ocr
Latest
IRIScan Book 2 mobile scanner: Review and giveaway
Although I tend to use my iPhone 4S and Readdle's Scanner Pro (US$6.99) or JotNot Scanner Pro ($1.99) apps to do most of my scanning, there are still documents that need a regular scanner of some sort. For that, I have an old Epson 4490 Photo scanner, but it has issues handling anything that isn't flat. For example, I've been trying to scan some sections of some really old books into a digital format, but due to the thickness of the book the section nearest the spine of the book is unreadable on a scan. The new IRIScan Book 2 (US$129.00) mobile scanner is a lightweight scanner that can handle a number of document types easily. Design When it comes to portability, the IRIScan Book 2 is almost as easy to carry as an iPhone. It's a tiny 10" long, 1-1/8" wide wand that averages a little over 1" in height. It's entirely self-contained: the scanner contains a pair of AA batteries (included) and uses a micro-SD card (2 GB card included) to hold your scans until you're ready to process them. There's also a micro-USB port and included cable for dumping your scans to a computer for processing. %Gallery-161947% It's an attractive little scanner, with a metallic blue finish and a carrying bag to protect it while in transit. Some addition value and power comes with the software that's included with the IRIScan Book 2 -- Readiris Pro 12 is an older version of the OCR and scan management software that is sold by I.R.I.S. Note that there is an iPad version of Readiris ($37.99) on the App Store; it is not included with the scanning hardware. Functionality The IRIScan Book 2 works like a flatbed scanner, only you provide the motion of the scanning head over the item to be scanned. There's a large and clearly labeled scan and power button; pushing it for two seconds turns the device on (or off), and a quick push starts or ends the scanning process. I decided to test the device without reading the instructions, so I grabbed a catalog for a local community college where I teach and started scanning away. Although the original catalog was printed on newsprint and had been folded for mailing, the scans were still extremely clear and legible. I also like the idea that you don't have to scan from top to bottom on a page; it's also possible to scan from side to side, which works best with books. Another pair of buttons provides an easy way to switch between color and grayscale scanning, or change the resolution of your scan from 300 to 600 dpi. There's a tiny LCD to show you how many scans you've made, what mode your currently in, and to help you set the time on the device. Let's talk for a minute about Readiris Pro 12, the scanning and OCR software that comes with this little scanner. To be honest with you, I'm not a big fan of scanning software. OCR software, which I've used since the early days of scanners, always has the same problem -- it works great for scanning one-column text, but start throwing a lot of columns, tables, and graphics at one and you end up doing a tremendous amount of manual labor to try to extract text from your scan. That's not to say that Readiris Pro 12 doesn't work well -- it does. As an example, I scanned a page from a book with wide margins and the text was saved into an RTF file that was completely accurate. It's just that the number of situations in which you're going to get this type of OCR accuracy are relatively few. When I scan documents, I prefer to just keep them in a PDF format without doing any OCR. In other words, the documents are an image of a document rather than the textual information. Sure, that makes for larger file sizes, but at least I'm not fighting OCR software to try to get readable text. As for the scans, take a look at this gallery. The first two images show one scan from a book, the other from a tabloid-sized course catalog, both "scanned" with Scanner Pro. The next two images are the same types of pages scanned with the IRIScan Book 2, and the final two images are using JotNot Scanner Pro. %Gallery-161942% The scans from JotNot Scanner Pro and PDF Scan are both curved somewhat due to the curvature of the book's page, but they're both quite legible. The IRIScan Book 2 scanned the curved page nicely, but note that if you're scanning a book with very narrow margins, you'll have problems. Looking at the catalog page, you'll notice that the page is cut off in the IRIScan Book 2. That's because the scanner only scans documents up to 8.5" wide. The scans from the iPhone applications were both full-width; I felt that JotNot Scanner Pro worked better for this page. Conclusion Before you invest in a document scanner, think about your end goals. Are you planning on scanning every document you receive in order to achieve a paperless life? If so, maybe a sheet-fed scanner would work better for you. Are you thinking about just scanning receipts while traveling? If you already have an iPhone or iPad, then perhaps scanning software will work better for you. But if you often need to scan articles from magazines or if OCR is a necessity, then the IRIScan Book 2 is a reasonably-priced and definitely portable scanner for you. Pros Compact size makes it travel-friendly Does not need to be attached to a computer in order to scan Attractive design Comes with OCR software package Absolutely quiet in operation Uses widely available AA batteries Cons Is not rechargeable Limited to 8.5" wide scans Who is it for? Best suited for those who need a small, portable scanner that is capable of scanning articles and converting them to editable text. Giveaway You know how we love to give away review items here at TUAW, and sure enough we have a full IRIScan Book 2 package complete with Readiris Pro 12 software, the 2 GB memory card (installed), and more. Here are the rules for the giveaway: Open to legal US residents of the 50 United States, the District of Columbia and Canada (excluding Quebec) who are 18 and older. To enter, fill out the form below completely and click or tap the Submit button. The entry must be made before August 10, 2012 11:59PM Eastern Daylight Time. You may enter only once. One winner will be selected and will receive an IRIScan Book 2 scanner and software valued at $129.00. Click Here for complete Official Rules. Loading...
