Detecting Faces (Viola Jones Algorithm) - Computerphile

Deep learning is used for everything these days, but this face detection algorithm is so neat its still in use today. Dr Mike Pound on the Viola/Jones algorithm.
Viola/Jones Paper: bit.ly/C_RapidObjectDetectPaper
After detection you may want to ID the face: • How Face ID Works... P...
Hardware Hacking: • Hardware Hacking - Com...
EXTRA BITS: • EXTRA BITS: Face Detec...
/ computerphile
/ computer_phile
This video was filmed and edited by Sean Riley.
Computer Science at the University of Nottingham: bit.ly/nottscomputer
Computerphile is a sister project to Brady Haran's Numberphile. More at www.bradyharan.com

[@dvilardi]

Placing a GoPro close to the paper to see what the guy is writing: check. Guy is left handed: oh boy...

[@shantinguyen3195]

Left hand and is filed under the impression that the only thing I

[@Sam_Kings]

Can't believe I have only recently discovered Computerphile. Your content is great guys, very interesting.

[@Vogel42]

you have a lot to catch up on

[@Sam_Kings]

@@Vogel42 I have been binge watching Mike's stuff about passwords. It has made me paranoid.

[@kerron68]

Welcome

[@stupedaso5046]

If you haven't yet, check out numberphile

[@OvertakeGT]

Computerphile Captions please? Haven”t been able to learn from your previous 15 videos without captions disabled...

[@ZeedijkMike]

I could listen to Mike for hours. Though some of the _stuff_ goes right over my head - I still feel a little smarter after each video.

[@aychaKifah]

me too

[@saurabh7489]

Me too. My intelligence part is terribly low. I understood maybe only 1% of this video. But 1% is still much better than maybe even the negative impact of watching `shorts` or `tick-tocks` for an hours.

[@daft_punker]

This man face detects! Mike Pound is an absolute legend

[@AlejandroThacker]

I'm really thankful for having Peter Parker explaining us in such a friendly and simple way.

[@TH3J0KEI2]

I am a simple man, I see Mike Pound, I like

[@harrysvensson2610]

You see Mike Pound, you Pound.

[@geniusonejustin5847]

A fellow hacker... anyway I see you also comment because everybody knows KZbin dislike does nothing

[@joonasfi]

You like to... pound.. Mike?

[@Shocker99]

I am a simple man.

[@silkwesir1444]

Is it just me or does he look a lot older all of a sudden?

[@kranefivem]

Gotta love this guy

[@Sonex1542]

THIS IS PROBABLY THE BEST ~EVER~ /COMPUTERFILE EPISODE DONE. I would have loved to see more detail matched from the paper to practical application. But over all. Amazing video.

[@karlkastor]

I actually used this when I played around with OpenCV, but didn't know how it works, very interesting! I'm actually taking a few computervision classes this year, hope its as interesting.

[@sorrefly]

I already am at college, and the course is very interesting! Totally worth it. There are a lot of things that I thought were working differently but apparently when doing image processing you need to learn to think about things in different ways

[@nullnull6032]

this is really one of the best sources for computer vision students, I love the way he explains things, Thank you!

[@HebaruSan]

Amazingly clear explanation of a very clever algorithm. Thanks!

[@andrepedersen1147]

Always amazed of how Mike Pound make videoes so entertaining and interesting at the same time

[@drulli6]

Really interesting video/algorithm. I generally really like the topics Mike does for the computerphile videos.

[@mahakileach9223]

i am positive that the drawings on the whiteboard where just quickly randomly scribbled on before the video to add to the background.😂😂

[@thomasp4902]

I had to explain this at uni :) Unlike another commenter I didn't notice much difference with race, but lighting was definitely an issue. It's also quite slow to train and it requires quite a high resolution image of the face. Unfortunately we had to detect with small faces, mixed races, and mixed lighting but it gave good results. Explanation is really good though ^_^

[@MarkBTomlinson]

I really enjoy Computerphile and dare I say the enthusiasm and presentations from Mike the most. Nothing taken away from the great team it is just that I can imagine chatting in a pub with Mike somehow.

