Linux Handwriting Recognition 78
Dark Paladin writes "Cnn.com is reporting that Communication Intelligence Corp. and Middlesoft is working on Linux based handwriting software that will work in handhelds, Internet appliances, and have GTK and QT hooks. Now we can move from carpal-tunnel to writers cramp. " Now I'm curious, what matters more to people, handwriting or voice recognition?
Okay, I'll bite. (Score:3)
But, all-in-all, this is pretty cool. Maybe we'll finally see Palm-style Open Souce handhelds.
And, if you're wondering, an open souce handheld would be great. Why settle for what Palm (or Microsoft) thinks is good for you when you can write your own look and feel?! Just think, you could probably add compatibility for both Palm apps and Wince apps. Now all we need is some good touchscreen support, and we're set! (Or is there already touchscreen support I don't know about?)
so what? (Score:1)
Writing > Voice recognition (Score:3)
The other reason why handwriting is better than voice recognition, despite the possible and immediate use in handhelds, is that we seem to be fairly saturated with voice technologies, but nobody has created a decent OCR package. (Unless, of course, SANE has done it and I haven't noticed.) Getting--not *just OCR*--but handwritintg recognition, is something to be pushed. Hearing about the US post office using stuff for sorting is one thing; it's totally another to have advanced stuff on your own machine.
voice (Score:3)
Uhhh. (Score:1)
I type 120 wpm, I write like 5. Just my thoughts on Christmas morning
*3rd post*
Re:so what? (Score:2)
-- Give him Head? Be a Beacon?
Or Maybe! (Score:2)
Anyway, I think handwriting recognition is definitely appropriate for handheld computer applications, while Voice recognition will evolve into regular applications.
Just out of curiosity, How long will it be before everyone forgets how to write?
-- Give him Head? Be a Beacon?
What linux really needs (Score:1)
Which is most important? (Score:1)
Well, to me it would be which is the most efficient. I know I can certainly type faster than I can write, so I would choose typing over handwriting.
Voice recognition would me much more usefull in situations where the hands are needed to control delicate things that only the trained motor skills of a human could do the job (fighter pilot, surgeon) to control things such as providing the right tool or weapons control.
So I would rank the three options in this order:
1. Voice
2. Typing
3. Handwriting
However I have left one option out, thought control (You know what I mean). The reason I left this out is because I think it is such a long way of. Sure we can train rats to think about pulling levers, but it is a long way before we can create machines that could understand the brain patters. It must be even more complex than voice recognition...
Don't waste time on either (Score:1)
Re:Writing > Voice recognition (Score:1)
A couple of free [python.net] or semi-free [umd.edu] efforts have been started, but they seem to have lost momentum. I'm still building up the gumption to start a project, but if anyone else is working on it, please drop me a line...
Hmm... time to check on the turkey.
hr... (Score:1)
There are a fair number of projects out there. Heck, I even designed a HR system and implemented in VB in 1/2 an hour (after 3 weeks of design work). That was when I thought I had money to buy a uCsimm with and build my own handheld. Since the handheld didn't happen, I left the prototype where it stands, but if anyone wants the system, they are welcome to it. (email me, and I will describe my method and send you the code.)... Anyhow, I think linux is ideal in many way for handhelds, because it can (and has) been implemented on mmuless systems, it's efficient (which is good for small microprocessors, and you can still get lots of full fledged software for it. Keep up the good work everyone.
handwriting (Score:1)
Handwriting matters as a handheld, same with voice (Score:1)
For most of the present users of unix, the machines are large and in charge, and have keyboards. So voice is a larger market for TODAY. (handwriting -> keyboard -> voice in order of ease)
And, as voice can exist on handhelds (when handhelds become powerful enough), people will use the voice interface over writing. (because writing is more work than talking)
Voice on handhelds exists as demo-software. The Newton 2000 had voice software from Dragon Systems. (20 or so words)
Re:Uhhh. (Score:3)
There are three reasons for handwriting recognition I can see off the top of my head:
Re:Okay, I'll bite. (Score:1)
Hands or Mouth (Score:2)
Aditionally:
1) A *noise resistant* voice dictation technology would apply to
2) It is readily apparent that in the desktop situation (ie non-portable) a voice technology is FAR *FAR* faster than a handwriting system. As voice improves it will
So from my standpoint it seems that Voice Dictation addresses a true "holy grail" of computing accessibility and ease, whereas handwriting recognition fufills a few important niche markets. This would be a tough choice to make except that voice recognition also performs suitably well in 90% of the aforementioned niches.
