Slashdot Mirror
Breakthrough In Face Recognition Software
An anonymous reader writes: Face recognition software underwent a revolution in 2001 with the creation of the Viola-Jones algorithm. Now, the field looks set to dramatically improve once again: computer scientists from Stanford and Yahoo Labs have published a new, simple approach that can find faces turned at an angle and those that are partially blocked by something else. The researchers "capitalize on the advances made in recent years on a type of machine learning known as a deep convolutional neural network. The idea is to train a many-layered neural network using a vast database of annotated examples, in this case pictures of faces from many angles. To that end, Farfade and co created a database of 200,000 images that included faces at various angles and orientations and a further 20 million images without faces. They then trained their neural net in batches of 128 images over 50,000 iterations. ... What's more, their algorithm is significantly better at spotting faces when upside down, something other approaches haven't perfected."
"What's more, their algorithm is significantly better at spotting faces when upside down, something other approaches haven't perfected."
Add this step: Rotate the image and run the algorithm each x degrees. What am I missing?
"Breakthrough in face recognition software"
"The idea is to train a many-layered neural network using a vast database of annotated examples"
How novel.
For every "terrorist" they track through the mall, how many ordinary Joes like me who like their privacy are also tracked and stored in huge databases for all time?
Rats, there goes my ceiling-walking bank-robbery plans.
Table-ized A.I.
"using a vast database of annotated examples"
Oh Rlly? You have a massively perfect training set and things just magically work better? I'm shocked.
It reminds me of the paper I read about a "breakthrough" in text processing that mysteriously used the exact same algorithms already known in the field. When you went through the finer details of the paper you found that they had the grad-student slave manually go through all the training pairs and select the "correct" training data. Shockingly enough the hand-tuned results worked better when applied to an artificially narrowed test set....
AntiFA: An abbreviation for Anti First Amendment.
The grocery store or ATM, with cameras all over the place, could do it by simply having a sign at the front of the store that says CCTV. They could record your picture at the register and associate it with a bank card or credit card. After 5 transactions they could guarantee that the person using that card has your face and is likely the owner. They could then flag how many times somebody else uses your card. They could track you throughout the store, like they do now but associated with an individual. Stores would have cameras at the entrances and exits. They would know how many people are currently in the store and who they are. They can't track though, I use cash, right?
The grocery store subscribes to a third party a face recognition aggregator.
At the beginning you'll have a shadow profile (#34950892). All it takes it one pump at a gas station, or taking cash out at the ATM to associate your face. About the only thing you could do is wear a disguise, but a different one each time.
What if I copyright my face and charge every time someone stores an image of my face??? Cha-Ching!!!!!!!!
http://arxiv.org/pdf/1412.1897v2.pdf
Very much anecdotal, but here goes anyway - a little while back, I found a recipe for cow tongue that seemed intriguing. If I had eaten it before I couldn't recall, at least I hadn't prepared it myself. So off to the butcher's I was, as this is not found in every shop. The tongues they had on display there seemed very tiny (in retrospect, they must have been veal tongues), so I said "give me the largest tongue you have". As the saying goes, "you should be careful what you wish for" - what I ended up with was a monster, something like over 1.3kg (nearly three pounds). I really didn't need that much, but all I could do was to say thanks and go home with my prey.
As I laid it on my cutting board, pretty much filling it entirely, it looked at the same time so awesome and gruesome that I had to take a photo of it (not a food blogger, or a blogger of any kind, I just had to document it). And to share the experience, I sent it to a friend via Hangouts. Now, as she uses Hangouts from the GMail web interface, the images are not visible inline but are Google+ links. So she clicks the link.
...and G+ helpfully asks her "Is this xxxxx?" (xxxxx == her name) While people are, rightfully, concerned whether companies such as Google know too much about their lives, at least when it comes to Google and facial recognition, they have a long way to go.
When there is a competition to test solutions, do they call it a "face off" or a "face face off"?
Table-ized A.I.
Hurray! :(
Even less privacy.
The facial recognition software thinks all Asians are the same guy.
Priest: "Universe from nothing, no laws of physics, sped up time"+ huge discrepancies. Creationism? No. Big Bang Theory
The top technology I'd like to undiscover is nuclear fission, for its military applications. I am aware there are civilian uses, but the military downside is greater. I want facial recognition to remain undeveloped. I wonder what sort of police state the computer technology of 2015 has made possible.