[@nicksherron9603]

Love me some Dr. Mike Pound! Keep them coming!

[@damirdze]

Mike , you are doing the marvelous presentations.

[@Torsan1977]

Woah! Inception... I was compiling my implementation of a neural network for object detection (takes about one minute) and I had a look at my youtube feed and this was at the top! We do Viola Jones at work so I'd heard about it before. Thanks for the video!

[@jumbo6498]

This is a suprisingly intuitive detection method, great explanation!

[@meeradad]

You have an excellent way of making a complicated thing very easy to grasp.

[@retroman7952]

I like your work Dr. Pound! Keep it up

[@totlyepic]

Always love seeing Mike Pound's videos. Wish more contributors bothered with technical detail/theory.

[@adverspace]

This is one great video with one great algorithm I have a little test related to this algorithm (a verbal exam) , and this video and boosted up by confidence Thank you so much.

[@MusicalRaichu]

I was lecturing in computer graphics shortly after integral images came about, but they were called "summed-area tables" and were used for filtering images down in resolution. I think they were replaced with mip-maps but it's good to see that they made a come-back in another field.

[@hardlyb]

I just started working on image processing, and I remembered this video from years ago, and have made use of the hack he described for computing features to do something else.

[@bryan69087]

MORE MIKE POUND

[@nibblrrr7124]

[goes up close to everybody & whispers forcefully in their ears] aaaall mike pound aaaaall the tiiiiiime

[@General12th]

POUND MIKE MORE

[@flurki]

It actually is a really cool algorithm! Impressive how it's so good that it's still relevant after so many years.

[@meta7gear]

Unlike other math which is usually fleeting :P

[@poppop-oj6by]

That was some really cool perspective correction you did there!

[@setsunaes]

I always learn so much of this guy videos!

[@dripcode2600]

Love this channel! Thanks for sharing!

[@kazimafzal]

Man I loveeeee this channel and Dr. Mike Pound is bloody awesome!! Wana learn everything he knows!

[@sverre1734]

Been watching you for a while... I love your content

[@Ribby00]

Mike Pound is love

[@IceMetalPunk]

That's pretty cool! It feels a bit like dynamic programming with the way the integral image is calculated :)

[@victorherbert2728]

Cause it is dynamic programming indeed

[@AdityaBhadauria]

I've read the original paper and wasn't able to wrap my head around it completely. Thanks for doing this video.

[@Futschikatores]

And after watching this video you are now able to understand it completely? Ahem…

[@Imagonem]

It's not that complicated of an algorithm. And it's possible to use visuals to explain it, since it operates on visual data. When I say "not complicated", I'm comparing it to i.e crypto algorithms or neural networks. If you watch the Numberphile video explaining the Diffie-Hellman key exchange, they use a metaphor in which combining keys is likened to mixing coloured paint. That's obviously not what happens, but the underlying maths is very advanced, and can't be explained to a layperson in a 10 minute video clip. For the Viola-Jones algorithm, the bulk of the maths basically boils down to lots and losts of additions and subtractions. (I don't think the training part of the algorithm is quite as simple, though.).

[@fzigunov]

That's because of the greatest problem in academia... Most of them don't really have any interest or motivation to communicate. So they write unintelligible papers that are accessible only to experts through paywalls.

[@hanchesterman5661]

I love that guy and his way of explaining things

[@TheSpurion]

I really like listening to Mike Pound explaining stuff

[@dhvalden]

finally a video with Dr. Mike Pound

[@maxmusterman3371]

PLEASE MORE VIDS LIKE THIS!LUV IT

[@indianakernick3788]

That integral image thing blew my mind. It's a 3D graph of the integral of the 3D graph of a function. Wow!

[@undefBehav]

Mike Pound and explaining face detection, a match made in heaven

[@jordanfranck]

I would love to hear more about this.