EyeRing finger-mounted connected cam captures signs and dollar bills, identifies them with OCR (hands-on)
Ready to swap that diamond for a finger-mounted camera with a built-in trigger and Bluetooth connectivity? If it could help identify otherwise indistinguishable objects, you might just consider it. The MIT Media Lab's EyeRing project was designed with an assistive focus in mind, helping visually disabled persons read signs or identify currency, for example, while also serving to assist children during the tedious process of learning to read. Instead of hunting for a grownup to translate text into speech, a young student could direct EyeRing at words on a page, hit the shutter release, and receive a verbal response from a Bluetooth-connected device, such as a smartphone or tablet. EyeRing could be useful for other individuals as well, serving as an ever-ready imaging device that enables you to capture pictures or documents with ease, transmitting them automatically to a smartphone, then on to a media sharing site or a server. We peeked at EyeRing during our visit to the MIT Media Lab this week, and while the device is buggy at best in its current state, we can definitely see how it could fit into the lives of people unable to read posted signs, text on a page or the monetary value of a currency note. We had an opportunity to see several iterations of the device, which has come quite a long way in recent months, as you'll notice in the gallery below. The demo, which like many at the Lab includes a Samsung Epic 4G, transmits images from the ring to the smartphone, where text is highlighted and read aloud using a custom app. Snapping the text "ring," it took a dozen or so attempts before the rig correctly read the word aloud, but considering that we've seen much more accurate OCR implementations, it's reasonable to expect a more advanced version of the software to make its way out once the hardware is a bit more polished -- at this stage, EyeRing is more about the device itself, which had some issues of its own maintaining a link to the phone. You can get a feel for how the whole package works in the video after the break, which required quite a few takes before we were able to capture an accurate reading.
Google reCAPTCHAs now featuring Street View addresses, 221b Baker St. to get even more famous
If you've enjoyed decrypting the often frustratingly skewed (and occasionally humorously juxtaposed) reCAPTCHAs, you might be a bit sad to learn that Google is mixing things up with some rather more boring numerals. The combinations of two words are typically used as part of a registration form to ensure the registrant is, indeed, human. Google is now replacing one of the words in some of its reCAPTCHA forms with photos gleaned from Street View service. Google says it uses these numbers internally to improve the accuracy of Street View and that pulling them into reCAPTCHAs is part of an "experiment" to "determine if using imagery might also be an effective way to further refine our tools for fighting machine and bot-related abuse online."In other words, Google's bots are already capable of decoding these numbers, which makes this all sound like a bit of a challenge to the rest of the OCR-loving coders in the world. Any takers?[Image Credit: dirtbag]
Daily iPhone App: WorldCard Mobile scans your business card collection
The paper business card may go away someday if innovative apps like Bump and Evernote Hello take over, but for now we're still dealing with these little chunks of cardboard. Of course, in almost all cases it's not the physical object we care about, but rather the data printed on the card. (Some exceptions are inevitable.) Getting those inky bits converted to actual bits is easy enough with your iPhone and the right app. My default tool for business card scanning has been CardMunch, which has a number of advantages: fast, ties in easily to parent company LinkedIn, accurate (using actual humans to do the card transcription) and free. Unfortunately, CardMunch's cloud dependency means that sometimes it can get backed up, and when you're sitting on an airplane with a stack of post-conference business cards to go through, it's quite likely useless. That's where the Penpower family of contact management apps comes into play. The flagship iPhone app is the US$6.99 WorldCard Mobile, and it picks up nicely where CardMunch leaves off. You can scan your cards neatly without any network connection, and all the OCR processing is handled locally on the phone. Additional features include the ability to copy an email signature and parse it into a contact record, which is a lot more useful than I thought it would be. How good is the OCR function? Well, you can test it yourself with the app's lite version (allowing three scans the first week, and one scan per week after that). In my evaluation, I'd