exists - no-one typesets books by hand any more. It is highly likely in fact that the book was written with a mainstream word processing program like Word and a final draft exists in this format. You only need a) to make a strong enough case for them to let you have it and b) a technique for converting it into a format that you can use. The latter probably already exists too.
Re:Here's a few suggestions (Score:3)
Nobody wants to be viewed as being nasty to the disabled.
I have more. (Score:3, Funny)
Achieve 100% Accurecy (Score:5, Funny)
Just like this post!
just curious (Score:1)
Sweet irony! (Score:1)
Abby FineReader... (Score:4, Informative)
In regards to accuracy: I've tested and compared OmniPage Pro to Abby FineReader [abbyy.com] 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.
I'm pretty sure that Abby FineReader has language modules, so you can scan works in many languages.
Re:Abby FineReader... (Score:2, Informative)
Dan
Re:Abby FineReader... (Score:2, Informative)
You can also download a fully functional demo version [abbyy.com] 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.
Re:Abby FineReader... (Score:2)
If you want free, head on over to the National Library of Medicine's DocMorph [nih.gov] page. You can upload TIFF files, and have them converted to plain text in about 15 seconds. Not bad for 'free', I think.
Re:Abby FineReader... (Score:2)
Re:Abby FineReader... (Score:2)
I'll normally go for OSS solutions if I can, but there wasn't anything I could find in the realm of OCR that compared in terms of ease of use and accuracy. If I ever need to do lots of scanning, I'll be investing in a copy of Abby...
ABBYY FineReader... (Score:2)
OpenBook Ruby (Score:2, Informative)
Aphex Twin? (Score:1)
with built in scan to MP3 conversion!
Do you mean through text-to-speech, or through bitmap-to-Aphex-Twin's-face [google.com]?
Yes, I know it's the former, but I was making a joke.Google does this. (Score:3, Insightful)
They've got a number of image-based paper catalogs online and searchable, and thus OCR'd.
Talk about varied formatting. It seems to be reasonably accurate, and I'm sure that the pocess is pretty streamlined -- everything else they do seems to be...
Here is an example [google.com].
Re:Google does this. (Score:2, Insightful)
You don't know what you're missing.
If the OCR fails, you don't get the hit. So long as you never see any false positives, the OCR appears to be batting 1000. In reality there might be a few catalogs that it misses because the OCR didn't work. You just never know.
Compare this to OCRing a document. Every error stands out.
Don't get me wrong, I'm still impressed by Google. They are just solving the 'easier' side of the problem.
Re: (Score:1)
GOCR (Score:2, Informative)
There are good frontends (Score:2)
Well, in the best traditions of UNIX software, the gocr authors decided to keep the user interface and the actual OCR code separate. Sensible.
Actually it comes with Tcl/Tk (gocr.tcl) and GTK+ (gtk-gocr) frontends. My personal favourite, though, is the KDE scanning program, Kooka, which includes support for gocr amongst its many very useful talents.
Do not lock yourself with .doc (Score:3, Insightful)
you will do yourself and your lab a big favor if you choose RTF. RTF is documented [biblioscape.com], so you do not lock yourself with a single vendor (microsoft) for further processing of the electronic data. It may not matter now, but it could be very important for you guys at some point in future ...
Re:Do not lock yourself with .doc (Score:1)
My guess is if this content is geared toward the vision impaired, niceties like hanging indents, styles, etc. aren't that important. In such a case, using XML with perhaps a few style-based tags (such as <B>, <I> <U> etc) should do the trick.
The nice thing about XML data is it's relatively clean, it's easy to convert to other formats, and can be made to store data or metadata as well.
Re:Do not lock yourself with .doc (Score:1)
The XML-hype will be gone soon, don't worry.
Re:Do not lock yourself with .doc (Score:1)
It's true that the XML format is "bulky", but with processor speeds increasing and memory increasingly cheap, that is less of an issue. XML can be processed and cataloged pretty quickly, even if it isn't the most "efficient" way of doing it. Besides, we're talking document access in a specialized library for the visually impaired. We're not talking about many concurrent accesses all going at the same time.
Without a description of the tags used and the relation between them they are just as unreadable as anything else
Wrong. This is the nicest feature of XML! You can actually look at it, and assuming that the tags are intuitively named, you can pretty much figure out what information is in the file. Think about this: which would you rather try to decipher from within a plain text editor: volumnious RTF code, the binary content of a
You can't easily display or print your stuff without digging into the technical side of XML.
Yeah, that is true. Without a decent application capable of opening and interpreting an XML file, you just can't print or display it. That also applies to every other existing data format, except *maybe* plain text, which is not really a useful format to store information in.
XML is not hype. It makes sense as a data storage format for all of the opposite reasons you cited: it can be processed fairly quickly, it is easily readable, even in text format, and there are many tools which allow you to very easily display or print XML formatted information.
Xerox TextBridge Pro (Score:2, Interesting)
The scanner I used is a $99 scanner that is several years old, Canon CanoScan FB620P.
