BlindType — the Amazing Keyboard of the Future
kkleiner writes "BlindType has created a new touchscreen keyboard program of the same name that changes size, orientation, and position to match your wandering fingers as they type. BlindType also features some of the most impressive typing correction software I've ever seen. The result is a practical touchscreen interface that knows what you meant to type, even if you make mistakes. Lots of them. In fact, you can type without looking at the screen at all."
I've been typing without looking at the screen for my entire life!
"I'd rather be a lightning rod than a seismometer." -Ken Kesey
I really can't believe it took so long for them to make something like that, I figured that the Android/iPhone keyboard would look at finger movements on each key to try to see if you pressed in the center like you wanted that letter or far to the side like you didn't and adjust accordingly much like this. But I guess not.
Taxation is legalized theft, no more, no less.
I still find a touchscreen keyboard to be a bit wonkey...for me, it isn't an accuracy problem, but a tactile problem.
Living With a Nerd
If you can't type on a keyboard without looking at it, you're doing it wrong.
This is not the penguin you're looking for.
In fact, you can type without looking at the screen at all.
Gee, that's new! Typists from decades ago were able to do just that. It was called "training" and "expertise".
Seriously, though, I expect two distinct problems with this:
1) How well will it handle "non-US slopiness"? Sloppy typing in Spanish (etc.) is quite different from typical english-language slopiness.
2) IT'S NOT A MODEL M KEYBOARD!!! There, I said it. I don't care for "the keyboard of the future" if the "keyboard from the past" is still alive and well and functioning nicely. Actually, make that "the keyboard from the past and present". :-P
"Trust me - I know what I'm doing."
- Sledge Hammer
As standard spell check has already "corrected" my spelling into sending out requests for dates to my entire department, telling my boss I was flatulent and created numerous marital misunderstandings, I'm not sure I'm at all wanting to use this. Sometimes its best just to leave the typo so the reader can wonder what I meant, and not think I meant what the computer wondered.
Good thing no one was talking about typing on keyboards.
Call me when it can accurately decide when I meant when typing commands using vi or emacs.
I can type on swype without looking with ease.
So if you start to (touch)typing something it don't understand (foreing names or languages, i.e.) he relocates itself and "corrects" what you typed ? What could possibly go wrong?
Also, the blindness part... in normal keyboards you should see the monitor, you get some input both from the physical keys and of course, from what is being displayed in the monitor, and that helps writing without watching the keyboard. But in a tablet (as shown in the article) you only have the monitor, you see the keyboard because is basically right there, taking a big portion of the screen, and you still don't have tactile feedback. You still get most of the cons of an on-screen keyboard and get almost nothing over it. A bluetooth or plain wireless keyboard would be better.
As long as it can guess I want to type C-x C-c, I am fine with it.
As this program appears designed to interpret what you want to say based on actual, English-language words, it would be interesting to see how it would handle poor spellers.
Personally, I am probably somewhat of a spelling nazi, as I cannot stand how inept some persons (seemingly the younger generation--get off my lawn!) appears to be at spelling. If this is released, I would imagine that poor spellers would either (a) be forced to finally learn how to spell (again, get off my lawn!), or regrettably more likely (b) be frustrated with the program and write off it's inability to correct their own deficiency as a problem with the software, itself.
Now you can type actual messages on an iPhone [1] without wanting to pull out clumps of your hair!
[1] or any physical keyboard-free smartphone
Information theory is life. The rest is just the KL divergence.
This would work fine if the typist's fingers are accurate in the sense that they move the correct fingers in the right sequence. However, not all typos are of this variety-- using my habits as an example, sometimes I type out of seuqence (faster fingers tend to beat the weaker fingers to the punch), sometimes I dont put enough pressue on the keys/touchscreen for them to register, sometimes I get the finger right, but on teh wuong hand. (I'm also horrible with grammar, and tend to write in free verse more than actual prose... thank goodness for backspace.)
Of course, correcting these typos requires just a few more conditional checks and/or hash lookups in the algorithm, so it shouldn't impact performance much-- but it would probably impact the size of the dictionary.
"We are Microsoft. You shall be assimilated. Competition is futile."
I figured that the Android/iPhone keyboard would look at finger movements on each key to try to see if you pressed in the center like you wanted that letter or far to the side like you didn't and adjust accordingly much like this
The iPhone keyboard does actually take a lot of slop into account - if you type and shift to accidentally press other keys, the final word will correct based on keys that were almost where you hit, so that you don't have to be totally precise - the correction is pretty good on the iPhone and lets you type pretty fast as long as you trust the corrections.