give it a B+ compared to the intelligent transcription of CardMunch -- keeping in mind that CardMunch also makes mistakes on some cards. Given that it's working in disconnected mode, the slight loss in accuracy seems to be a reasonable tradeoff. What's a little harder to take is WorldCard Mobile's UI, which has the same weird aesthetic and hinky buttons as a lot of other utilitarian apps on the App Store. It compares unfavorably to CardMunch's clean look, and it's most reminiscent of the early versions of Readdle's apps (which have come a long way since v1, in fairness). The lite version will let you know pretty quickly whether the look will make you nuts or not. Penpower also has a WorldCard Contacts app, which lets you keep the card images alongside your contact records but omits the OCR tool; it's $2.99. There is an iPad version, too, which costs $14.99 and doesn't quite work as advertised with the iPad 2's onboard camera, per reviewers -- it's apparently not quite high-res enough for accurate recognition. If you're a frequent business card recipient and you'd like to be mobile-enabled, check out WorldCard Mobile; start with the lite version, and if it's useful you can fork over the $7 for the full build.
Doxie Go portable scanner creates searchable PDFs without a PC, syncs to almost anything
As far as scanners go, Doxie makes some of the more interesting products on the market. There's one problem though... the bright trail of hot pint hearts splashed across the front. Thankfully, the upcoming Doxie Go dons a more conservative shell that will look just as at home in a CEO's office as it would in a 16-year-old girl's bedroom. The Go is a portable scanner with built-in memory for up to 6,000 pages, and you can even add on more storage through the USB port or SD slot. All scans are automatically fed through OCR software and turned into searchable PDFs. To get the scans on your PC you actually sync the Doxie Go to your Mac or Windows machine. You can also sync with your iPhone, iPad or send your documents straight to Dropbox, Evernote or Google Docs from the Doxie 2.0 desktop app. You can pre-order the Go now for $199 and it'll start shipping in late November. Check out the gallery below and PR after the break. %Gallery-136890%
LG announces LSM-100 Scanner Mouse, saves valuable desk space
You may recall, back at CES, we got our hands on LG's LSM-100 mouse scanner and were able to try it out for ourselves. Well it appears that you may have that same opportunity soon. The company has announced that it will be "opening a new era for scanners" at IFA in a few days with its mouse that boasts a built-in scanner. Simply by holding the Smart Scan button, you'll be able to save or drag and drop scanned images as large as A3 paper size in a variety of formats -- PNG, JPEG, TIFF, and PDF, just to name a few -- by swiping the mouse over it. If that wasn't enough to entice you, the peripheral also features Optical Character Recognition that converts text from said images into an editable Word document. Perhaps lost in all this is the fully functioning mouse bit... which you'll probably need as well. No word yet on pricing or availability, but hopefully soon, you'll have room on your desk for one of these. Update: Apparently this bad boy is already available the UK for £89.98 (around $148), via the coverage link below. Also, we added a promo video from the folks at LG showing the peripheral in action -- which you can check out after the break. [Thanks to everyone who sent this in]
Google Docs gets an Android app, we go hands-on with tiny spreadsheets (video)
Staring at spreadsheets crushed down to unreadable sizes on a 4-inch phone screen is far from pleasurable but, clearly there is a demand. In fact, we've been clamoring for a proper Google Docs app for ages, even though sometimes we're not entirely sure why. It was only a matter of time before Google finally got around to appeasing us mobile workaholics and put an official app in the Android Market. Well, our masochistic prayers were answered -- the Mighty Goog unleashed the new, native Google Docs for Android app and we rushed on over to the Market, clicked the install button, and gave it a whirl. %Gallery-122400%
Google Docs gets an Android app, lets you capture text with your phone's camera
Google's had a mobile-friendly version of Google Docs available for some time now, but it's now finally gone the extra step and released a dedicated Android app. That will of course let you access and edit your documents on your smartphone, but the real standout feature is the ability to capture text with your phone's camera and have it instantly made editable thanks to some optical character recognition. Google notes that won't work with handwriting or some fonts, but it promises it will get better over time. Hit up Android Market to try it out for yourself.
