This is really neat. I was playing with it on pictures of street signs and buildings and realized that if I select some text and then do ctrl+a it tried to select everything it thought was text...Then I used right click > translate > reprint to see what it thought each thing was.
Here is the picture: http://thesuperslice.com/wp-content/uploads/2012/04/downtown...
And the text outcome - found it most interesting what symbols it thought it recognized:
lam
on-0'0
s.
Ic 0on
§-i-
I-*-
-unm
-$3.»;
o
G %T1
00-O
. o C-‘7' H ' .-.”-." «'~3;
.35
$16 O-O
‘D Q-=¢1
‘-M
km“
‘MIMI
DOW:
TLDR
D001”
'."'IIu
ff"
)0‘
\\
,¢-.5 ,:~L.
r/J