Forgot your password?
typodupeerror

Handheld Device Reads Printed Words to the Blind 110

Posted by samzenpus
from the too-busy-to-read dept.
geekotourist writes "3,000 people in Dallas this week for the National Federation of the Blind convention are getting a demonstration of what life is like when you can read printed menus, mail, business cards and memos," reports the Dallas Morning News. The NFB spent two million dollars developing the $3,495 Kurzweil-National Federation of the Blind Reader, which weighs 15 ounces and combines text-to-speech with sophisticated OCR. The device 'gives the user an initial "situation report," describing what it can see. The user then makes a decision about whether to take a picture. After a few seconds to process the image, the contents of the document are read aloud.' Beta testers describe the joys of reading receipts, CDs, food labels, bulletin boards, conference printouts, or of simply reading books with privacy, without another person's help."
This discussion has been archived. No new comments can be posted.

Handheld Device Reads Printed Words to the Blind

Comments Filter:
  • by Capt'n Hector (650760) on Thursday July 06, 2006 @12:57AM (#15665008)
    >You are driving on I-80. You are surrounded by cars.
    >*turn wheel right*
    >You have crashed your car. It is on fire.
    >*Run away*
    >I don't understand "away." ...
    • by Anonymous Coward
      Yeah, when I read the blurb stating "3,000 people in Dallas this week for the National Federation of the Blind convention," I was thinking, gee, those guys were just in Seattle last weekend, driving up and down I-5...
  • by DaCool42 (525559) on Thursday July 06, 2006 @12:59AM (#15665016) Homepage
    Wouldn't braile output be better? It would allow for more privacy without the need for headphones, and I suspect most blind people could read it faster.
    • by alphakappa (687189) on Thursday July 06, 2006 @01:05AM (#15665037) Homepage
      A device that would produce braille output on a surface would be much more expensive than one that had to simply convert words to spoken voice (using one of the many excellent text-to-speech technologies available today). Also, where's the lack of privacy when you are using headphones :-)
      • I don't think blind people are really waiting to use headphones. I mean, there is no reason why to obstruct one of the other senses when your main sense is already missing. But maybe for privacy in e.g. public transport, I could see them use headphones. Any blind person reading this on his braille terminal is of course invited to confirm/reject this statement.
      • Actually, couldn't they use something like the old 24 pin printers did? Just have that under a fairly tough membrane....

        I know the 24 pin head would be a bit small; but the theory would be the same. Just make a long pad (maybe 30 characters long?) with these things poking the surface enough to act like braille.... :)
        • Have you seen a braille reader? That is almost precisely how they are designed, except instead of a "tough membrane", the pins just stick up out of the surface (they are rounded, not pointed, and only stick up a millimeter or so above the surface of the reading area). Yes, they are located on "one long pad", so many characters wide.

          Also, have you ever looked at an entire dot-matrix print head? While the area where the pins meet to print is fairly small, the solenoid driver end is actually pretty large - typ

    • by jfmiller (119037) on Thursday July 06, 2006 @01:32AM (#15665118) Homepage Journal
      Braile is not necessarly always the best solution. First a large number of vision impaired people never learn it, esp those that go blind late in life. Second while braile can be read as fast as typed print, it takes a good deal of space. This device is too small for a good surface.

      As a side note, my supervisor is blind and has a device like this of the desktop varity. He can "read" about 300 words per minute, and be doing other things at the same time. I have fine vision but the though of being able to listen to my textbooks while doing the dishes almost justifies the $2500 price tag.

      JFMILLER
      • What about buying a dishwasher machine? They are much cheaper than $2500.
        • I have one of those. Unfortunatly it's as old as I am and the apartment manager doesn't see anything wrong with that. In addation to needing to get all but the most microscopic bits of food off the plate, it also does not hold two of my favriot pots, and of course wooden utensils.

    • As one who is sporadically losing her sight, I would find this very helpful, but do not, as of yet know braille, nor in the middle of medical procedures which may or may not improve the issue in the possible near future, have the time, energy or immediate need to add one more semi-difficult skill to the list of "Help! I'm overwhelmed".

      BUT BOY! It would be a handy addition for the research I need right now.
    • Regarding privacy, is extreme privacy really such a major concern in this situation? I mean, it isn't private information that is being passed along, as much as just reading one's (public) surroundings. I am sure this is much more private than the current method of having a friend reading and explaining everything!

