OCR!

DotComCTO

秀才
Great release, Mike. I just posted a 5 star review up on iTunes. This is a great release, and it couldn't have come at a better time. I got the update just before heading into Chinese class tonight (we're on NPCR Vol 3). The OCR was a lifesaver as there are always a few characters I seem to forget. I used it in class and showed my professor as well as the other students; everyone was blown away.

I will say that the OCR is a tad jittery and it took me a little bit to get the hang of it; however, now that I've figured it out, it works just great.

Thanks again!

--DotComCTO
 

anchan42

探花
YoshiCookie said:
These are quite ingenious little ideas, but it seems like much time, effort, and money. Just buy an unlocked iPhone if you don't want AT&T! :p

(I do respect and salute clever guys like you... I could never cone up with these kind of ideas)

And still no OCR to speak of!

The differences between iPhone and iPod touch here is about 500 dollars. That is a large some of money around here. Are unlocked iPhones available in the US?
I got an iPhone but thinking about reverting back to treo and get an iPod touch instead. It would be great if we could find a way to make it OCR work on iPod touch without too much hardware hassle. The mods I have seen so far including the one I put a link here do not look very promising.

I still could not find the OCR module in in-app purchase. Not sure why but I will try agian this evening when I am home.
 

mikelove

皇帝
Staff member
Harm said:
So glad I lost my old Treo in Hangzhou and was able to buy an IPhone in the Apple Store in Shanghai. Now I am back in Amsterdam and I can fully enjoy the new IPhone version of PlecoDict. In fact I like it so much that I bought a new license for the IPad I bought last week as well. I really do not mind to support a company that during the last decade or so has helped me with my Chinese to such a great extend.
I have also been looking forward for the OCR for some weeks now and after having tried it for a short while I already believe it is AWESOME!!!
After OCR, I do not know what is left to be desired. But I am sure you will come up with something new in the next years.

Thank you! We really appreciate the extra business.

Entropy said:
Oh, look, the instruction manual on iPhone is hidden in the "reader' tab. It should probably appear in lots of places, including at the top of the settings.

Only once we rewrite it to break it up / link it to area-specific information better; right now I'm already embarrassed about the fact that we've got the web browser linked from 3 different places and I'm not particularly inclined to repeat that bit of awkward design for help.

Entropy said:
And, do you have a new icon?

Yes, the drop shadow was askew and the silver foreground set up a nicer contrast / made the whole thing look a bit classier.

WeiPhotoArts said:
Thanks for getting OCR up & running. Thought I had to wait until eom Nov. Then I clicked the Appl Update bottom. Worked well on tea box, w/ slight script Chinese. Didn't do so well on a soy sauce bottle, but it may be my shaky hands & the glare of lighting (I'm a photographer.)

Great! We were a little worried about that too, particularly given that Apple's reviewers often go on hiatus for a week around Thanksgiving. Bottle labels can be dicey both for lighting and curvature-related reasons so I'm not surprised that gave you a little trouble.

character said:
Now's the time for you and others to post YouTube videos demonstrating it and drumming up interest in Apple/gadget blogs.

Yes, once we've let a day or two go by and established that there really aren't any showstopper bugs / that people really do find this usable in its current slightly-jitter-prone form.

dustpuppy said:
Thanks so much for this release ! It works just as expected, so impressive. This is a very cool app.

Thank you!

DotComCTO said:
Great release, Mike. I just posted a 5 star review up on iTunes. This is a great release, and it couldn't have come at a better time. I got the update just before heading into Chinese class tonight (we're on NPCR Vol 3). The OCR was a lifesaver as there are always a few characters I seem to forget. I used it in class and showed my professor as well as the other students; everyone was blown away.

I will say that the OCR is a tad jittery and it took me a little bit to get the hang of it; however, now that I've figured it out, it works just great.

Thank you very much for that - I'm glad it helped.

Would it help on the jitter front if we made characters less prone to changing when you're not actually moving the camera around? That's the kind of jitter most of our efforts are currently focused on.

anchan42 said:
I still could not find the OCR module in in-app purchase. Not sure why but I will try agian this evening when I am home.

If it's not supported on your device it'll be listed at the very bottom of Add-ons.

Entropy said:
I can't download the OCR module on iPad. Is that the desired result?