BlindType is more impressive though, since it's all dynamic and doesn't rely on keys to be in a fixed position - yet seemingly works just as well. The only downside to BlindType for actual blind typing is, I'm not sure how many people touch-type well enough already to use it without a visual reference. But you can simply leave up the keyboard in that case.
"There is more worth loving than we have strength to love." - Brian Jay Stanley
If it works as well as depicted, then I hope it gets incorporated in the iOS. If it's not incorporated into the iOS then it would only be marginally useful. Queue the Android vs. iOS comments now... but I love my iPhone anyway. If it works, Apple ought to buy it from them and hire them.
When you look at things like Swype and BlindType, it really shows the power of having a device with a virtual keyboard. It lets you have data entry mechanisms that can be a lot easier than working very physically small keys.
It also shows the limitation of Apple's approach in that a user cannot replace the system keyboard (unless they jailbreak), although I think you'd have to root Android to replace the keyboard system wide which is similar in nature. Third party apps could individually include the keyboard but then of course you might get an app you really like to type in that does not support the keyboard...
I would say that users would not use different keyboards across apps but the nice thing about BlindType is that in a way it's backward compatible with a traditional keyboard that people are used to - so in some applications they'd simply get more accurate typing without having to adjust how they typed (unlike Swype).
"There is more worth loving than we have strength to love." - Brian Jay Stanley
Wow, I can't imagine that those clacking and "phoo-OOM" sounds could ever become irritating. They're just so awesome!
Hey, somebody has to be the first to do it. Like many profitable ideas, once presented it's a "duh", but someone had to have - and act on - that "duh" moment first.
I figured that the Android/iPhone keyboard would look at finger movements on each key to try to see if you pressed in the center like you wanted that letter or far to the side like you didn't and adjust accordingly much like this.
The iPhone keyboard's spelling correction takes finger drift into account. If you type an unrecognized word, but one/some keys are one-off from a recognized word, it adjusts accordingly. It deals with lack of tactile feedback by figuring out what word you would have typed if your hand hadn't drifted.
This new keyboard is different. Instead of relying on pattern-matching words with one-off keys, it tracks where your hands drift to (perhaps making use of that algorithm to some degree) and moves the keyboard to match where your fingers drifted to.
Distinct difference.
Can we get a "-1 Wrong" moderation option?
Every time I see tools like this I wonder if QWERTY should still be relevant. "We're using a QWERTY keyboard, because everyone knows how to use a QWERTY keyboard." IIRC QWERTY was originally designed to keep typebars in manual typewriters from jamming together, and its kept on keeping on through Selectrics to PCs to today. It's all so roman-chariots-and-railroad-gauges (why abandon a good metaphor even if its not really true?) Are there finger-based text-inputting tools for touchscreens and/or smartphones that are a snap to use and lightning fast, but are sitting abandoned in the technology attic simply because they're not based on QWERTY?
.
Prisencolinensinainciusol. Ol Rait!
couldn't resist - no karma for me :(
The only problem that I see here is that my ex-girlfriend is going to be able to understand my drunken texts I send her now.
Great, now monkeys can type and text me cause the way they talk is killing the phone call.
Steve Jobs' primary directive, (operating on the subconscious layer. . , I hope), is to dumb down humans so that they degrade into malleable monied children who don't think about any reality other than the bloopy, candy-coated dream world presented to them by Apple.
Part of that master plan was to surgically remove user interactivity from the internet, so that people can only fingerpaint, play games and communicate in twittery bursts of retard-speak.
But now two brothers from Greece might just nix that plan with their little tool which allows people to still communicate on the internet via the almighty written word. Awesome!
The Dark Side can try to numb Intelligence, try to program Minds, but there will always be a few smart people out there fucking with the system to allow the spirit to shine through. Put that on a T-Shirt and wear it.
"Down with the Pod People!"
-FL
Let's think of how they might have designed the algorithm for this. In the videos, it looks like it is treating one word at a time, so let's consider that scenario here as well. I would define the problem as assigning to every possible word the probability that it is the word the user intended. I would use Bayes' theorem to achieve this.
First, assume a prior probability distribution over all words. Words not in our dictionary, and words of the wrong length, we give probability zero. The remaining words can be assigned equal probability or, better, a probability proportional to their frequency in the language. If you want to be fancy, you could have more sophisticated models that knows which words are likely to come after others and such things.
Second, for each candidate word, what is the probability that the user would tap the screen as they just did? A model for this could be that the location of each tap is drawn from a Gaussian probability distribution centred at the intended letter with a known standard deviation and that each tap's deviation from its target is independent of the others'.