ScanDrop comes to Mac: makes scanning to cloud services simple
I've been a fan of a paperless workflow for a couple of years now, and I rely heavily on Evernote for organizing everything scannable that crosses my desk. One of the tools I've found invaluable for speeding up the scan and filing process is ScanDrop, as it allows me to scan a document and do basic image editing. I can also send a PDF to Evernote with a name, tags, and the appropriate Notebook setup without having to juggle files between multiple applications. Unfortunately, this has also kept my scanning leashed to Windows, since ScanDrop didn't exist for Mac OS X. I was delighted to find out that OfficeDrop has debuted a Mac OS X version on the Mac App Store at the bargain launch price of US$1.99. If you aren't an Evernote user, ScanDrop also works directly with Google Docs and OfficeDrop's own commercial cloud service, or you can scan files to any location on your drive, enabling you to sync documents to Dropbox, iDisk or similar solutions. The only downside is ScanDrop depends on the service to do optical character recognition (OCR), so you'll need to be an Evernote Premium user, a subscriber to OfficeDrop, or put up with the limitations with Google Docs' OCR. If you're saving to your drive, you may need to find an additional tool for OCR or live without searchable text documents. Make sure to read over the details about scanner support to make sure ScanDrop will work with your hardware before you click purchase.
DocScanner successfully transitions from iOS to Mac app
Today I spent a half hour playing around with the first iOS app to Mac OS X app port I've gotten my hands on, and if DocScanner is any indication of the quality and usability of other iOS apps transitioning to the Mac, the Mac App Store is gonna rock indeed. DocScanner iPhone is an existing app that turns your iPhone into an OCR scanner. You simply snap a photograph of a document, and the app uses built-in OCR (Optical Character Recognition) technology to extract the text from the document. The app then lets you save the text as a PDF for emailing or sharing with Evernote. DocScanner Mac is the OS X version of the iPhone app that works just as well and offers added functionality because it allows you to turn any camera into an OCR scanner. Simply snap a picture, import it to your Mac then drag it to DocScanner Mac's interface. You'll then be presented with a PDF version of the text that you can copy and paste into any editable document. The logic for bringing DocScanner from the iPhone to the Mac doesn't end with simply allowing you to use any camera as an OCR scanner. Porting the iOS app to Mac OS X allows DocScanner to take advantage of the OpenGL 3D accelerated graphics on your Mac. The results are much faster image processing and OCR extraction than you could ever hope to get on your iPhone. Out of the hundreds of thousands of apps for iOS, a large majority of them would probably not offer added user value if they were ported over to Mac OS X (like currency apps or apps that are fronts for websites such as Mint or Yelp). But an app like DocScanner is an excellent example of the usefulness that select iOS-to-Mac ports will provide. DocScanner iPhone is on sale now on the App Store for US$0.99. DocScanner Mac makes its debut tomorrow exclusively in the Mac App Store for $14.99.