As much as I have enjoyed handwriting recognition (I'm a happy newton owner), I would trade it in a second for a really slick and accurate voice interface.
-nullity-
Re:Uhhh. (Score:1)
2. Pens are easier to use and more less restricted in character composition than keyboards. (Think of Japanese, Chinese, etc. with a keyboard. A nightmare!)
IMHO, the biggest current limitation to computers is their archaic interfaces: monitors, keyboards & mice.
Besides, while most people can type faster than they write, they can *speak* even quicker. Choose the interface that is best for the application.
(Think medical charts -- replace that clipboard on the bed with a pen-based computer [big business now] and a vorec chip for doctor notes.)
Re:Hands or Mouth (Score:1)
I can already imagine it.
hash include lessthan stdio dot h greaterthan feed feed int main open void close feed curlyopen feed indent-one printf open quotes h e l l o comma space w o r l d backslash n quotes close semicolon feed back-one curlyclose feed
Though I don't really think that editors would try to naively replace the keyboard with a voice recognition interface :-)
one hand (Score:2)
- handwriting is a one-handed activity
freeing your other hand to hold a handheld, the telephone, etc.For a desktop, I actually like having everthing in parallel. Touchscreen, mouse, trackball, stylus, trackpoint nubbin, and glidepad. I've never had them all at once, but I've had many of the combinations and they're all useful at times throughout the day. If my hands are on the keyboard, I don't want to take them off, but if I'm standing, talking to someone, on the phone, or my workspace is cluttered, I like to reach for more convenient or demonstrative devices.
Re:Writing > Voice recognition (Score:1)
-----
Re:Writing > Voice recognition (Score:3)
Sometimes you don't want to be blurting everything out for the world to hear.
Typing vs writing vs speaking. (Score:2)
Antoher thing about speaking is that, when the user wants a written report or something about that, she / he would generally produce better material writing than speaking (which gives no time to think about things
Handwriting recognition should be more useful, but, as someone else said here, keyboard recognition is probably much faster (and uses fewer resources - plus the ability to backspace
// Simon Kågström. Enters his text keyboard-wise.
Handwriting Software Will Not Help Me (Score:1)
Merry Christmas and Thanks to All for an informative/entertaining year.
JM
Don't knock handwriting recognition (Score:1)
Police Reports/Tickets
Hospital/Doctor's Charts
Signature Recognition (With a pressure-sensative device a signature could be used as a unique encyption key. It's basically a manual "key" now to banks, UPS, etc.)
There are numerous applications that lend themselves to handwriting much better than voice (noisy environments; limited but various response questionnaires, etc.)
I think the best items will combine both (voice notes w/recognition).
Several WinCE PDAs have the ability to record voice notes (w/o recognition).
Linux Handwritting recog. (Score:1)
just a thought
Thought! (Score:1)
After years of typing my handwriting has devolved so much I can't see handwriting recognition being any benefit to me.
Lets skip both and move forward with research on thought recognition. You wear a headband, hat, wrist strap, ring or something and you control your computer (or at least a pointer) with thought commands.
The goal is to have an imput device that you could use in public without looking or sounding like an idiot.
Handwriting Recognition More Useful (Score:1)
For a specialized wearable computer or robot, one that executes a limited set of commands, voice recognition is more beneficial as it does not require physical contact with the device. Both have their places, but for using Linux on a PDA, handwriting is more useful.
--
Gregory J. Barlow
fight bloat. use blackbox [themes.org].
anyone know how jot compares to graphiti? (Score:1)
I've never used 'true' handwriting recognition, but having used a palm pilot (not a palm, i had an old usr palm pilot pro), I really liked graphiti.
I can write in graphitti much faster than I can in any legible script and it seems to me that in the present state of processors and power drain that it is much better to train users to learn the computer's script than it is to train computers to learn the user's script.
Other than that, I think this is good. Now if eventually I can get something like jot to work with my touchpad in X, that would be great.
Why we need handwriting recognition (Score:1)
You are missing the point. In many situations, you don't have a keyboard! This is particularly true with PDA's, but any compact, hand held device will have the same need. Many embedded devices would be easier to use with some sort of handwriting recognition.
If you are sitting in front of a computer, there is no doubt that the keyboard is a better input device, at least for most people, but computers are quickly growing out of the confined model of mouse, keyboard, CRT desktops that we have grown to know and love.
Think of of how we could use StarTrek style data pads.
