TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

OCR by uploading images to Google Docs

66 pointsby gintasover 14 years ago

10 comments

antyover 14 years ago
In case anyone wonders: I tried if Google could solve its own captchas. It can, if each character is separated, but once they overlap, like they usually do, it doesn't work.
nodataover 14 years ago
Does anyone know if this uses Google's open source tesseract-ocr software?
评论 #1942800 未加载
CWuestefeldover 14 years ago
I find it tremendously frustrating that so many people are creating this problem for themselves.<p>Anything that needs to be data should be data, not images. Except for some very specific cases, you're not doing anybody any favors by outputting PDF. That format is a data black hole. It allows you to transmit very well-formatted output, but it absolutely <i>stops</i> you from reliably <i>using</i> anything in that content.<p>I beg you all: if it's anything that contains data, or really, if it's anything for which layout and formatting is not absolutely critical, please don't use PDF. Send data as data.
评论 #1942498 未加载
评论 #1943469 未加载
评论 #1942464 未加载
ylemover 14 years ago
Has anyone checked to see if this works with Japanese, Korean, or Chinese? What about Arabic or Hindi? This would shed some light on whether it's likely to be tesseract or ocrpus....
joakinover 14 years ago
Wow I just tested with an image, and you get a GDoc with the image on top and the OCRed text in the bottom.<p>Pretty cool.<p>I wonder what are they using for Google Goggles and this
Estragonover 14 years ago
Incidentally, I noticed that if you try to use tesseract on an image taken from a Google Books page, you get terrible OCR accuracy. Anyone know why that is?
评论 #1942638 未加载
Tichyover 14 years ago
Is there an API by any chance?
评论 #1942472 未加载
mikecaneover 14 years ago
G1ver whar OCR locks lice in g00gLe ePubs in g0og1e Buuks, th1s w111 du we11.
trezorover 14 years ago
Trying to improve some scanned forms I have, I got an average of 5 characters per page recognized. Also form formatting recognized as "1 1 1 1 1 1 1 1 1 1 1 1 1".<p>I may not rely entirely on google docs for my OCR needs in future ;)
评论 #1942792 未加载
rorrrover 14 years ago
I wonder what's stronger - google OCR or google captcha?