Slashdot Mirror
How Google's High Speed Book Scanner De-Warps Pages
Hugh Pickens writes "Patent 7,508,978, awarded to Google, shows how the company has already managed to scan more than 7 million books. Google's system uses two cameras and infrared light to automatically correct for the curvature of pages in a book. By constructing a 3D model of each page and then 'de-warping' it afterward, Google can present flat-looking pages online without having to slice books up or mash them onto a flatbed scanner. Stephen Shankland writes that the 'sophistication of the technology illustrates that would-be competitors who want to feature their own digitized libraries won't have a trivial time catching up to Google.' First, a book is placed on a flat surface, while above it, an infrared projector displays a special mazelike pattern onto the pages. Next, two infrared cameras photograph the infrared pattern from different perspectives. 'The images can be stereoscopically combined, using known stereoscopic techniques, to obtain a three-dimensional mapping of the pattern,' according to the patent. 'The pattern falls on the surface of (the) book, causing the three-dimensional mapping of the pattern to correspond to the three-dimensional surface of the page of the book.'"
Did they get the "processing software" out of a cereal packet?
Does it run on Linux? Does it work for scanning porn?
I wonder how ass curvature comes out with that scanner.
do NOT sit on the copier machine with pants down at google hq
intellectual property law is philosophically incoherent. it is your moral duty to ignore it or sabotage it
When is the patent office going to quit giving patents for obvious techniques? :)
How long before some particularly vengeful luddite publisher starts printing on treated paper stock that has an IR visible pattern, calculated to confuse these scanners, printed on it?
They've been making "anti-copy paper" designed to defeat optical scanning for years now, surely something similar in the IR band could be effected...
Wasn't this a Sci-Fi movie staple back in the 80s? They used it for body and object scanning, not books...but still.
I've read many comments over the years about the old Bell Labs and how a huge amount of pioneering research came out of them over the course of their existance, i.e. before they got axed.
It would seem that Google Labs is performing somewhat the same function, albeit more oriented towards software rather than physical research.
May the Maths Be with you!
And thus, as easily pointed out in the blurb ("would-be competitors..."), this patent will hamper progress.
Ok, is it just me, but wouldn't it be easier to just cut the spine off the book instead of developing a whole new way of scanning it? I could understand for old/valuable books, but it seems to me to be a bit of overkill.
... The sophistication of the technology illustrates that would-be competitors who want to feature their own digitized libraries won't have a trivial time catching up to Google.
Especially with that shiny new patent.
Cretin - a powerful and flexible CD reencoder
...who's flipping the pages?
That's cool and all that, but who (or what) flips the pages?
--riney
Anyone else wondering lately if anyone else is submitting stories? Or is this guy the next Roland?
What are we going to do tonight Brain?
Can't you just calculate the 3D model of the page based on a known stuff?
Make a generic flattener filter that takes in page height and length, as well as page number.
Manually tweak the output a bit for the first and last pages, and then intermediary pages can all be calculated with much more accuracy than you need.
Hell, with this method any book "scanned" (using a camera from overhead) could be processed. Let those college kids who love Google so much run their books through your filters (and do the manual tweaks and verification) for you. They won't need anything but a tripod, a camera, and the book.
The technique is old, many years old. What is google's patent for? The use of a decades-old technique ON BOOKS?
Unless I'm willing to just shred the books, of course. Cut em up, scan the pages individually, a lot less overhead than a 3d scanner.
...that Google licenses this to scanner manufacturers and we see this at a consumer level at some point in the future? I know I'd pay good money for a book scanner that doesn't need to have a 'book edge' (which you already have to pay through the nose for)...
But who turns the page?
Reviewing just the first hour of video games.
Snapter already does the compensation for curvature:
I lets you use a digital camera to take a picture of an open book with a constant colour behind it.
http://www.snapter.atiz.com/index.php
Imagine what this technology could do for coworkers who like to photocopy their butts!