For the moment yes - we aren't confident enough in the still image capture mode to sell it to iPad users who wouldn't be able to access OCR in any other mode, and we didn't want to delay the release of OCR for the extra day or two it would have taken to test / fix the UI for still image capture on iPad when we weren't ready to officially sell it on them yet.
 

djbass

Member
I installed the OCR today but have not been able to reliably test it because for some reason the focus button has no effect on my 3GS, since the letters are too blurry it can't successfully identify characters.
 

mikelove

皇帝
Staff member
djbass said:
I installed the OCR today but have not been able to reliably test it because for some reason the focus button has no effect on my 3GS, since the letters are too blurry it can't successfully identify characters.

That's odd... does the focus work correctly in the built-in camera app? It could be that there's something awry mechanically with the camera itself... if focus works OK in the built-in camera, does it help in Pleco at all if you shake your iPhone? For some reason that seems to convince the phone it needs to re-focus, at least on our test device.
 

Entropy

榜眼
mike love said:
Would it help on the jitter front if we made characters less prone to changing when you're not actually moving the camera around? That's the kind of jitter most of our efforts are currently focused on.

That might help, but I'm thinking that still-image recognition will end up being much nicer, at least for translation. Take a sharp picture, drag your finger over the characters you want, no camera shake at all. At least in my limited trial, it was really hard to get the app to decide oon a character, and camera shake was a serious problem. I guess I want an iPhone 5 with optical stabilization.

Kiran <entropy@io.com>
 

mikelove

皇帝
Staff member
Entropy said:
That might help, but I'm thinking that still-image recognition will end up being much nicer, at least for translation. Take a sharp picture, drag your finger over the characters you want, no camera shake at all. At least in my limited trial, it was really hard to get the app to decide oon a character, and camera shake was a serious problem. I guess I want an iPhone 5 with optical stabilization.

The problem with still image recognition is that when the system gets a character wrong - and even the best ones do - you're kind of stuck; have to either re-take the image or look up the character another way. Whereas with live recognition you can be self-correcting, move the camera about a bit / resize the box a bit / etc, and know right away whether or not it recognized it accurately. We do need to work on jitter, but even with that I think it's a better design for the typical Chinese learner doing quick lookups than still image capture; still image is certainly a priority too, though, and that should get fleshed out over the next couple of 2.2.x updates before becoming a part of OCR on an equal footing with live capture in (hopefully) 2.3.
 

Entropy

榜眼
mikelove said:
The problem with still image recognition is that when the system gets a character wrong - and even the best ones do - you're kind of stuck; have to either re-take the image or look up the character another way.

Or, select the offending character and get a list of the most probable matches and choose the right one? So far, it's pretty obvious to me when the OCR engine gets it right, even though in the demo I never see it turn to blue.

mikelove said:
Whereas with live recognition you can be self-correcting, move the camera about a bit / resize the box a bit / etc, and know right away whether or not it recognized it accurately.

Unless there's so much green gibberish that you can't see the original character. I'd like to be able to divide the screen so i see the raw image and the overlay in separate panes.

mikelove said:
we aren't confident enough in the still image capture mode to sell it to iPad users who wouldn't be able to access OCR in any other mode

Will I be able to download it after I buy it on my phone? Much easier to test still image rec on an iPad. :)

~ Kiran
 

dustpuppy

榜眼
i think for the still image mode, you should let the user pan and zoom the target image, which would mimic moving the phone. that way, i can take a nice crisp picture of a sign with perfect focus, then perform character recognition easily with having to keep my hands steady
 

Luke

Member
The OCR is great, Mike. Thanks so much for working on the feature, it's hugely to so many of us. I'm fighting with iTunes to actually be able to purchase it (I'm in China but my Apple Store account is in the US…I think that complicates things), but on my iPhone 4 the OCR in demo mode has been impressive in its ability to correctly recognize characters. It will be a real life-saver for me here in Beijing.

Thanks again!
 

Entropy

榜眼
dustpuppy said:
i think for the still image mode, you should let the user pan and zoom the target image, which would mimic moving the phone. that way, i can take a nice crisp picture of a sign with perfect focus, then perform character recognition easily with having to keep my hands steady

Exactly. That would be much easier than aiming the camera. Just drag the image around with your finger.

~ Kiran
 

elipio

秀才
Mike, the OCR is out this planet! The silver detail in the icon is superb too... the coolest icon on the front page of my iPhone 4.
Thanks!
Pete
 

John

举人
Does the OCR depend on where in the box the character is ? I could get the OCR to easily recognise two characters earlier (displayed on my computer LCD screen) but as soon as I shifted the iPhone so that the left side of the box only enclosed the second character, the OCR had trouble recognising it.
 

mikelove

皇帝
Staff member
Entropy said:
Or, select the offending character and get a list of the most probable matches and choose the right one? So far, it's pretty obvious to me when the OCR engine gets it right, even though in the demo I never see it turn to blue.