Thimble concept translates real-world input into real-time Braille (video)
From the great tomorrowland of concept videos comes yet another potentially life-changing product: a thimble (looks more like a one-finger glove to us) that takes ambient input and relays it in via an electro-tactile grid to the wearer's finger in Braille. It gets text input from an embedded camera, like in the picture above, or pulls RSS feeds, books, or presumably any other text via a Bluetooth-paired smartphone. We are, of course, addicted to the flow of info our mobile devices feed us throughout the day, and this little guy seems like the perfect tool to bring that flow more easily to the visually impaired. Now, venture capitalists, work your magic -- we'll be expecting to see this thing on shelves just in time for holidays season 2012. Video after the jump.
Word Lens: an augmented reality language translator for iPhone
Word Lens is one of those apps that grabs your attention the first time you see it in action. Created by Quest Visual, it is an iPhone-based optical character recognition (OCR) application used for language translation. In real-world usage, it will translate a foreign language sign in an instant using your camera. Word Lens uses OCR to single out the letters in an image captured by your camera. It identifies letters, builds the words and looks them up in its built-in dictionary. Once the words are identified, translation from one language to another is easy. Translation is not perfect, but it is good enough to get the basic understanding of the translated words. Word Lens is similar in functionality to Google Goggles, which also lets you translate words within an image. Word Lens, though, has a leg up on its competition as the image processing and translating is done on the phone, in real-time. Google Goggles relies on Google's servers for the translation, which slows down the translation time and requires you to have an internet connection. Word Lens is now available on the App Store for you to try. The core app is available for free, and language pairs (English/Spanish) are available as an in-app purchase. At launch, the app only supports English to Spanish and Spanish to English translations. Additional languages will be added in future versions. If you don't want to buy a language pack, it is worth a download as the app includes two demo modes. The reverse mode will reverse the letters in an image, and the erase mode will white-out the words. Word Lens requires iOS 4.0 or later and a video camera. It is compatible with the iPhone 4, iPhone 3GS or the 4th generation iPod touch. You can see Word Lens in action after the break.
Pleco Chinese Dictionary iPhone app now handling real-time image translations
Talk about timely. We've been waiting for months (with bated breath, might we add) for Pleco 2.2 to finally hit Apple's App Store, and after dealing with a few launch day bugs last week, we can finally say it's out and ready to dominate any Chinese homework you've been hastily procrastinating on. The Pleco Chinese Dictionary is now available in the app store at version 2.2.1, supporting both fullscreen handwriting input and live camera-based character recognition. Have a peek at the video past the break if you're still curious as to what this app can do for you, and feel free to toss your experiences with it down in comments below. Here's hoping this is only the first of many languages Pleco decides to tackle -- not that we're much on tossing out subtle hints.
Prizmo is a pretty amazing iPhone app for OCR and more
There are a few apps that are great demos for the iPhone. Pulse News is a super RSS feed reader, iMovie always drops a few jaws, and Siri is a pretty amazing way to talk to your iPhone and get intelligent search results. You can add Prizmo to the list of great demo apps, and it's going to be a very useful app for a lot of people. Prizmo combines OCR (Optical Character Recognition), text to speech, and translation all in one place. Prizmo, which sells for US $9.99, can scan business cards, books, white boards, or even receipts. It can output the text to the clipboard or email, and can even take a receipt and put it into a spreadsheet format. If that isn't enough, Prizmo can read the text to you with the addition of an optional text to speech module. There are 35 voices you can choose from, in ten languages. Each module is $2.99. %Gallery-100014%
Pleco 2.2 Chinese Dictionary uses iPhone camera to translate text in real time (video)
Can't say we've heard of the Pleco Chinese Dictionary app prior to today even though it's been around for two full version releases. Of course, we've seen plenty of Google Goggle-like smartphone apps that can snap pictures and then convert the image to text using optical character recognition (OCR) -- something that can be incredibly useful when important stacks of business cards. Pleco 2.2, however, is one of the first apps we've seen that can translate text in real time using the live image presented on your phone's camera display. The new feature, targeted for release in September, requires iOS 4 and should work with either the iPhone 4 or older 3GS. Sure, you might not need this app every day, but it might just be the difference between ordering chop suey or a thousand-year old egg garnished with a side of stinky tofu. See it in action after the break.