That's probably a non-issue. Google, for legal reasons, only scans books they're permitted to, or whose copyrights have expired or been abandoned. (legal decision pending though). There are plenty of existing books, that if a publisher decided to be spiteful would amount to less than 1% of what is currently available to google and most works are now done via the computer so there would be an electronic copy somewhere. Google's pipe dream has been to organize the world's information. Therefore, if a group didn't want their work floating around on the internet or for scanning, there are plenty of practical and legal methods for doing so.
Mr. Google book scanner page flipper guy!
When the rest of humanity vomits reflexively at the thought of turning the pages of 7+ million books, you prevail by showing us that, even if your job sucks, you can take pride in it. Some how.
So here's to you, crack open a cold Bud Light and keep on flippin'.
I don't see why this is such a showstopper for other book scanning projects. Right off the top of my head I can think of three methods of dewarping book scans that have nothing do to with Google's methods. While Google's method is definitely quite interesting and seems like a great solution, it is by no means whatsoever the only way of accomplishing this.
That's modded funny, but take a look at this.
Maybe they use automated page turning machines for normal books, and turn pages by hand for older/more fragile works?
"Anyone who [rips a CD] is probably engaging in copyright infringement." - David O. Carson
This is useful and interesting, but doesn't seem particularly novel.
Projecting a known pattern onto a surface or using multiple cameras to determine the shape of a surface have been around for quite a while, so adding it to an OCR system doesn't seem like a big deal.
Umm.. you're aware that "anti-copy paper" is totally worthless against photographs, since any measures that work to defeat a photograph will also work to defeat normal reading too.
Any attempts to make it impossible to detect an IR grid projected on the page will meet the same fate, since very-near-IR is just "red" to some people. (Replace "very-near-IR" with "R+epsilon" if you need further explanation.)
What could you do?
All of the above hurt regular readability and/or violate the laws of physics, so nobody would want your book if you used any of them.
"We want our Library!"
"And most of all, we want our REAL books!"
- Your local Scooch-a-mout belief circle
Actually, Google's non-invasive scanning approach would have prevented the belief circle collision, as it didn't require the shredding of any texts. Not sure how well it would scale to a Library's worth of books, however.
Totally off topic here but I'll risk it.
It really bothers me that neither Rock Band nor Guitar Hero can auto-calibrate the audio lag using the microphone. There's absolutely no reason I can see that they can't "listen" for the calibration beeps with the mic to get a perfect reading.
I wonder if this will every get out of beta.
If the publishers see this article, the next book I want to read is going to be written in capchas!
The really hard ones without an audio guide!
Cough, you don't ahve to. I can copy your book all gad damn day long and have not violated your rights or the copyright code.
The moment I try to distribute them, then it's a copyright violation.
It's called copyright, because the only reason one would copy it was to distribute it.
Backup really wasn't an issue then like it is now.
The Kruger Dunning explains most post on
De-warping sounds useful, but there are problems that it probably won't solve --
Like the operator who scans a book page with his/her fingers or hand stuck between the page and the scanner-glass. For example, the dreaded 'New York Hand' or its fingers can be seen occupying the place of part of the text or figures on many pages of books scanned for Google-Books from the New York Public Library. On some pages, the impression of the fingers is clear enough to show the rings worn by the Hand that was doing the scanning. :(
It will take more than a de-warping patent to solve that one .....
-wb-
I once confessed to someone I wanted to digitize one of the books I have. (out of copyright for over 25 years now).
Turns out he was involved with one of the big book-digitizing projects. He told me they had already digitized the book(s) I have. Besides that it was a translation, it turns out that their cameras broke down somewhere along digitizing this book And apparently this didn't get noticed. So over 90% of the digitized pages were blank.
So personally, if they claim 8 million digitized pages, I'll believe 800 thousand for now, I need more proof to believe more....
Do they have a patent for a mechanical arm that turns the pages ?
You didn't buy my book - you copied it onto the internet for others to read - and thus stole from me.
Just ask my friend Ursula K. LeGuin, you PIRATE.
