Share it with your friends Like

Thanks! Share it with your friends!

Close

MIT 6.034 Artificial Intelligence, Fall 2010
View the complete course: http://ocw.mit.edu/6-034F10
Instructor: Patrick Winston

We consider how object recognition has evolved over the past 30 years. In alignment theory, 2-D projections are used to determine whether an additional picture is of the same object. To recognize faces, we use intermediate-sized features and correlation.

License: Creative Commons BY-NC-SA
More information at http://ocw.mit.edu/terms
More courses at http://ocw.mit.edu

Buy/Stream:

Comments

E M says:

Nice view 0:30 1:17 showing us the professor instead of the material he shows to his students

Цветомир Цветков says:

Boom! Tetris for Jeff!

0 1 says:

Wish the professor could expand the binary mask technique (for finding correlation) to higher dimensions and to non-binary cases.

Clinical Neuropsychology says:

thank you for sharing.

jasdeep singh Grover says:

I am just a B Tech first year student…. just a small query…. if we have orthographic projections… we take views from mutually perpendicular directions… if my coordinate system is set with axis parallel to our viewing direction then won't the computation be much easier…. view along x axis and view along y axis will always have same z coordinate and that along x and Z would have same y coordinate… so won't these condition actually give the object in 3d(I mean a 3 dimensional array with known XYZ coordinate of all vertices)… later then we can rotate and check if we can generate similar 2d images from 3d view?)….

q zorn says:

very interesting, now back to my RPi3 and opencv AI logic. thanks.

D. Refaeli says:

Can anybody explain why, in the projections, he subtracts the Ys*Sin(theta) instead of adding it? If we are in a vector space, subtracting Ys*Sin(theta) would mean our new point is going to be down and under our current point, and not up and above like it is shown on the graph… Did he make a mistake or did I just missed something?

Mesut Pişkin says:

this lesson it's great. I think teacher is very tired 🙂

mathIsART says:

The problem of recognizing which verbs are happening in a picture is now (partially) solved by researchers at Facebook, right? Did anyone see the demo where you ask the program if some verb is happening in a picture, and the program will reply yes/no?

Musa Yusuf says:

Yes! I'm a Muslim and a staunch opponent of Western values. But I'm hereby confessing, recognising and acknowledging the good product and personalities of the west. To me, this guy is one of the most valuable people on the face of the planet. May Allah forgive him and guide him.

Jeremy Lakey says:

Interesting!  The faces are easy to recognize when they're upside down or noisy, but not both.  It seems that our brains rely on lower-level features specific to the individual face to recognize the faces when they're upside and higher-level specific features to recognize the face if the photo is noisy but right-side-up.

What I'm saying is that there is BOTH low-level and high-level features inside our brains that specifically identify Bill Clinton.

Plugtree says:

Patrick Winston put his face for computer recognition by artificial intelligence. The machine did the job. But only humans can recognize and appreciate his incredible teaching skills. Thanks Patrick #LearnAIforFun #AI #MIT

Write a comment

*

DARPA SUPERHIT 2021 Play Now!Close

DARPA SUPERHIT 2021

(StoneBridge Mix)

Play Now!

×