Prizmo provides optical character recognition on the iPhone
Prizmo is a popular OCR (optical character recognition) app for the Mac that allows you to scan documents and things like business cards easily and quickly, avoiding the step of typing them in by hand. Now, Creaceed has announced that it's bringing the app to the iPhone, so you'll be able to make use of the really powerful OCR software, all on the go using the iPhone's HD camera as a scanner. As you can see above, it's pretty impressive. It's not just the fact that you can scan for text (I believe there are a few apps, including Evernote, that already allow you to do this), but all of the options that come along with it, including adjusting for brightness and calibrating the scanner. Anything you scan gets included in a Spotlight search, and you can also share whatever you put in right off to Dropbox or similar Cloud apps. Very cool. Creaceed hasn't set a date or price for the app officially yet, so look for it soon on the App Store.
LookTel's 'artificial vision' makes Windows Mobile useful to blind people (video)
There's a surprising abundance of tech geared toward helping out people with visual impairments, but you won't find too many smartphones populating that sphere of electronics. Aiming to reverse this trend, LookTel is in the Beta stage of developing so-called artificial vision software that combines a Windows Mobile handset with a PC BaseStation to provide object and text recognition, voice labeling, easy accessibility and remote assistance. It can be used, much like the Intel Reader, to scan text and read it back to you using OCR, and its camera allows it to identify objects based on pre-tagged images you've uploaded to your PC. Finally, it allows someone to assist you by providing them with a remote feed of your phone's camera -- a feature that can be useful to most people in need of directions. Skip past the break to see it demoed on video. [Thanks, Eyal]
Meet Star Trek Online's dashing Joe Blancato
Hey we know this new Star Trek Online guy. No really, we swear -- we've got proof and everything! You know, we don't normally talk about these things but since we taught Joe so much in his short time with here, we feel like it's important to share.It wouldn't be going too far to say that because of us here at Massively, Joe was able to master a rare form of the martial arts known as Kung-Blogging-Jeet-Jistu-Do. So if you're ever wondering why his writing is so deadly and sharp, now you know. Also, if you ever see him shooting lasers out of his eyes, he learned that one from us, too.Okay, fine. In actuality, Joe's a really great guy and we know he'll make a wonderful online community representative for Star Trek Online. There are no ridiculous expectations or assumptions in our minds, either. Once he's gained untold success and riches, we'll even wait patiently for our golden toilet seat covers to come in the mail.
Video: Japanese robot reads aloud from books, whispers vague threats while you sleep
Perhaps our Future Robot Overlords™ aren't planning on decimating the human population after they take over -- they might have a good reason to retain a handful of bipedal hominidae. Who knows, really? But we're betting that if they do, the lucky slave population is going to want to hear some bed-time stories from time to time. To that end, Japanese researchers have developed Ninomiya-kun, a 3.2-foot tall aluminum-framed robot capable of reading aloud from printed material. Developed at Waseda University and recently unveiled at a trade fair in Kitakyushu, the bad boy uses cameras to "read" the text, which it parses with OCR software before synthesizing its voice. As far as we can tell, this thing still sounds like a machine, and it's vocabulary is somewhat limited (it can currently recognize over 2,000 kanji, hiragana and katakana characters), but researchers are working on a more lifelike voice and a broader vocabulary. After that, the developers would like to unload this thing on elementary schools and old folks homes, whose population won't find this thing creepy or disconcerting at all, at all. We're sure of it. Peep the video after the break.[Via Pink Tentacle]
PDFpen 4 adds OCR and Word importing
SmileOnMyMac has released a major update to PDFpen, their PDF editing software which we examined at a while back. PDFpen allows you to edit PDFs to fill out forms (e.g. scans of existing forms), mark-up documents, etc. The biggest new feature for version 4 is the inclusion of basic OCR functionality that will turn a scanned document into editable text. In addition there is support for new file formats including importing Microsoft Word documents.PDFpen comes in two versions, a basic version for editing PDFs and a pro version that also allows you to create editable forms (i.e. forms that can be filled out by users with a PDF reader like Acrobat or Preview). PDFpen is $49.95 (or $99.95 for the pro version). Upgrades for to version 4 from previous version are $25. Demos for both standard and pro are available for download.
