Detecting Faces (Viola Jones Algorithm) - Computerphile

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

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

excellent!

wubbubbull-out pen

what confused me is how does the algorithm know to make the rectangles sufficiently large enough to be useful for face detection? i.e., faces can be different sizes depending on distance/etc...

Cramming for my Computer Vision Exam this afternoon 😬 At UoN

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

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.

Integral images is just 2D static sum from competitive programming!

this guy is very smart and good at the computers

Really awesome !

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😂

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.

That accent, though!

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

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

Amazing!

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?

boss need your help to build real time face tracking system for institute using python

Looking forward to see a machine that scan a person to ditect its whole body. The image will then be stored...in colored & 3d.

Jared from Silicon Valley :|

Is this why people just block out the eyes in black when they don't want to be recognized in a photo? :3

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.

So are these the haar cascades from open cv?

Wal-Mart is using this at the check out lanes today.
I feel like I'm in minority report.
Being tracked every time I buy a pair of socks.

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.

Love this channel! Thanks for sharing!

man out here calling a whiteboard a blackboard

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

"Facial detection? Nah, I prefer racial detection"

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

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.

can you tell me all steps of the algorithm to implement the face detection from scratch?

Thanks for the great video!

Mike needs his own channel

His hair is always so perfectly taken care of.

could you please provide source code for this?

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

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.

great explanation of integral images!!!!

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.

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

👋🏻Greetings from MÈXICO 🇲🇽

I like the channel the only thing I don't like its phile. It really creeps me out.

Thanks Dr. but how i can get the code ... my email << qusayh43@gmail

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.

Two complications:
a) how well does such an algorithm distinguish identical twins (I know fingerprints are a better distinction)?
b) in future how will next of kin/executors unlock phones (or computers) belonging to their deceased loved ones without the biometrics?

I always learn so much of this guy videos!

This channel is heaven for students like me