Re:Or Maybe! (Score:1)
That's a bad idea, I can hardly read my own hand writing. How about it transcribes to my wife hand writing instead?
Re:voice (Score:1)
Chinese (Score:4)
For English-speakers, voice recognition and OCR might seem like neat gimmicks, but they're going to be *vital* to bring information technology into places like rural China, where people are lucky to be literate in their own language, nevermind learning a foreign phonetic alphabet and awkward keyboard input methods.
Check out China's up-and-coming domestic computer maker Legend at http://www.legend-holdings.co m/eng/press_centre6.html [legend-holdings.com]... Their basic model includes a keyboard, but more centrally - a writing tablet.
I'm glad to see Linux-based voice and writing recognition efforts. Imagine this - Linux bringing the Internet to 1+ billion more people...
I'll second that. (But paper computers?) (Score:3)
The only thing a handwriting input device buys me is the possibility of a smaller machine. Voice recognition, on the other hand, gives me computer input in contexts where my hands are busy - such as while driving. It also allows for an even smaller machine - since the input interface can be a pinhole rather than a surface at least the size of a Postit note. And I can usually speak faster than I can write.
But while voice recognition may strike me as more enabling than handwriting recognition, it's not an either-or issue. They each add a unique capability. Pick either one, and I'm sure there will be a number of applications where it's a better fit than any other input mode.
Handwriting recognition seems like the ideal input mode, for instance, for paper computers. Imagine a pad of Postits, each running PalmOS. B-)
Also: If they ever come up with a handwriting recognition program that can read my writing better than I can, I've got a lot of old notes around here that I wish I could read...
OCR matters to me. (Score:2)
Handwriting recognition:
Great, so far as it helps with OCR on handwritten pages. Not so great, as the primary interface to a handheld computer. As much as I prefer the Palm Pilot as a PDA, I'd much rather have a tiny, two-finger typeable keyboard than use graffiti (or the onscreen keyboard alternative). Graffiti just doesn't work as quickly for me and feels more awkward. And recognizing "natural" handwriting would be even worse. My handwriting goes from left to right; it doesn't stay within the sensory area on a PDA. The "unnatural" graffiti writing actually helps because it eliminates that instinct to move your hand while writing.
Voice recognition:
Sure, would have been great to dictate homework when I was in the 6th grade and didn't know how to type. But today it would have to get punctuation, spelling of homonyms, etc. exactly the way I wanted it to be marginally better than typing long paragraphs. And as for voice commands? Forget it. It's been like three years since I've had my computer situated out of hearing range of any other computer around, and I don't want to work within some wacky scheme to decide which computer is supposed to be listening to me.
OCR:
Now, this would be useful. I'd love to live a paperless life, but unfortunately I live within a society that doesn't see things my way. It would be nice for my "filing cabinet" to be completely electronic, but today that's not really a good option unless I save
Is it GPL? (Score:1)
Re:Linux Handwritting recog. (Score:1)
There has been some rumours that apple might be using some of the Newton technology with a PalmOS comuputer, but I would take this with a grain of salt as this has been predicted for over a year, with no solid info. If this were true, though, then I think that there would be no chance that Apple would release the tech.
Programming languages. (Score:2)
Perhaps natural language may not be efficient for computer control. But that's a separate issue from voice recognition input.
We've been programming and controlling computers using UNnatural, contrived languages for a long time - and directing other machines, domestic animals, and human work teams ditto since long before comptuers - or even recorded history. Think about driving a horse - or a car, military command-and-control, coordinating a crew of sailors, or calling a football play.
Voice recognition technology give us a way to capture, lex, and parse vocal gestures. Whether we try to decode the vocal gestures as a natural or a contrived language is an issue that doesn't arise until the parser level.
Open source handwriting recognition and I18N (Score:2)
Adaptable interfaces (Score:1)
Handwriting, voice recognition, sign language recognition, face recognition, special keyboards all good.
Large & small screens, speech output, Braille, 3d all good.
Different devices, different users, different situations, different tasks call for software that can adapt it's interface.
There is no easy way for a programmer to take advantage of these different scenarios now, or easily write software that adapts to new environments.
This sort of thing could be done at the component level in a toolkit. It would be a book the mobile and disabled users. You could use the same software, and programmers could more easily write their software for several audiences.
IBM can work on Voice Recognition... (Score:1)
Handwriting recognition and the Chinese community (Score:2)
Neither (Score:1)
The answer I think is to sacrifice some small part of our primary visual cortex (the bit of the brain your little finger is over when you're sitting back with your hands behind your head) to interfacing with the computer. By surgically implanting an electrode chip with a radio transmitted that had just enough power to transmit through bone, and then letting it heal over so there was no risk of infection (which would happen if you had wires hanging out of your skull).