That's fine for single-character errors, but maybe 25% of the time you'll get a page of total gibberish and have to re-take the whole thing; it's usually obvious right away at least, but it can be very annoying if you've already moved on from the thing you took the picture of and have to go back / frame it up again.

Entropy said:
Unless there's so much green gibberish that you can't see the original character. I'd like to be able to divide the screen so i see the raw image and the overlay in separate panes.

You can turn off the "green gibberish" with the "hide unused chars" option in Settings / OCR. Though an option to move the overlay might make sense too... I'm not quite sure where we could fit it on that already-overcrowded screen, though.

Entropy said:
Will I be able to download it after I buy it on my phone? Much easier to test still image rec on an iPad.

Unfortunately no - that does work on the iPod Touch (though you have to load the OCR data files manually and we haven't posted the link yet) but it won't even let you in on the iPad; as I said, we didn't want to spend time designing / testing an iPad interface for something we weren't yet selling on iPad.

dustpuppy said:
i think for the still image mode, you should let the user pan and zoom the target image, which would mimic moving the phone. that way, i can take a nice crisp picture of a sign with perfect focus, then perform character recognition easily with having to keep my hands steady

That's a possibility, but it doesn't really get around the problem of the recognizer not seeing an image correctly - the reason "live" panning works is that it's sifting through hundreds of frames of video, each with a slightly different angle / focus / lighting level / etc, while even a well-shot picture of a sign might not be recognized correctly. So it's requiring extra work on the part of the user (moving around the box) without the attendant improvement in accuracy that you get from live input.

We're actually leaning more towards something like the document reader, but with a photo - tap on a character in an image and get a popup definition bubble just like in the document reader. A key advantage to that is that it keeps the actual image right in front of you, so you can see exactly where a particular word appeared on a page and easily go back and forth between the original document and the onscreen version without having trouble keeping track of your location in it.

Luke said:
The OCR is great, Mike. Thanks so much for working on the feature, it's hugely to so many of us. I'm fighting with iTunes to actually be able to purchase it (I'm in China but my Apple Store account is in the US…I think that complicates things), but on my iPhone 4 the OCR in demo mode has been impressive in its ability to correctly recognize characters. It will be a real life-saver for me here in Beijing.

Thank you! If you're getting rejected credit card errors, the easiest way to clear them up is to contact iTunes support and ask them to unblock your account (http://www.apple.com/support/itunes/contact.html) - they get a TON of email like this and can usually fix the problem very quickly.

elipio said:
Mike, the OCR is out this planet! The silver detail in the icon is superb too... the coolest icon on the front page of my iPhone 4.

Heh, thanks - actually that was inspired by a user who wrote to say that he loved the product except for the icon and the splash screen. (we're still working on the latter, though it's about to become less of an issue now that OS4 / multitasking are finally arriving on iPad) But the old icon didn't even have correct drop shadowing, so a change was certainly overdue, and it was perfect timing since our icon's temporarily showing up in a bunch of places in iTunes that it doesn't normally (the iTunes-wide top grossing list, e.g. - we made more money yesterday than Flight Control, though that's considerably less of an accomplishment than it would have been a year ago :) ).

John said:
Does the OCR depend on where in the box the character is ? I could get the OCR to easily recognise two characters earlier (displayed on my computer LCD screen) but as soon as I shifted the iPhone so that the left side of the box only enclosed the second character, the OCR had trouble recognising it.

It can, for two reasons: #1, with only a single character to look at the recognizer might be having difficulty figuring out the correct font height (whether it's one character or two, e.g.) - usually not a problem but it occasionally does happen with certain characters - and #2, if the box includes a little bit of the previous character that might be confusing it. A good workaround when this happens is to point at the full word, tap the pause button, tap the > button, then tap on the character in the separate dictionary entry screen to look it up.
 

Dr.Grace

秀才
mikelove said:
djbass said:
I installed the OCR today but have not been able to reliably test it because for some reason the focus button has no effect on my 3GS, since the letters are too blurry it can't successfully identify characters.

That's odd... does the focus work correctly in the built-in camera app? It could be that there's something awry mechanically with the camera itself... if focus works OK in the built-in camera, does it help in Pleco at all if you shake your iPhone? For some reason that seems to convince the phone it needs to re-focus, at least on our test device.