-- Tigger warning: This post may contain tiggers! --
A typical book page has text on in in parallel lines which can be used to correct for curvature, straight-edge formatted into rectangles which can be used to correct for skew. Who needs another grid?
If a page doesn't have suitable text on it (e.g. a graphic), then just assume it's warped the same as the previous page (the one it's lying on top of).
This is one of those things that pretty much everyone thinks up, then decides "oh it would be too much trouble and in the end no one would really care about the slightly superior results anyway," and then nobody ever really does it. So Google went ahead and did it? Neat!
It's technology Jim but not as we know it :-P
This is way better than my idea, which was to throw the book into a wood chipper, scan the results, and then algorithmically reassemble them...
"Not an actor, but he plays one on TV."
TFA doesn't appear to be mention or even hint at how many books have been scanned. TFA does, however, mention the patent number 7508978....
Be sure to check out the exclusive rights in copyrighted works before making blanket assertions on what is and is not legal under copyright law. The exclusive rights granted by copyright include both reproduction and distribution. There are lots of exceptions to these exclusive rights, but an interpretation that completely eviscerates the exclusive right to reproduce a work is not supported by the Copyright Act.
http://www.google.com/patents?id=wga6AAAAEBAJ&dq=7,508,978
Why is Google's site so much better than the USPTO's?
This is just awesome. A perfect example of using smart engineering to combine existing technologies to result in something effective and useful.
it's derivative.
I'd also much rather hear how they managed the page flipping. Even with a lot of these machines they'd still have to achieve an impressive flipping rate without damaging the page being scanned.
You're not doing a parody of my work, so you have no rights to it.
-- Tigger warning: This post may contain tiggers! --
On that note has anyone tried the option on google books to report unreadable pages and if so do they do anything about it?
note: i'm known as plugwash most places but i screwd up registering that here somehow in the past and now can't register
Back in the early 70s a little firm in Yorkshire, the Scolar Press, specialised in the production and publication of high-quality facsimiles of old books (16th and 17th century). They were faced with the problem of scanning extremely rare and valuable volumes that were too fragile to be fully opened and placed on a flatbed scanner. Their solution was to invent a narrow glass prism that could be inserted into a slightly-opened book, and by clever optics produce an exact, undistorted, optical image of a page.
I turned down a much smaller offer on a much less significant, but still very cool, two hundred year old angler's guide (with hand colored plates and original binding) for the same reason.
Interesting! Would Google be interested in making it possible for you (me, them?) to have your unique book scanned?
You want to sell it someday, but, you want it scanned and accessible for posterity, everyone wins.
I hope Google is listening.
This was sophisticated in 1990 (along with other morphing technologies seen in various music videos of the day). Today it is common sense.
Google should return to the open source community a decent OCR app+engine. Tesserac+ocropus are just too little, and it's already too late.
Windows already has decent ocr habilities, any hp scanner comes with decent image to page-document sofware. It's a shame that google, that has been build upon open source and has maybe the best ocr technology in the world, hasn't returned a competitive and free ocr solution for Linux.
What's in a sig?
I have seen paper shredding trucks arriving at the Google headquarters... I thought it was to take out confidential papers, but maybe it was a delivery?
Gently reply
Why don't they just cut the pages out of the book?
That way they have individual sheets and they can easily scan the pages without all this unnecessary over-engineering.
On that note has anyone tried the option on google books to report unreadable pages and if so do they do anything about it?
Yes, and while I guess instant action is hardly to be expected, on last check it had taken nearly three months after a report of three volumes with dozens of defectively-scanned pages, with nothing doing. (A separate message to the google people had produced only the (semi-automated?) response 'use the option'.) So, it seems like nothing is done about it.
-wb-
I think the austrian book scanner is much more simple+efficient+speedy+page-protecting: http://www.treventus.com/index_en.html
Why not lay the whole book flat in a CAT scanner and grab each page as a vertical slice? I'm kind of joking but maybe someone with CAT scanner experience knows how the machine would respond to the ink on each page and how thin each slice could be.