These electrodes would then be used to decode the nerve cell activity in a small patch of brain tissue. By visualising characters in that part of your visual field, you could communicate with the computer [the jury's still out on whether 'visual imagery' reaches all the way down to the primary visual cortex, but I hope it does].
The end result might be that we could have a unix command-line interface in a small strip in the lower part of our visual field, where we just visualise command-words. Of course, English is a pretty inefficient language for communicating in this way, so performance would be improved by operating with a specifically optimised alphabet (even Chinese would be much more efficient for this, you'd think).
Both suck separately.. together, it's unbeatable (Score:3)
On the other hand, if you combine speech recognition with a system of gestures and written jottings for doing corrections on the fly and for "nudging" the interpretive engine in one direction or another, you can probably increase the speed at which fully-corrected speech or text gets input by several orders of magnitude. Such a system gets rid of the need for stopping dictation/writing to go into an "edit" mode.
Current products show a strange myopia--designs that do handwriting or speech recognition as though users are unable to do both at once, partly an outgrowth of these technologies' origins as accessibility tools. That is, while it's terrific that someone with no mobility can use ViaVoice to fully operate any software other than perhaps a raster imaging package, this approach has made these technologies more tedious and linear than they need to be.
Indeed, such a thing may not even need handwriting recognition to get most of the benefit. I'd love to see what could be done to speech dictation performance with a gesture interface implemented on a pen tablet.
IBM already has ported ViaVoice... (Score:1)
Even though it is still in beta, it is already being used as a foundation for things like GVoice. [ogi.edu]
Neither, except in special situations (Score:1)
Unlike many others, I can also type faster than I can talk. Frankly, I think speech input should never be an universal option as there are many people who have some sort of speech problem, foreign accent, or just plain mangle their language (just listen to any teenager :-).
Re:Which is most important? (Score:1)
intrusive in public contexts (like a business
meeting.) than typing into a computer. For years
I carried around a Newton for notetaking and it
was great for the quick notes and sketches that
I used to use a notepad for. Now I use a pilot
in similar situations.
If you use a laptop in a meeting, for some reason
you seem like you are ignoring the other atendees.
great (Score:2)
I can see a large market for hand-writing recognition among certain segments of the online population who use their computers for certain activities that use a certain other hand....
Re:More important... (Score:1)
I wish explained your position that "a lot of people find handwriting recognition crucial". From what I took from reading the other articles it seemed that more people were dismisssing it rather than encoraging it. I also couldn't figure out if your were attributing your "more like graffitti than the newton" comment to the many people who strongly desire handwriting recognition, or was that more of your own opinion?
The Newton's data input system is one of the biggest things that I miss when using my pilot. Although when I tried "Jot" I realized that a Newton like data input system doesn't work with screen real estate as small as a Pilot, but if I wanted something as big as a Newton, I'd still be using it.
As I said in another article in this thread, there are situations like meetings, that jotting down notes seems less intrusive to others than typing. Voice recognition would be even worse. And for anyone who is saying that they can type much quicker than they can write, I'd suggest they try a Psion PDA for a bit. (Athough smaller than a Newton, even Psions are looking a bit hefty these days.) Once you get into the size of a PDA, there is no data input system that convenient. Except maybe the desktop computer that you are synchronizing your data with.
So, could you point me to all the people who were clammeroring for "graffitti-style" data input?
Re:Okay, I'll bite. (Score:1)
Oh, you were talking about Linus' OS..
Been There, Done That. (Score:1)
Come on folks!
Its called the Newton Message Pad 2100.
I don't know what Steve Jobs did with the technology, but these little honeys really did the job.
I don't see that handwriting recognition is going to help Linux in any way, most things Unixy are designed for the keyboard with a occasional mousing around. To really make efficent use of the technology you need a shell or operating system design to support it.
For references check out anything related to the Newton or for a good view of the damage Redmond has done to pen computing check out the book Start Up : A Silicon Valley Adventure by Jerry Kaplan.
Handwriting, maybe. (Score:2)
As for voice recognition, perhaps there are some limited uses, but I don't see this as being useful for me or most of the people I know either. I don't want to be talking at my computer - this would require either wanting everybody around to hear what I'm saying or being alone. I don't think it'd speed me up much either. I can type around 100-120 wpm, I doubt I can talk much more than 10% faster than this.