Finally the wast number of upside-down portrait photography in my hard drive will be recognized, instead of just identifying power outlets as faces. Some of you will definitely know what I'm talking about.
Can I finally automatically tag the performers in my porn collection? I'm asking for a friend.
It seems that they've increased the data size, and that's about it. How about having a paper that shows the false positives that might happen? There's a paper out there with noise based images that fool the convolution nets with a random set of noise. Or remember the one with the back end of a duck that fooled haar classifiers?
What are the false positive rates on these?
When they figure out the IR LED vs camera problem. ;)
I didn't read the article, of course, but the summary sounds like they're doing face *detection* not recognition.
Detection: find which portions of an image are faces.
Recognition: compare to a database of faces and find out whose face it is.
First is way easier than the other.
I apologize for the lack of a signature.
The most important numbers are suspiciously missing. The old best performance, and the gains by the new algorithms. Instead a lot of hoopla about "how much better it is" and what it's doing differently. Maybe it's a serious break-through, but the summary certainly hasn't convinced me of diddly squat other than a bunch of kids tried some new things, and they think they're hot shit because they picked some data-sets that lent well to their algorithm. Please. I was a grad student once too.
I wish that interesting developments in algorithms such as this could be discussed without resorting to cynicism (as in, how they'll be used by the NSA to breach our privacy and etc). Yes they're valid concerns but my God, what point is there in enjoying advancements in technology if you're going to see the downsides in everything? I long for a simpler time when we didn't need to worry about such BS.
Facial recognition implementations based on Viola-Jones tend to have much better results for certain ethnic groups, specifically Caucasians. How does this new algorithm fare in an increasingly racially diverse population?
This is frankly beyond disturbing. While the technical aspects are "Gosh! Wow! Amazing!" the fact is this technology will most assuredly be horribly abused.
This is a hugely invasive technology...and while the hue and cry will be "...because TERRORISTS!!" this has little to do with low probability external threats (external in the sense that someone from outside the culture/society infiltrates the populace) and everything to do with those who have established themselves in power exerting control over the population.
And to the apologists that want to trot out the "you cant expect privacy in public" and the "if you haven't done anything wrong you have nothing to hide" arguments...they are both fallacy's.
You can, and its not about hiding anything, respectively.
Adding another 5 million images to your training database to get a better recognition rate over the previous guy isn't a breakthrough. There's nothing new to this. It's applying a deep neural net to a large training set. Maybe they've sped up the training rate, but that advancement would apply to all deep neural nets, not face recognition specifically.
Masks like http://www.thatsmyface.com/vmchk/3D-Portraits-and-Masks/View-all-products.html become necessary for even a modicum of privacy? Perhaps we should open-source a generic set of faces.
The faintest grasp on machine vision. That goes for your 5 moderators, too.
Facial recognition mostly gets used for all of the wrong reasons, Facebook tracking, illegal police tracking etc.
'photos of innocent people have been retained in contempt of an explicit order from the court to remove them' - 18million by police
Facebook's new face recognition policy astonishes German privacy regulator
And what about people who don't have Facebook accounts, does Facebook allow 'tagging' of their faces?, I'm already annoyed by Facebooks obvious data collection on me as shown by the fact I get email from them telling me who my friends are and inviting me to join.
Waterfox - a Firefox fork with legacy extension support, security updates and better privacy by default.
This plus drones with missiles = aimbots in RL
Have I missed something?
I've always believed algorithms and neural networks to be essentially opposites to each other.
Algorithms are blocks of code that handles a predefined task. Classic example: quicksort vs bubblesort
Neural networks are a black box of systems that are trained with input until they produce the output you want. Further, even when it is working, you won't truly know what is happening internally, and you're only hope of knowing that it works is throwing a ridiculous amount of inputs at it and seeing how it responds.
Is it even possible for one to figuratively work on face detection/tracking software on low power ARMv7/8 CPUs?
What's more, their algorithm is significantly better at spotting faces when upside down, something other approaches haven't perfected.
Very usefull if you want your system to work in Australia!
Try it! Library of Babel
OTOH, what these networks have actually learned can be eye opening.
Stefan Axelsson
"Add this step: Rotate the image and run the algorithm each x degrees. What am I missing?"
The title answers your question.
Don't those guys on the NCIS TV show do this all the time?
Everything we need to know to defeat these we learned in Army tradecraft.
Back in WW II.
Keep trying, n00b2.