In his defense that quote was taken out of context. In the actual interview being quoted he is referring to his company purchasing a few iPads to explore the technology.
SEIDENBERG: -- they want, when they do it. (Laughter.)
But, on balance, they're good for the industry. They create -- if you don't mind, I'll just -- let me extend to the iPad --
MURRAY: Yeah, sure --
SEIDENBERG: -- just to give you a -- (inaudible) -- everybody's familiar with this. So, like everybody else, you know, we're interested in it. So we had our -- some of our technology people go out and buy a couple of devices --
MURRAY: You didn't stand in line on Saturday?
SEIDENBERG: No, I had somebody else stand in line. (Laughter.) But we had people standing in line.
* Phone numbers are also stored to manage the number of accounts created per phone.
so, that should prevent some abuse by spammers
Re:Maybe it's monday, but
on
The Face Detector
·
· Score: 2, Informative
The dataset they are probably using is the CMU+MIT hard face detection dataset available here (link to 30 meg tar file at bottom of page):
http://vasc.ri.cmu.edu/idb/html/face/frontal_image s/
This dataset is made of images that contain static, contain faces at unique angles, contain complex scenery which would mess up the way most face detection algorithms work, and more "hard" cases. It's the dataset that all face detection programs are tested against. If I remember correctly most other face detection programs only achieve approixmatly 80-85% detection rate when they only get 4 false positives in the results, so this algorithm is definatly an improvement.
Slashdot Mirror
... which is a violation of Net Neutrality.
... which doesn't apply to countries outside the US
Your company's internet service is crap!!!
neither of them, this is slashdot after all
This reminded me of this story. http://qntm.org/responsibility
From the interview transcript:
SEIDENBERG: -- they want, when they do it. (Laughter.)
But, on balance, they're good for the industry. They create -- if you don't mind, I'll just -- let me extend to the iPad --
MURRAY: Yeah, sure --
SEIDENBERG: -- just to give you a -- (inaudible) -- everybody's familiar with this. So, like everybody else, you know, we're interested in it. So we had our -- some of our technology people go out and buy a couple of devices --
MURRAY: You didn't stand in line on Saturday?
SEIDENBERG: No, I had somebody else stand in line. (Laughter.) But we had people standing in line.
when you go to sign up it tells you:
* Phone numbers are also stored to manage the number of accounts created per phone.
so, that should prevent some abuse by spammers
The dataset they are probably using is the CMU+MIT hard face detection dataset available here (link to 30 meg tar file at bottom of page): http://vasc.ri.cmu.edu/idb/html/face/frontal_image s/
This dataset is made of images that contain static, contain faces at unique angles, contain complex scenery which would mess up the way most face detection algorithms work, and more "hard" cases. It's the dataset that all face detection programs are tested against. If I remember correctly most other face detection programs only achieve approixmatly 80-85% detection rate when they only get 4 false positives in the results, so this algorithm is definatly an improvement.