Reverse OCR

#1

Post by mrtbld » Wed, Nov 05, 2014, 1:39 PM UTC

Reverse OCR
reverseocr.tumblr.com

Re: Reverse OCR

#2

Post by albertzeyer » Wed, Nov 05, 2014, 2:29 PM UTC

I was thinking about this: http://www.cs.toronto.edu/~graves/handwriting.html

Re: Reverse OCR

#3

Post by bane » Wed, Nov 05, 2014, 2:30 PM UTC

This could be a cool way to visually "encrypt" messages. They're readable, but only by the correct tool. I wonder how these squiggles might be creatively arranged steganographicly in an image and still be "read" by the OCR tool.

Re: Reverse OCR

#4

Post by cosarara97 » Wed, Nov 05, 2014, 2:31 PM UTC

I couldn't get that OCR to read my mouse-written E. It's a nice experiment nevertheless.

Re: Reverse OCR

#5

Post by mrtbld » Wed, Nov 05, 2014, 2:33 PM UTC

Perhaps this could lead to a new kind of captcha that only bots can solve. I doubt it would be efficient, though.

Re: Reverse OCR

#6

Post by emhart » Wed, Nov 05, 2014, 2:37 PM UTC

It has been fantastic watching Darius' myriad experiments over the past few years. His work always has a great mixture of whimsy and serious experimentation.

Re: Reverse OCR

#7

Post by amelius » Wed, Nov 05, 2014, 2:38 PM UTC

albertzeyer wrote: post #2

I was thinking about this: http://www.cs.toronto.edu/~graves/handwriting.html

I wonder if it also works for voice synthesis.

Re: Reverse OCR

#8

Post by amelius » Wed, Nov 05, 2014, 2:41 PM UTC

cosarara97 wrote: post #4

I couldn't get that OCR to read my mouse-written E. It's a nice experiment nevertheless.

Indeed, the underlying OCR seems to need lots of work still. It's no wonder that the "reverse" operation results in such messy line art.

The demo is nice, though.

Re: Reverse OCR

#9

Post by MrBra » Wed, Nov 05, 2014, 2:45 PM UTC

Nice. Finally computers approached the age of writing. :)

Re: Reverse OCR

#10

Post by Aaronneyer » Wed, Nov 05, 2014, 2:46 PM UTC

Looks like my handwriting