I've been playing around with the OCR, and it's fantastic! I've made flash cards with all of the vocabulary in one volume of my textbook, in no time at all.

One suggestion: it would be nice to be able to create a new flash card category from within the OCR, so you don't have to keep going out to the flashcard organizer to make a new category.

I have seen the autofocus problem sometimes with my 3GS. Seems like the autofocus mechanism gets confused at times. Shaking the phone did not help, but exiting and re-entering OCR worked. Once it helped to focus out on something at a distance, then gradually shorten the distance to the text.

But what REALLY helps is using the magnifying lens in the Griffin Clarifi case. Fortunately, the guy I bought my 3GS from had one and gave it to me. I've experimented with OCR, with and without the lens. With the lens the OCR is much faster and less prone to focusing problems, especially for small type. So I'd recommend it for anyone with the 3GS.
 

mikelove

皇帝
Staff member
Dr.Grace said:
I've been playing around with the OCR, and it's fantastic! I've made flash cards with all of the vocabulary in one volume of my textbook, in no time at all.

Thanks! Hardly any of the beta-testers seem to have used that flashcard function, actually, oddly enough, so it's nice to hear it's working correctly.

Dr.Grace said:
One suggestion: it would be nice to be able to create a new flash card category from within the OCR, so you don't have to keep going out to the flashcard organizer to make a new category.

Good idea - we'll see about getting that added in 2.2.x.

Dr.Grace said:
I have seen the autofocus problem sometimes with my 3GS. Seems like the autofocus mechanism gets confused at times. Shaking the phone did not help, but exiting and re-entering OCR worked. Once it helped to focus out on something at a distance, then gradually shorten the distance to the text.

But what REALLY helps is using the magnifying lens in the Griffin Clarifi case. Fortunately, the guy I bought my 3GS from had one and gave it to me. I've experimented with OCR, with and without the lens. With the lens the OCR is much faster and less prone to focusing problems, especially for small type. So I'd recommend it for anyone with the 3GS.

Interesting - it'd really be nice if they'd start making those again, especially for the iPod Touch. Hopefully Apple will add an option for us to manually adjust focus in a future iOS release, or at least improve their autofocus code to hold a lock better at close distances. (though I can't fault them for designing it primarily for farther-away objects since those are what the vast majority of people are using it for)

numble said:
Mike: You need to update your website with all the OCR info.

Working on it, along with the obligatory announcement email.
 

kun4

举人
Dr.Grace said:
With the lens the OCR is much faster and less prone to focusing problems, especially for small type. So I'd recommend it for anyone with the 3GS.

At least one manufacturer of such 3G/3GS cases is located in Guangzhou.
http://www.bohobo.cc/iphone-accesso...es/crystal-magnifying-glass-shell-for-iphone/
Costs less than $6 retail:
http://www.focalprice.com/IP447W/Hard_Crystal_Case_with_Magnifier_Lens_for_iPhone_3G3GS_White.html
Maybe it would be interesting to inquire how much an iPod Touch 4 case would cost?
There's a market in this, not only for Pleco OCR, but also for the much bigger market of barcode apps.
 

mikelove

皇帝
Staff member
kun4 said:
Maybe it would be interesting to inquire how much an iPod Touch 4 case would cost?
There's a market in this, not only for Pleco OCR, but also for the much bigger market of barcode apps.

It's not a question of the per-unit cost but rather of the quantity; even a small Chinese factory is going to want at least a 10,000 unit order - it costs something just to make the molds - and given that we wouldn't even take delivery on the things until January or February (no hope of getting them for Christmas at this point) I don't think we'd be able to sell more than a couple of thousand before September (when there's a very good chance that the next iPod Touch would include autofocus and effectively kill the market for this).

So it'd be nice if somebody developed this, but I don't think it would make sense for us to do so on our own - needs to be somebody who can move a lot more units than we can.

This would actually be an excellent idea for a Kickstarter project - someone else did the same thing recently for an iPhone grip holder and got it funded many times over; all you'd need to do is find the factory, figure out how much it would cost, start a Kickstarter project to raise the money (the reward for contributing being a copy of the finished product), and plug it on a bunch of gadget blogs / convince companies in the OCR / barcode reader business to spread the word about it. Pleco's involvement would probably be a negative for the last part (iPhone developers tend to distrust other iPhone developers, and in this case since our name would be right on the Kickstarter page they actually would be giving us free publicity) so it would be much better if this was someone more neutral.
 
Top