[@mindgame112]

Much more videos like this please!!!

[@Furiends]

Note that this algorithm determines if a block of an image contains a face. Facial recognition goes further and takes what it knows is a face and then characterizes features that can be used as identifiers.

[@HereComesPopoBawa]

IF one starts from the presumption that each head neatly corresponds to some kind of personal identity.

[@lordbry470]

Dude. We are talking about detection here, not recognition.

[@chrischauhan1649]

This channel is heaven for students like me

[@PaulFidika]

It's crazy that an image-processing algorithm built 20 years ago is still state of the art in its category. Awesome.

[@user-lc7ku6je1o]

I liked the idea of "rectangle sums": so easy and so effective.

[@tenseikenzx-3559]

OOo, neato! using dynamic programming to calculate the blocks really fast

[@noraalosily57]

Talk about Eigenfaces! It was introduced in the 90s and still very interesting. At least students learn how to use some of the math concepts in practice like eigenvectors.

[@allhaillukeywes]

god I love those videos. the same algorithm is also used in opencv

[@iflnr978]

Thanks for the great video!

[@ulisesm.a.2770]

Excellent video, object recognition is the future.

[@baldeepbirak]

Clever technique to compute if there is a face or not.

[@greengreekloyalfan]

His hair is always so perfectly taken care of.

[@klam77]

This is really brilliant. It's an exellent explanation too. These viola jones guys did for Image proc what Thorp did for Black Jack......completely HACKED the game.

[@JakeHillion]

I played around with this method today, not really for it's intended use but to see how well it'd work for basic image location tasks. My only issue with this is how colossal the numbers are even on my relatively low resolution screen. Is this less of an issue then I'm imagining, or does this run on already shrunk down images?

[@4mathieuj]

Yay more with Mike!

[@prasadjayanti]

Really awesome !

[@dabas32]

I love this man!

[@wmd5645]

Dr. Mike. Your tests are just as hard as Dr. Steve’s, I bet. I bet endless do while loops are on your test just to confuse all the normal people.

[@shookus]

Very interesting. Thanks.

[@Mechanical1Midget]

These videos are more helpful than my hour long university lectures.

[@crabvakho]

I have no idea what's he taking about but i like to listen to stuff like that

[@speedbumphu]

How do they decide where to put these classifiers? I dont think it can be a moving window as that would be pretty slow. Also its unclear how do they decide the size of the classifiers.

[@3DSowner22]

so does it fail for faces turned sideways or digaonal to the image?

[@formelekandscreen]

Yes, its terrible when the orientation of the training set changes, the vj-algorithm does nothing the compensate. I've used this algorithm a lot in theory and practice. What you could do though, is rotate the image yourself, the vj-algorithm is fast so doing it several times over rotated images is possible.

[@4.0.4]

I never imagined how clever this was! I can only imagine this is used for more than just faces right?

[@lennartgimm]

Chrysippus Late to the party, but it is! I stumbled upin this algorithm because it was used as a base for a lunar crater algorithm. This can be used to detect basically anything, as long as you use the right filters, which you can determine using the right training set for the selection algorithm. In theory, you could use this algorithm to find horses, apples or anything else that you want.

[@danieltlang]

Would this also work with some other objects instead of faces? Like cars, etc?

[@zenawarrior3012]

I know you guys have done a bunch of videos on denial of service attacks, but I just learned of something called a low orbit ion cannon. Is that just a different name for the same type of attack?

[@100megarock]

I felt something was odd with the video. Mike was wearing a Shirt. Anyways, Great Content Guys, Keep it coming. Love Mikes way of teaching things.

[@Ehmiiz]

fascinating informative!

[@duygu_sarikaya]

Sweet series, may I ask what do you use to create the animations?

[@Computerphile]

Animations are nearly all created in Adobe After Effects (the odd 3D animation some videos created in Blender) >Sean

[@VLS-Why]

How well does this work for you different ethnicities though?

[@laurasilvalopes8929]

Amazing!