I am very impressed with it. For OCR I used Xerox TextBridge Pro, the interface it awkward, but the OCR part it works. The biggest problem was the way the windows twain drivers were setup such that I had to go through several windows and mouse clicks to scan, and finish scanning.
I can do over 30 pages per Hour, I get about 99.8% on clean copy, the trick was to use a gray scale scan or text mode, Also I scan at 300 DPI , I find it's important to give the OCR as much info as possible to work from.
You still want to run this past a human proofreader, but overall I am very impressed with the setup and it's results.
I'll second that (Score:2)
I first delved into the world of OCR back in 98 with this product and havn't turned back. The current version is made by scansoft (the same makers as OmniPage), this [scansoft.com] product is much better. Even PCWorld has a review [pcworld.com] of it (March 2000).
It achieves 98% accuracy on typed text and can handle graphics, bullets and tables. These were big plusses for me. I still use the 98 version and have very few complaints. Dirty pages can be a problem, but it has frequently amazed me in how it catches characters in the midst of goop.
the trick was to use a gray scale scan or text mode, Also I scan at 300 DPI , I find it's important to give the OCR as much info as possible to work from.
I agree. The right settings are very important. I recommend some serious tweaking before you get to hard and heavy with it. For plain text, the above works great, although I sometimes prefer 150dpi. For anything with tables and graphics, 300dpi is a must. A good scanner can make a big difference too. My work uses network ready scanners that copy the file to a network share and the software picks up the files automatically. Very efficient.
My experiences with OCR... Scanfix+Textbridge (Score:3, Informative)
I started a small document scanning service a few years ago. (I am no longer in that business). The biggest issue in OCR accuracy is pre-process. (in particular de-skew and grayscale removal). If the page is skewed even a couple of degrees OCR will fail miserably. I have had superb results using TMSSequoia Scanfix [tmsinc.com] software which automatically cleans-up and straightens the page nicely. Its expensive but worth-it if you have a lot to scan. I believe that they still have a demo available.
My experience has been that the consumer OCR software is considerably MORE accurate than industrial versions that cost 20X as much. I obtained excellent OCR accuracy using Scansoft's Textbridge [scansoft.com] software which utilized the Xerox Textbridge engine. Scansoft appears to have purchased Omnipage [scansoft.com] OCR and discontinued the Textbridge OCR line. I found that I achieved much higher accuracy with Textbridge then with Omnipage after the document was processed by Scanfix. Textbridge did not have some of the features of Omnipage but Textbridge was faster and better at OCR. I would definately download the Textbridge 98 demo [xerox.com] that is still floating around on the web.
Both Textbridge and Omnipage OCR were vastly superior to anything else I previewed, including Adobe's OCR engine. OCR can be surprisingly accurate but the source image needs to be free of distortion. Sometimes you will need to break up the page into several using photo-editing software since no OCR can inteterpret the structure of a document very well.
I suspect that you will be better off just typing in the mathematics in by hand. Maybe a visual LATEX editor like Scientific Workplace [mackichan.com] would be helpful. The LATEX output could be manipulated using a parser to put the equations into the simpler forms that you need while keeping the raw equation in a form that could be used for other purposes later on.
Honesty, 10pgs/hour is pretty good so it doesn't sound like you are doing all that much touch-up. I suspect that using Scanfix will provide the greatest boost in productivity.
PrimeOCR - primerecognition. Voting Engines (Score:1)
Open Source has no OCR (Score:2)
Kind of surprising.
Help GOCR (Score:2)
My experience, for what it's worth (Score:3, Informative)
The scanner you have is hard to beat. As for the software, I found that the Caere engine was a little better than the OmniPage engine when I first started working with OCR, but over time OmniPage has gotten that little bit extra oomph into it.
Having said that, there are some posts that recommend Abby, a product with which I'm unfamiliar, and state that a trial version is available, so it's probably worth a check.
Finally, one small factor that sometimes is overlooked: what resolution do you scan at? You may want to try lowering the resolution and seeing if that gives any better results. Lowering the resolution can have the effect of smoothing out some of the noise that can confuse OCR engines. Try going all the way down to 200 dpi.
Finally (part two), I've found you can also sometimes tweak the results by playing with the depth -- instead of scanning in b&w, try gray scale (I suggest 4 bit).
Finally (part three), I'm dubious that you'll find anything to handle formulae. For those readers who may be surprised to learn OCR accuracy is not quite up to scratch, just wait until you encounter OCR format preservation.
Good luck -- and if you do get better results, by all means let us all know!
Cheers
Contact BBN - bbn.com (Score:2, Informative)
Good Luck.
Re:Contact BBN - bbn.com (Score:1)
Be Careful -- Might Not Be Fair Use (Score:1)
IAAL, just not a very good one so get a good one's advice.
Correct Scanning: double-entry method. (Score:2, Insightful)
Get 2 different OCR-engine programs
Scan the same text in - to plain text - with program 1, scan it in to a second plain-text file with OCR program 2, and 'diff' 'em, ignoring white-space.
That means the indifidual person running the scanning doesn't have anywhere near the amount of work to do.
Small erors may get through, but it is drastically fast, in comparison with the way it normally is done, eh?