      I have a friend who is extremely dyslexic, and thus can't really read. He loves walking down the street listening to books on tape, as it is his only chance to "read". How much more so for som
    • by hooeezit (665120) on Thursday July 06, 2006 @01:58AM (#15665196)
      This is a common misconception that Braille is the easiest form of presentation for the visually impaired. But that is not so.

      Mind you, I use the word 'visually impaired', and not 'blind' for a good reason. A large proportion of the people considered legally blind do have some vision - they fall into the category called 'Low Vision'. There are about 2 million people in the US at present who have Low Vision, but number will swell significantly as the baby boomers age into 50+. Most visual impairments are actually age related, and when you've had vision till age 55 and you suddenly lose it in 6 months, it's a very disturbing experience. Most people who undergo that experience either do not have the ability to or don't care about learning tactile braille at that stage. Even as of now, only a fraction of the visually impaired population can actually read braille.

      Also, as the other poster mentions, braille devices are extremely expensive, require a lot of power and are bulky (both in size and weight). A braille display with 40 braille cells will cost an additional $2500.

      All that said, I should also mention that building a purely verbal user interface for 'describing' things is a very challenging task. I've been working the last 2 years on a similar device but purely for addressing navigation issues for the visually impaired. We already have a prototype device that can read special barcodes at a distance of about 6 feet, and then that barcode can be looked up in a database to determine the user's location. But how to describe their current location in a manner relevant to their task is proving to be a very tricky problem to solve. Every few months, we feel that we are very close and then discover one more issue that sets us back another few months.

      So, it's encouraging to see that someone has been successfully able to build a verbal only interface for descriptive tasks.

      - Rudrava Roy
      Minnesota Laboratory for Low Vision Research
      University of Minnesota, Minneapolis

      • Why not use gps? That can be so precise nowadays you could even use it for in house navigation.

        What do the barcodes offer that GPS does not? And if you are going to use something like barcodes why not rfid instead?

        I can understand the logic of barcodes 10-20 years ago but in this day and age it sounds like a project that has been around to long and been surpassed by technology. Am I wrong?

        • GPS doesn't work well in situations where there isn't a fairly clear line of sight - I just started doing geocaching, and while I realized this long before I started, I didn't really have a feel for it until I tried it. Even out in the clear sky where the device could see four satellites, your best average fix is still +/-3 meters - regardless of the GPS unit you are using. For full disclosure, I was using a cheap Garmin Etrex bought used off of Craigslist, but from what research I have done, this limit app
          • Okay, why not LPS? I just made that up, it means Local Positioning System. It's like GPS, but instead of receiving satalite signals, it receives signals transmitted from 3 corners of the building that you are in. Obviously, each building has it's own database that can be transmitted while wondering around inside the building with the most useful part received just after entering.
            • Such systems do exist - they are mainly used in warehousing and other industrial buildings to track machinery, supplies and (sometimes) workers. But they tend to be very expensive technology (mainly because of the niche market they are in, but the technology figures in to it). Barcodes and simple cameras and/or laser scanners are way cheaper to develop and deploy...
      • In the case of the severely visually impaired / really blind, how do they keep the scanner aligned with the text, to prevent reading gibberish?

        I didn't read TFA, but isn't *some* sight required to perform alignment tasks?

      • Also, as the other poster mentions, braille devices are extremely expensive, require a lot of power and are bulky (both in size and weight). A braille display with 40 braille cells will cost an additional $2500.

        I could look it up, but this sounds like something worth discussing: why are braille devices so large and expensive? Aren't they basically a bunch of little solenoids that poke rods up from a surface? Unless I'm missing something, a 40 character (same as cell, right?) device would need 2x3x40=240

        • Have you ever played with a solenoid or a bare relay? If you had, you would know just how weak they are, and how size matters when it comes to these devices.

          To form the 2 x 3 cell pattern for a braille character, you have only a limited amount of space to put it in, because a single cell needs to fit in the area of a adult's fingertip, or about 1 cm^2. Furthermore, when the tips of the rods are pushed up, they need to stay up under the light pressure of the users fingers. It won't be great pressure, but it

    • This is a device to give the blind the ability to read written words. Audio hardware is cheap and abundant. This is more designed to give blind people the same level of capability in business than to give them situational awareness. Also this device gives the blind the ability to read publications that haven't been transcribed to Braille, like a newspaper or magazine. Most blind people aren't able to read newsprint as so little of it is available in Braille.