Finally, Bayes' theorem states that the posterior probability (the one we want to calculate) of each word is the word's prior probability (from step one) times its likelihood (the probability of step two).
To implement the arbitrary position, orientation and size of the keyboard, we redefine the problem from finding the probability of each candidate word to finding the probability of each tuple (intended word, keyboard position, keyboard orientation, keyboard size). Make it simple; have each element of this tuple to be independent of the other and use flat distributions for all keyboard parameters. To choose the most likely word, you could either pick the word of the most likely tuple or, more correctly, for each candidate word, integrate over all possible keyboard parameters (weighted with their prior probabilities) to get the probability of that word. Likewise, you could introduce the standard deviation of the taps as another element of the tuple, with its own prior distribution.
I suspect this method is a bit to heavy on computation cost and power consumption, so if you cannot find a clever way to do it fast, you might have to cut corners in the rigor (or do something completely different).
(Can I come work for them now?) :-)
Swedish plasma phys. PhD student; MSc EE; knows maths, programming, electronics; finance interest; seeks opportunities
When I was a kid I had a magic act. Among my (admittedly mostly mechanical effects) was something called "Carson's Zombie Ball." This ball (about the size of a regulation softball but metallic) sat on a pedestal. By draping a magician's silk over it I could make it float around the room as if by magic. It really astonished people and got a lot of applause. I can tell you - no magic was involved but it sure looked astounding to the folks who didn't know how it worked. So - as I said - this keyboard for which there doesn't seem to be a credible demo for (aside from videos and controlled demos) seems creepily like my Carson's zombie ball. Seems like someone has it remotely wired - probably looking for funding. I'll believe it when I can personally try it in the absense of the owners.
I mean will it know enough to use grammar and figure out that you should type "Their" versus "There?" Would it fix bad punctuation?
Will this cause more "fat finger" mistakes that it will resolve? For example, will the keyboard software be so smart that when you type in an order to sell Proctor and Gamble it'll replace that "M" with a "B?"
Your method is simply too good and precisely defined to result in a patent filing.
A US patent filing should always be broad and not do more than restate the problem and stating that it is somehow being solved by a black box, so that your company has a real chance to stop any competitor from coming up with a less optimal solution that doesn't violate the patent.
Hey don't blame me, IANAB
Abcd1234 wrote:
I'm calling bullshit.
There's no way you use both Vi *and* Emacs.
One word: viper. See http://www.gnu.org/software/emacs/manual/html_mono/viper.html#Top for details.
Also known as the C++ of editors. ie, making an octopus by nailing more legs to a dog. ;)
I write 4 different languages and the nifty spell correction thingies always need to be told which language I am currently writing in. And you also can forget about messages written in multiple languages.
Hence for me a keyboard is good when I can accurately type what I need.
I hadn't the slightest objection to his spending his time planning massacres for the bourgeoisie... (P.G. Wodehouse)
Trying using that stuff to control an ssh session. Total nightmare.
Right, but that's because the dictionary is not optimized for shell commands.
I'm not sure if any of the current SSH apps take advantage of it, but with 3.2 Apple opened up a lot more control of corrections and keyboards - I think at this point a decent SSH app could be built.
"There is more worth loving than we have strength to love." - Brian Jay Stanley
Really?
So how would you handle regexs?
I'd have a reg-ex specific keyboard (with the common regex characters directly above the letters), that understood common command points where you might use a regex (like after grep "s/...") and disabled correction altogether so it wouldn't get in the way.
There are a lot of ways to make typing in regexes better, you could even do live file matching in a window for example.
Basically an SSH client more tied to an understanding of common shell commands could be really powerful. Or at least less painful.
"There is more worth loving than we have strength to love." - Brian Jay Stanley
I was taught to touch type just for that reason, so I can watch the screen while I type.
So, what, now I can watch porn while I masterba, eer, I mean, type?
cool.
Be seeing you...
Still seems like a physical keyboard wins anytime the correction gets turned off.
For regex? You have to be joking. A virtual keyboard can make that so much easier to type than repeated use of tiny shift/function keys...
"There is more worth loving than we have strength to love." - Brian Jay Stanley
I find it hilariously disturbing that this technology is being applied to a QWERTY keyboard layout. It is symbolic to all that is human and is just sad.
-ubuntu others as you would have others ubuntu you.
how would this allow you to type a nonsense password? Also, I noticed a lack of special keys and numbers but hey, guess it's still in development.
...keys type you!