Big Brother just got scarier: Japanese CCTV camera can scan 36 million faces per second

reply to post by buddha

36 million faces per second

Wait a minute.
Can anyone think of a place where there are 36 million people in the same spot all at once?
I can't.
I guess this means that it would have a fairly easy time identifying everyone since there aren't even nearly that many people in Times Square for New Year's Eve. Maybe if the camera looked at each person 12 times in one second and tracking their movements. Is that even possible?

reply to post by stumason

Now, tell me, where are they saying they plan to put these camera's in your homes, public restrooms or dressing rooms?

Your question was brought up just the other day.
www.abovetopsecret.com...

Originally posted by Biigs
Result of this system to catch every tiny criminal every time, might that be bad overall?

Consider the trend that everyone may be labeled as a criminal eventually....then what?

At what location will 36 million faces pass within the frame of any one camera per second? Or how long will a camera have to run for 36 million faces to pass in front of ..in order to take one second to scan them?

Overkill if you ask me.


ETA: Just saw your post, post by Afterthought

In that case I second that question.

Originally posted by UberL33t
At what location will 36 million faces pass within the frame of any one camera per second? Or how long will a camera have to run for 36 million faces to pass in front of ..in order to take one second to scan them?

Overkill if you ask me.

 

ETA: Just saw your post, post by Afterthought

 

In that case I second that question.

edit on 3/24/2012 by UberL33t because: (no reason given)

I think this is a hoax. Moderators, can we put this in a hoax bin?

reply to post by RUSSO


Wait, not just yet.

This technology, its real.

As one example, if a person walks into a convenience store and robs the cashier, if his or face is captured by a video camera, police could use that imagery to search for that same face in prior video recorded by the store to see if that person has been to the store before, and if so, if they left any clues as to who they might be, by say, using a credit card to pay for purchase. Similarly, the same face could be searched in a much larger database of still or video that the police have stockpiled from surveillance cameras from other places, allowing them to see, almost instantly, if that person has been caught on tape at any other point in time doing anything that might help lead to an arrest, such as trying to pawn stolen merchandise. Perhaps more interestingly, the system can be used to scan for that face in a large crowd. It will look at each individual face in every scene in a video for a match.

Representatives from Hitachi say the system works by using image recognition software combined with algorithms that group people who have similar faces.

Currently, those in the surveillance business have to sift through video by actually watching it all to try to identify someone they suspect might have appeared in another video. This new system, its makers say, should be of great interest to mass transit authorities, police and store owners, particularly those that run large ones that have a lot of people coming and going. They also say that they expect to deliver a finished product next fiscal year, which means organizations that are interested, can start booking orders almost right away.

www.physorg.com...

More on this tech:

Developed by Hitachi Kokusai Electric, the system can automatically detect a face from either surveillance footage or a regular photo, and search for it.

The search results are displayed immediately, showing thumbnail images of potential candidates. When a thumbnail is selected, the associated recorded surveillance footage can be viewed, so users can quickly review the persons actions before and after the image was taken.

"This high speed is achieved by detecting faces through image recognition when the footage from the camera is recorded, and also by grouping similar faces."

www.diginfo.tv...

reply to post by burntheships


Thing is. Should ordinary people bother about this?

reply to post by RUSSO


Well, one thing for sure...the organic farmers market most likely will not have
one of these....now that vs Costco, or another big store....???

We think this system is suitable for customers that have a relatively large-scale surveillance system,
such as railways, power companies, law enforcement, and large stores." www.diginfo.tv...

Originally posted by Afterthought
reply to post by AaronWilson

 

As an introvert, I NEED privacy. I am to the point where to enjoy my weekends, it requires me to hike seven hours out into the mountains to be alone.

I'm right there with you.

The older I get, the further I want to be from the hustle and bustle of society. I'll never take my personal space and privacy for granted nor trade them for anything.

You guys DO know that they can see you from satellite, right? Good enough to home in on your cell phone and read your license plate

Originally posted by Afterthought
reply to post by RUSSO

 

That's just crazy!

I have to roll my eyes when people say that facial recognition technology isn't this advanced yet.
Sure. Right.

I tend to not take that claime of x faces per second seriously. I can't believe a fairly conventional computer will work that fast. Can some computer-knowledgeable person give us an opinion on that Japanese claim?

The loophole is that the faces have to be at least 40x40 pixels in size. Any less and the matching does not work so well.

40x40 is a 5x5 of chessboards, to help visualize the detail needs. If only one of those 1600 pixels are different, the computer sorts you in another way.

May I suggest that should you ever need to get past ID supercameras in the future, that you apply a realistic mole on your face that can be repositioned at various times of the day at your discretion. Make sure it is a rather large mole.