      Anyone who has not experience blindness really has
    • My mom's been blind since birth and she's a braille speedreader...and she prefers for things that have audio. She has had talking calculators (the one she had in the '80s was the same model that The Pet Shop Boys sampled in "Two Divided by Zero"); talking clocks; talking fluid level meters (hang it on the side of the cup and it tells you when it's full); tape machines for listening to books on tape from the Library for the Blind; a JAWS card, scanner and screenreading software for her PC, an iPod nano for b
  • by FleaPlus (6935) * on Thursday July 06, 2006 @01:02AM (#15665027) Journal
    I wonder what sort of camera resolution and processing power this requires. It would be great if in the near future something like this could be loaded onto an off-the-shelf cameraphone.

    As far as current cameraphones go, (picking semi-randomly...) a Treo 700p has a 312MHz XScale processor, and a PPC-6700 has a 416 MHz XScale. Both have 1.3 megapixel cameras.
    • As far as current cameraphones go, (picking semi-randomly...) a Treo 700p has a 312MHz XScale processor, and a PPC-6700 has a 416 MHz XScale. Both have 1.3 megapixel cameras.

      Those are smartphones, not camera phones. Don't expect the average camera phone to have anywhere near that much CPU power.
  • Awkward! (Score:5, Funny)

    by andrewman327 (635952) on Thursday July 06, 2006 @01:06AM (#15665041) Homepage Journal
    This has just made your commute to work that much more awkward when the blind gentleman next to you pulls out a Playboy.
    • Re:Awkward! (Score:3, Funny)

      by Anonymous Coward
      so thats who reads the articles
    • Re:Awkward! (Score:3, Funny)

      by Soko (17987)
      That may also indicate why he went blind in the first place...

      Soko
    • Beta testers describe the joys of reading receipts, CDs, food labels, bulletin boards, conference printouts, or of simply reading books with privacy, without another person's help.

      Ok, I hope I'm not the only one reminded of David Cross's impression of Stephen Hawking having phone sex.

      I wonder what the voice options are. Sign me up for Alice from the Brady Bunch.

    • Holy cow, somebody reads Playboy for the articles?!
  • by Solra Bizna (716281) on Thursday July 06, 2006 @01:09AM (#15665053) Homepage Journal

    I wasn't aware that one blind reader constituted a federation.

    </sarcasm>

    I seriously had to read that two or three times before it came out right.

    -:sigma.SB

  • by FleaPlus (6935) * on Thursday July 06, 2006 @01:10AM (#15665055) Journal
    It's probably be noted that the inventor/developer discussed in the article is Raymond Kurzweil [wikipedia.org], who's recently gotten a lot of press for his book about the technological singularity [wikipedia.org]. Here's a brief blurb from the Wikipedia article about Kurzweil's inventions:

    Kurzweil was the principal developer of the first omni-font optical character recognition system, the first print-to-speech reading machine for the blind, the first CCD flatbed scanner, the first text-to-speech synthesizer, the first electronic musical instrument capable of recreating the sound of a grand piano and other orchestral instruments, and the first commercially marketed large-vocabulary speech recognition system.
    • I went to a concert back in 1984 in college where everyone in the audience put on headphones and the performer (I can't remember his name) used a synthetic human head with microphones embedded in it to simulate acoustically the human head (and this was a Kurzweil invention IIRC).
       
        He placed the head inside a grand piano and played - the effect was striking (no pun intended). He tapped and scratched the head and it sounded like he was doing it to my head. What a memory!
    • And the K-NFB reader could count as a demonstration of what Kurzweil means when he talks about the Law of Accelerating Returns [wikipedia.org]. Looking at the beta tester article [nfb.org]:

      The 1975 reader cost $50,000 (over $150,000 in today's dollars) and was the size of a dishwasher. This new reader "is about a thousand times smaller than the original Kurzweil Reading Machine, the PDA in the portable Reader is two thousand times faster. In fact, the portable Reader can execute about 500 million instructions per second as compa

      • Oh, don't worry about it --

        If you look at the numbers, {1975, $150000}, {2006, $3500}, you can extrapolate that COST = -4725.8*YEAR + 9483455 (roughly speaking). By next year, they'll be paying people around $1200 just to take them off their hands...
        • Your linear regression is a mind-blowingly stupid way to interpret the decay in price. It's more likely to be an exponential decay. I calculate that COST = 1.358E+109 * EXP(-0.1212 * YEAR). By next year, they'll cost $3100, the year after that, $2750. They will hit the $1000 barrier some time in 2016.
          • Due to a grave travesty of justice I'm not allowed to both moderate and post in the same discussion (*shakes fist at CmdrTaco and /. rules*), but next time I'll try to remember to put a [HUMOR] tag at the bottom of my post for the androids and Vulcans in the audience.