Re:Or Maybe! (Score:1)
That has already happened were I live. Instead of writing, people here just mope around clattering their teeth like beavers for communication.
Dilbert: I have become one with my computer. It is a feeling of ecstacy... the blend of logic and emotion. I have reached...
WinCE Compatability (Score:1)
What makes you think that writing WinCE API is going to be any easier than writing the Win32 API, a project which WINE is working at for some years now.
I am positive that there is more then one aspect of the WinCE OS that is being done without documentation (I can tell this by simply looking at the things done, compared with what the documentation claims is possible).
Shachar
Re:Don't waste time on either (Score:1)
Why would I want handwriting? (Score:1)
It doesn't make sense to come up with backwards technology. Give us something that is more efficient than a keyboard and we're talking. Voice input? I think I want something that doesn't make me look like a lunatic, it's bad enough to see those idiots in town just standing there and babbling into their hands-free, invisible mobile phones.
TA
HWR, a few reasons why (Score:1)
* I think most people have low expectations for handwritting recognition because the most they are familiar with is Graffiti. Graffiti is bunk. It's a highly circumscribed gesture system. Special characters, one at a time, not 'in place' on the screen, no visible ink. There's some acceptable reasons that Palm chose it when they did, but real handwriting recognition is something else entirely. Expect it to read your writting with 99.9% ease and accuracy, and within a couple years we'll be there.
* HWR is not for desktops, it's for portable devices. Keyboards are easier for most everyone when they are practical. That said, there's at least one place where good HWR really excels, and that's with form based info. Sure you can tab between items with a keyboard easily enough, but there's nothing more intuitive than writing information _where it goes_. It's fluid.
* Voice recognition has its place, but it's also a drag. I remember reading an interview with Jeff Hawkins (Palm/Handsping) where he describes trying out handheld voice recognition by talking to a dummy handheld for a day. Drove him crazy. I think that goes for most people. Try it for 15 minutes yourself, especially with other people around. Now compare that to writing with a stylus. Our technologies should be graceful, not vulgar (I say). That's how I'd characterize the two. (To elaborate: yes, there is nothing more natural than speech. But talking is not a data input device, and if a friend ever spoke to me that way I'd probably hit them.)
The CIC news is great. Handhelds are probably _behind_ where you'd think they would be by now. I'm sure some Linux competition will get things moving again...
Re:Hands or Mouth (Score:1)
hello.c:4:warning: main() declared as returning type 'int' but does not return expected type
Re:Or Maybe! (Score:2)
Very good question...
Palm and the Grafitti language are giving us a good start on that very possibility. Eventually, there will be further divisions between those who can write, those who only write grafitti, and those who can not write at all.
In Neal Stephenson's book "Diamond Age", he makes reference to "mediaglyphs." I assume them to be iconic references for common items or concepts, sort of like the international symbols of today. While this can be beneficial, it sure represents a great opportunity for further "dumbing down."
My Newton MessagePad taught to write better cursive (BTW, with practice I was getting 98% accuracy), my Palm is teaching me to write Grafitti. (And don't forget, Grafitti was available as a third-party product for my Newton years ago, so I could use either then.)
How long before everyone forgets how to write? Just keep an eye on the handwritten work that teachers receive in school. When it starts turning up interspersed with Grafitti, we'll know we're on the way.
Hopefully, the technology can catch up quickly enough to give us acceptable cursive recognition (sorry to be so Anglo-centric). I would love to see Apple GPL the code for their Newton recognition stuff. It's not perfect, but with the increase in hand-held processor capability and speed in the last few years and a bunch of talented Open Source programmers working on it, it could be whipped in shape in no time.
Are you listening, Apple? Hey Steve, maybe you can write it off as a tax break...
Russ
handwriting can't exceed typing speed? (Score:1)
They listened to the author, wrote what they said in a phonetic shorthand in real-time, then went back to their desks and re-translated their shorthand to typed output.
The only reason they used that system was because they couldn't type as fast as the person talked, but they could write (shorthand) as fast as the person talked...
Manifest Destiny (Score:1)
Re:Chinese (Score:1)
Korean (Score:1)
Actually, Korean isn't that bad since it does have an alphabet which maps fairly well onto an English keyboard (upper and lower case letters; 14 consonants + 21 vowels = 35 total letters which is less than 2*26 = 52). It only becomes a problem with hanja (Chinese characters), but they aren't used that much in modern Korean. For Chinese and Japanese you're right, though.
Cheers,
Philip