Every image tells a story Goal of computer vision: perceive the - - PowerPoint PPT Presentation

▶
every image tells a story
SMART_READER_LITE
LIVE PREVIEW

Every image tells a story Goal of computer vision: perceive the - - PowerPoint PPT Presentation

Mar 13, 2023 476 likes •776 views

Every image tells a story Goal of computer vision: perceive the story behind the picture Compute properties of the world 3D shape Names of people or objects What happened? The goal of computer vision Can the computer

slide-1
SLIDE 1
slide-2
SLIDE 2

Every image tells a story

  • Goal of computer vision:

perceive the “story” behind the picture

  • Compute properties of

the world

– 3D shape – Names of people or

  • bjects

– What happened?

slide-3
SLIDE 3

The goal of computer vision

slide-4
SLIDE 4

Can the computer match human perception?

  • Yes and no (mainly no)

– computers can be better at “easy” things – humans are much better at “hard” things

  • But huge progress has

been made

– Especially in the last 10 years – What is considered “hard” keeps changing

slide-5
SLIDE 5

Human perception has its shortcomings

1996 , Nature Sinha and Poggio,

slide-6
SLIDE 6

But humans can tell a lot about a scene from a little information…

Source: “80 million tiny images” by Torralba, et al.

slide-7
SLIDE 7
slide-8
SLIDE 8

The goal of computer vision

slide-9
SLIDE 9

The goal of computer vision

  • Computing the 3D shape of the world
slide-10
SLIDE 10

The goal of computer vision

  • Recognizing objects and people
slide-11
SLIDE 11

slide credit: Fei-Fei, Fergus & Torralba

slide-12
SLIDE 12

sky building flag wall banner bus cars bus face street lamp

slide credit: Fei-Fei, Fergus & Torralba

slide-13
SLIDE 13

Why study computer vision?

  • Millions of images being captured all the time
  • Loads of useful applications
  • The next slides show the current state of the art
slide-14
SLIDE 14

Optical character recognition (OCR)

Digit recognition, AT&T labs / http://www.research.att.com/~yann

  • If you have a scanner, it probably came with OCR software

Source: S. Seitz

Automatic check processing Sudoku grabber

http://sudokugrab.blogspot.com/

License plate readers

http://en.wikipedia.org/wiki/Automatic _number_plate_recognition

slide-15
SLIDE 15

Face detection

  • Many new digital cameras now detect faces

– Canon, Sony, Fuji, …

Source: S. Seitz

slide-16
SLIDE 16

Face Recognition

http://developers.face.com/tools/

slide-17
SLIDE 17

Face recognition

Who is she?

Source: S. Seitz

slide-18
SLIDE 18

Vision-based biometrics

story ” Read the How the Afghan Girl was Identified by Her Iris Patterns “

Source: S. Seitz

slide-19
SLIDE 19

Login without a password…

Fingerprint scanners on many new laptops,

  • ther devices

Face recognition systems now beginning to appear more widely

http://www.sensiblevision.com/

Source: S. Seitz

slide-20
SLIDE 20

Object recognition (in supermarkets)

LaneHawk by EvolutionRobotics “A smart camera is flush-mounted in the checkout lane, continuously watching for items. When an item is detected and recognized, the cashier verifies the quantity of items that were found under the basket, and continues to close the

  • transaction. The item can remain under the basket, and with LaneHawk,you are

assured to get paid for it… “

Source: S. Seitz

slide-21
SLIDE 21

Object recognition (in mobile phones)

Source: S. Seitz

slide-22
SLIDE 22

iPhone Apps: (www.kooaba.com)

Source: S. Lazebnik

slide-23
SLIDE 23

Google Goggles

slide-24
SLIDE 24

Google Search by Image

slide-25
SLIDE 25

Leaf Recognition

slide-26
SLIDE 26

Vision-based interaction (and games)

Nintendo Wii has camera-based IR tracking built in. See Lee’s work at CMU on clever tricks on using it to create a multi-touch display! Assistive technologies

slide-27
SLIDE 27

Kinect

slide-28
SLIDE 28

Smart cars

  • Mobileye

– Vision systems currently in high-end BMW, GM, Volvo models

Sources: A. Shashua, S. Seitz