Half a croissant, on a plate, with a sign in front of it saying '50c'
h a l f b a k e r y
My hatstand runneth over

idea: add, search, annotate, link, view, overview, recent, by name, random

meta: news, help, about, links, report a problem

account: browse anonymously, or get an account and write.

user:
pass:
register,


                         

OCR translate

french2amharic4mobileCam
  (+2, -1)
(+2, -1)
  [vote for,
against]

Read a swedish book by uploading an image from your webcam to google translate.
pashute, Jul 26 2010

OCR translate http://www.tauyou.com/en/image.html
[Jinbish, Jul 26 2010]

Amharic http://www.language...pedia/a/amharic.gif
uses a pretty syllabary, but would challenge most OCRs, I suspect. But that's OK, because it didn't say "Amharic2French", did it? [pertinax, Jul 27 2010]

Then again maybe it's baked (google goggles) http://www.youtube....watch?v=FYFSNy9FGqA
I'm not sure this is available yet to the public... [pashute, Jul 28 2010]

Halfbakery:Remembrance:Jinbish Jinbish
[pashute, Nov 06 2012]

[link]






       Shan't. So there.
MaxwellBuchanan, Jul 26 2010
  

       Less technically challanging, but perhaps also useful (and stronger justification for using an image as input) if it just tells what language the writing's in.   

       Another variant, using a gimmick to reduce the computational difficulty: give it photos of a few pages, and it looks for a match on Project Gutenberg, or similar, and translates *that* (or finds an existing translation).
mouseposture, Jul 27 2010
  

       Or the front cover... The Amazon app on the iPhone effectively recognises images of products. The image recognition could be a useful augmentation to the text recognition.
Jinbish, Jul 27 2010
  

       Anno translated from English via google translate to Danish: (Didn't think of Danish when I entered the idea, even though I definitely enjoy pastry...)   

       Faktisk sidste år jeg var nødt til at hjælpe nogle ældre etiopiske jødiske mænd med en bønnebog i amharisk. Jeg var i stand til at finde ud af de breve, fordi de ligner gamle hebræisk, dvs Phonicean alfabet - en forløber for det latinske og dermed engelske alfabet ...   

       Min kone forlod en svensk bog i vores arbejde på værelset, og jeg begyndte at oversætte det ved at kopiere teksten i google oversætte ...   

       Jeg kender det eksisterende software, der gør dette, men jeg snakker om google oversætte som er gratis og godt nok til at forstå, hvad siden siger.
pashute, Jul 28 2010
  

       Ah - I was about to link to Google Goggles... i see you've got there already.
Jinbish, Jul 28 2010
  

       Oh,wow. How inaccurate would *that* be. OCR x MT = gibberish.
squeak, Jul 30 2010
  

       Pashute, jeg gjorde det en måned eller to siden med et finsk bog, jeg gerne ville
læse. Google har givet mig mange halv-bagt OCR-oversættere
hvoraf ingen syntes enhver brug, så jeg endte ved en to-trins proces.
Først vil jeg scannet en side, jeg ønskede at læse, så jeg har uploadet den til et websted
navnet 'Fri OCR ", som jeg fandt, at der støttes finske karakterer. Så jeg
indsat produktionen i Google Oversæt. Det var let at se misreadings på dette punkt (måske 5 eller IO en side), fordi Google ikke
oversætte dem.
Naturligvis dette gjorde at læse bogen temmelig langsomt og jeg er ikke færdig
det endnu!
Jeg har sat dette annotation gennem den samme proces - at udskrive,
scanning, uploading til F ree-OCR.com, indsætte output i Google
Oversæt - men uden den manuelle korrektion. Jeg håber, at denne danske gør
eller anden form for mening for dig!
pocmloc, Jul 30 2010
  

       Yes Pocmloc, it does, thanks for the note.   

       Sorry to hear of Jinbish's (Dr. John Bush) fate, and wish his family my condolences. (see link)
pashute, Nov 06 2012
  
      
[annotate]
  


 

back: main index

business  computer  culture  fashion  food  halfbakery  home  other  product  public  science  sport  vehicle