[@matts3896]

I cannot even comprehend being as intelligent as you. How does your brain not explode? You're nuts 😂😂😂 I've almost watched all your videos now, very addictive lol.

[@88bjjmichael]

Cramming for my Computer Vision Exam this afternoon 😬 At UoN

[@zss123456789]

This might be completely wrong... but I get the impression that the way they came up with the algorithm still has similarities to a simple neural network. They probably tried each simple feature on thousands of images to make sure they all pass (the "training" part), and in the end ended up with a list of tests (the second last layer in a neural network) that gives you a decision (last layer). It's incredibly quick because it doesn't need any more layers before that, and it has a fast fail mechanism.

Mike Pound is awesome!

[@Elatestnews]

Awesome

[@JBarszczu]

This guy should have his own channel

[@mrlemon592]

Could you please do a video on wireless sensor network

[@btb9001]

Do you have any sample code in C# of the Viola jones algorithms?

[@tango8894]

Mike needs his own channel

[@youssefelamrani7905]

which is better Viola-Jones or deep learning? because Viola-Jones i think needs face forward images

[@Decxcraft45]

Great video and awesome topic! Just the go pro shots are not that great, should have try to have an overhead mount. anyways great job!.

[@utkarshsingh2675]

excellent!

[@TheBitProgress]

But what about different sizes and scales? You still need to check every pixel/region in every scale. That's really slow. How do deal with it?

[@vaishnavsonawane8619]

well simplified, enjoyed it a lot, was more fascinating than even recent R CNN, R FCNN, MTCNN.. gained more respect for 2001 people 😂, and that intergral image gave feel of dynamic programming😂

[@loam]

Huh, made my diploma using similar technology (Haara classifier): the goal was to detect vehicles and classify them into 3 categories (minivans, trucks and cars) in the aerial view images (to detect vehicles from the top view). Wait... It was absolutely the same technology, now I remember xD

[@nickwoodward819]

not enough mike on this channel

[@nickscurvy8635]

this guy is very smart and good at the computers

[@bluekeybo]

So would you need to train this algorithm before using it? So how do the cameras use it, have they already trained it at the factory to set the parameters? Can you just download their parameters from somewhere and code this up yourself?

[@alpw1234]

no, you don't. if you want to use it, look for opencv library.

[@Jure1234567]

So are these the haar cascades from open cv?

[@SenorQuichotte]

He needs his own channel

[@SiddheshNan]

it just works

[@donaldasayers]

So how would you design makeup t o make face detection fail?

[@zwz.zdenek]

Go bonkers with children's face colors.

[@SeamusHarper1234]

How do they account for size and resolution?

[@zwz.zdenek]

Brute force. The tests are ordered from the most likely to disqualify a region.

[@user-pr6qf9ed7g]

great explanation of integral images!!!!

[@ScottBaietti]

How does facial recognition work, like when Facebook not only knows a face is there, but who's face it is. Granted Facebook knows other info like geotags, and who I'm most likely to be in photos with, which helps narrow down the pool to consider, but they can identify each face accurately, from photo to photo. Is the algorithm related, or completely different?

[@Swirlstudios]

I don't think that information is public, but most of those systems either use full machine learning, or a hybrid approach where they determine where a face is using this algorithm and then classify who's it is with a neural network. I'd say it's likely facebook is using a full neural network for two reasons. One, facebook doesn't have to do its face detection in real time at upwards of 15-60fps, so they can afford to be slower and more accurate. But more importantly, this algorithm is quite bad at classifying faces that are anything but white and looking straight forward. This is mostly because the training set wasn't made that well, and that may be able to be fixed, but because of this and the 1st issue, Facebook probably just finds it easier to use their own machine learning solution.

[@tyrantworm7392]

Sorry for largely OT, but they could have used something a lot faster than a 700mhz P3 in 2002. Moore's law was strong over this period and both Tualatin and AthlonXP were hitting 1.4 -1.8 ghz.

[@trucid2]

That's a Parker image 5:45.