            [HUMOR]
  • Maybe I watch too much TV... but I can sware I seen these before.
    • by Anonymous Coward
      Yes you have. I was in one of the news pieces that aired in Chicago where we presented the "original" technology called the iCare Reader [google.com] (Link to video) [cbs2chicago.com] This is a technology that was invented at Arizona State University a LONG time before Kurzwile ever dreamed about it. The research center called CUbiC [asu.edu] has been working on developing devices for the blind since 2003. I personally helped develop the software for this and I can say we did it for a LOT LOT Less than 2 million.

      Oh and not only that, we took 6 mon
      • by Anonymous Coward
        You talking about the portable reader- the one that was about the size and weight of a laptop? I saw it a couple of years ago. That isn't the same as software running on a handheld: putting pattern recognition on a Treo sized thing takes some development.

        it doesn't look like either of Kurzweil or the National Federation of the Blind are big corporations, or not even a small corporation. And since Kurzweil started working on readers in 1975, I think his dreams could have been big enough to see this coming. I
      • In a news article [thebostonchannel.com] interviewing Ray Kurzweil, it says that he started on the software for the K-NFB reader in 2002: "Kurzweil said the key to being a successful inventor is predicting what the technology will be years from now. That's what he did with this reader. He started developing the software four years ago." Given that he also has a decades long track record in building reading machines, and that other groups have worked on reading machines, the idea that ASU was the first or the only group to be wo
    • Maybe I watch too much TV... but I can sware I seen these before.
      I saw it last night on a rerun of Smallville where Lex Luther's father was using it to read a book.
      But the coolest movie machine is the one that types out Braille from the screen as seen in Sneakers (kinda old but still nice movie). PLUS that guy could crack encryption from his fingers IN HIS MIND.
  • by Anonymous Coward on Thursday July 06, 2006 @01:38AM (#15665134)
    The device "gives the user an initial 'situation report', describing what it can see.

    "You are in a maze of twisty passages, all alike."
  • by Qubit (100461) on Thursday July 06, 2006 @01:49AM (#15665169) Homepage Journal
    How hard would it be to come up with a FOSS system to do the same thing? It sounds like the software makes up a good deal of the cost of the device -- with the proper patrons (like the NFB), perhaps you could come up with some system that would just cost as much as the hardware. I mean, heck, the NFB sunk $2 million into the project, and the blind will still have to pay $3500 for the device.

    So you'd start with a good digital camera and a small handheld device. Then you need OCR -> text and text -> speech. What's the state of research or code that one could use in FOSS projects? It's been a year or so since I last checked, but AFAIK the current OCR software that's Free just doesn't stack up with that latest commercial products....
  • This is a cool toy, but I wonder how they'll sustain demand for a purely visual text-recognition device when so many of the written items we encounter everyday are going digital anyway. Already many restaurant menus and conference programmes and utility bills are accessible over the Web, local street signs via GPS, and poster/event info via listservs and email lists. Come 2010, what exactly are we going to need to read off slips of paper?
    • I actually don't think it would be too hard to put together a FOSS version of this. OCR has been around for a long time now, and there are FOSS OCR packages available. Also, text-to-speech is nothing new and there are FOSS options for that as well. The only reason a device like this was not made before, either is FOSS or comercial versions, was that small, powerful hardware needed for a hand-held solution was not affordable. The software has been around for awhile, but today's small, afordable digital c

  • by gareth.fletcher (855305) on Thursday July 06, 2006 @02:40AM (#15665290)
    A cell-phone for the blind was recently made available to visually impaired people in New Zealand, costing around $300USD. It seems like only a small step further to add some sort of camera/document scanner... This particular device will unquestionably help visually impaired students of particular sciences (e.g. advanced math), where there is almost no demand of Braille versions of textbooks (and even the regular textbooks!) and too many books to pay the conversion to Braille (here I believe it's at least $500?).
    • Actually, even Kurzweil's desktop version can't do usable COR on advanced math. Advanced math still needs to be manually transcribed by a Braille Transcriptionist into a form of Braille called Nemeth code. Then it can be read and used by a blind student who knows the advanced math code. I'm not sure why there is no demand in New Zealand for advanced math and other science textbooks in Braille other than perhaps not enough blind studetns there are interested but in the U.S., strategies for getting advanced
  • by s-twig (775100)
    Wait a minute, it doesn't matter.
  • Ok, I think this could be a very useful device. But... (as usual) I am annoyed.

