ISSUE-66: image analysis heuristics - suggest closing on 2009-09-03

Sam Ruby and Dan Connolly asked me to send proposed issue closures in  
individual emails, with clear subject lines, and Cc'd to the issue  
originator when possible. Apologies for the spam. If there are no  
objections, I will close this issue on 2009-09-03.


ISSUE-66: image analysis heuristics

This issue raises an objection that is editorial in nature, and I do  
not believe it will have a material effect on normative requirements.  
Since being raised, this issue has not drawn any further discussion,  
nor had any actions assigned. I suggest that discussion of editorial  
text should just be done on the list and bugzilla - this doesn't seem  
important enough to block Last Call.

Further, I believe the premise of the objection is false. The  
objection categorically says that state-of-the-art image analysis  
heuristics cannot recover useful information from an image, "not even  
close". There exist optical character recognition algorithms that  
could recover text from an image of text with high probability of  
success. There are also image analysis algorithms that can detect  
specific features with fairly good accuracy. For references see < 
 >. I believe the current state of research is beyond what is descried  
in that article and at the links.


Received on Friday, 21 August 2009 05:45:52 UTC