36 million faces a second is only after the faces are logged. Acquiring the faces takes considerably more time. And, there are always hackers of databases that are able to mess with the computers, and crooked database operators, and people living with stolen IDs, and power failures. Why is 36 million faces a second important, when there has to be a human being around to verify the faces.

I imagine a 36 million face a second profile sorting session in Japan would go something like this:

Black hair. Dark brown eyes. Asian complexion. Flatter nose.

That is a generic stereotype of almost every person from Japan or in Japan. Actually, in reflection of my post in the making, did they just create a I-can't-believe-it's-not-racist algorhithm in their supercamera program? They'd have to, to find faces that fast. Digital segregation, at light speed.

I guess the scary thing would be when they take this program and attach it to an unmanned flying vehicle, with weapons, and train it to destroy anybody who fits the descriptors on the list. SkyNet, I'm looking at you.

The system holds insurmountable benefits to the casino security team, as well as to the police force. The Stratosphere became the first casino in Las Vegas to use facial recognition technology back in 1999. The system installed was created by Viisage, which is now part of L-1 Identity Solutions. Managers of the Stratosphere used a preloaded database of recognized offenders, along with the addition of their own known crooks, to identify potential threats to the business (Blades 2007). Corporate vice president of surveillance and compliance officer for American Casino & Entertainment, Derk Boss, explained the positive and negatives of the system in an interview:

The system was a great help in the beginning. It helped us recognize people who were just flying in from Atlantic City to Las Vegas and playing our games, and we were trying to figure out who they were because they were using false names and such.

www.abovetopsecret.com...

On top of the Mandalay Bay Casino is a TV News camera for one of the local stations... A few years ago here in Vegas the Fire Department, in an attempt to run a fireworks display safely, managed to set the wetland on fire. It was a major blaze and gave them a lot of embarrassment.

Filming the news, the TV station zoomed the camera from the Mandalay Bay's roof onto the fire over 3 miles away in Henderson. The footage was so clear you could read the writing on the Fire trucks

Vegas has cameras everywhere... every street corner, every casino, every taxi cab... and possibly every tourist

Originally posted by zorgon

Filming the news, the TV station zoomed the camera from the Mandalay Bay's roof onto the fire over 3 miles away in Henderson. The footage was so clear you could read the writing on the Fire trucks

Vegas has cameras everywhere... every street corner, every casino, every taxi cab...

Oh my God.

How can I not believe in God these days? So much tec to proof HE.

Its something to think.

WHO is god(in present days)?

I just went back and reread the article. Scratch my above statement. I misunderstood when I read it the first time.

As I now understand it, if I walked in front of a camera at say Wal-Mart. If I've been to that Wal-Mart before, the camera would load my image and would try to match it with the 36 million other faces in its database. If I've been to that store before, it would be able to match me to my previous photo within a second.

This is the type of stuff that's coming to Orlando soon. When you walk into a store, the camera will recognize and engage you. It may say something like, "Hi, Ms. Jones. Welcome back! We have your detergent on sale today."

Scary.
I'd be more impressed if we could get technology to buy that stuff for me and deliver to my door.

In 2010 the USA had over 40 million black folks, guess they have nothing to worry about.

Source

Or have they. Worked out that problem yet?
Facial recog. Racist?

Originally posted by Afterthought
Scary.
I'd be more impressed if we could get technology to buy that stuff for me and deliver to my door.

edit on 25-3-2012 by Afterthought because: (no reason given)

Really?

So the 'technology' would say hey Mr Jones I see you buy a dozen eggs every third Tuesday, I took the liberty to buy and deliver this upcoming Tuesday's eggs. Then you say to yourself "But I only had ten bucks in the bank and I'm gonna be out of town for two weeks for work WTF!".

reply to post by emaildogs


Here's a bit about what they're planning.
"Bars, stores to use facial recognition technology to increase sales"
www.clickorlando.com...

For example, if a woman was to walk up to a mall directory, a camera inside would take a photo. It will recognize her gender, age and race and instantly provide an ad for the appropriate products. So, if the shopper is a 30-year-old woman, she might see adds for makeup, shoes and clothing.

Industry expert Rafe Needleman believes it's just a matter of time before stores not only to recognize you, but track your spending habits.

“When you walk into a store, it might know who you are just when you walk in and give you deals based on past purchases,” said Needleman.

I'm just not comfortable with this technology at all.
(I was kidding about the tech sensing what I needed and delivering it to my home. That would be way too invasive.)

Since this tech is going to be able to track your spending habits, I have to wonder if all the stores with saver cards like CVS and Winn Dixie have been tracking this for years in anticipation of this system. All they'd have to do is load your card's data into the machine and everything's already set for the next time you come in. How convenient.

reply to post by Afterthought


I think you are right.
This face-recognition-system is the ultimate tool for data mining

The amount of statistical information this could be used for has enormous advantages when directing ads towards individuals, and optimizing market strategies. Combine this with facebook...