Carlo Tomasi Computer Science VISION IN PEOPLE AND

Carlo Tomasi, Computer Science VISION IN PEOPLE AND COMPUTERS

Human Vision

Computer Vision?

Human Vision ?

Seeing is Interpretation

Seeing is Interpretation

Seeing is Interpretation

Seeing is Recognition Giuseppe Arcimboldo, 1526 -1593

Computer Vision reconstruction recognition frog, mushroom

Reconstruction: Stereo

Triangulation is Easy

Correspondence is Hard ?

It Can be Done (More or Less)

Face Recognition

Recognition: Face Space

Recognition: Face Space

Hardware HDTV video camera: 10 M pixels, uniform 30 -60 frames per second 20 Mbits per second (compressed) Variable field of view up to 1/3 of a sphere Human eye: 7 M cones in the fovea, 120 M rods 1. 2 M axons in the optic nerve 0. 6 Mbits per second (compressed) 1/3 of a sphere field of view 28 arcsec resolution (finger at 30 m)

Hardware $1 M buys you this from Dell: 1012 operations per second 1012 bytes of memory 1015 bytes of disk space 1012 bytes per second of communication [speed of light 3 x 108 m/s] One human brain gets you this: 1012 neurons 1015 synapses (connections) [speed of action potential 100 -102 m/s]

Comparing Apples and Oranges David Marr, 1945 -1980, Cambridge (UK), MIT The levels: Computational: What Algorithmic: How Mechanical: Wherewith Computational goals are the same Algorithms can be similar Brains are essentially parallel Computers are essentially sequential Mechanical substrate is different

Paying the Bills