    I hate pricing like "3495". Why not suggest 3500? Especially for a big ticket item such as this. More reasonably, how about 20% over cost? (given its a medical item). Pick a number, and go with it. 3495?

    I know -- those pricing tricks work... Oh well.

    Ratboy
  • I saw this demonstrated by Kurzweil a few weeks ago at the Singularity Summit conference at Stanford. He held up the gadget above his book, pushed a button, and it started talking! So simple in concept but so hard to do. The audience went crazy, it was so clear how this would be a world changing gadget for blind people.
  • The high price for a device that would increase the quality of life of the blind is to me a really good reason for governments to subsidise these for their citizens. I hear americas medical system is expensive and not well supported by government, but Australia has a pretty good record of supporting its citizens medically, this is another opportunity to offer better service than their american counterparts, hopefully america will catch up with their compassion.
  • Now I just want a handheld device that reads Japanese kanji characters out loud in English.
  • I mean, I'm sure it's great for the blind people. But how are all those dogs going to get jobs?

    Won't somebody please think of the dogs?
  • I (and no doubt thousands of other people) had similar ideas. My idea was actually a bit better; how about a phone that can scan menus and read them out loud? How about when you're on vacation and you don't speak the language. Wouldn't it be nice to scan a menu at a restaurant, to have the contents translated to your native language, so you know that you'll be ordering monkey brains? Use it as your mp3 player, and we might also add GPS functionality to it, with mapping software. Small effort to add a tiny D
  • by tcdk (173945)
    How does it handle ... images?

    "I see a blond babe, with huuuuuge...."
  • I remember reading back many moons ago that photo software (Photoshop for one I believe) recognized money and refused to work with it on the chance the user might be trying to counterfeit it (never mind the number of legal uses for doing such a thing). I sure hope that that algorithm made it into this gadget but instead to recognize both the currency and amount.
  • For some reason, I remember seeing Stevie Wonder with a device like this on a commercial about 15 years ago. He was using it to read fan mail. Was that device fake or is this story non-news?

    Anyone else remember this ad?

    • Hard to say what you saw... certainly similar technology was around 15 years ago, but in a much much larger package.

      Your mention of Stevie Wonder brings up what I think is an interesting little factoid: he's the link that got Kurzweil into music synthesis. He was an early user of Kurzweil's reading machines, and at some point complained to Kurzweil about the state of music synthesis technology, which inspired the whole Kurzweil line of music synthesizers.

      More details here: http://www.kurzweilai.net/bio [kurzweilai.net]

  • How long under we see custom designed ones that fit into an eye socket? :)
  • I recall seeing little $100-ish devices in the catalog you get on airplanes that claim to read a word from paper, translates it into another language, and speaks it for you in that language. Why is something that only does a fraction of that somehow interesting? Because it is intended for use by visually impaired people instead of tourists?

    *rolls eyes*

    • Remember, these devices are to be used by blind people, not by sighted people who can see where to place the reader.

      Given this constraint, you now have a bigger problem on the software side: How much of the "material" to be "read" is visible? Are there letters and words on the paper? What if the media the words are written on is non-planar (ie, wrinkled reciept, curved or bent menu, etc)? What if the media has contrast issues (lighting, shinyness of laminate, etc)? What if the media to be read is presented

  • The one in the video seems pretty old. Is it limited by processing power or something?
  • I certainly hope they aren't planning to take any pictures of copyrighted works...
  • This puts me in mind of another use for a nice, cheap ebook device. It could read books to the blind. Call me blind as well, I never thought of it before I read the article.

    At risk of going even further offtopic, what would be the chances of makezining a cheap ebook device from parts? I only ask because this article causes me to think that its a cultural travesty that no one makes an open-spec ebook for less than a hundred bucks. We need reading devices for so many things; textbooks, saving paper, saving ou
  • Perhaps now with a combined Dobelle implant (Google it, can't find any one official site) and this reader, they can see the lines of what they're viewing AND have it read to them. Getting closer and closer, just need to add color and we're 90% of the way there.

Your mode of life will be changed to EBCDIC.

Working...