Notes
Slide Show
Outline
1
Computer Vision (CSE 455)
  • Staff





  • Web Page
    • http://www.cs.washington.edu/education/courses/cse455/08wi/
  • Handouts
    • signup sheet
    • intro slides
    • image filtering slides

2
Today
    • Intros
    • Computer vision overview
    • Course overview
    • Image processing



  • Readings for this week
    • Forsyth & Ponce, chapter 7 (in reader, available at UW Bookstore in the CSE textbook area)
    • Mortensen, Intelligent Scissors (online)
3
What is computer vision?
4
What is computer vision?
5
Every picture tells a story
  • Goal of computer vision is to write computer programs that can interpret images
6
Can computers match (or beat) human vision?
  • Yes and no (but mostly no!)
    • humans are much better at “hard” things
    • computers can be better at “easy” things
7
Human perception has its shortcomings…
8
 
9
Current state of the art
  • The next slides show some examples of what current vision systems can do


10
Earth viewers (3D modeling)
11
Photosynth
12
Optical character recognition (OCR)
13
Face detection
  • Many new digital cameras now detect faces
    • Canon, Sony, Fuji, …


14
Smile detection?
15
Object recognition (in supermarkets)
16
Face recognition
17
Vision-based biometrics
18
Login without a password…
19
Object recognition (in mobile phones)
  • This is becoming real:
    •                       Microsoft Research
    • Point & Find, Nokia
20
Special effects:  shape capture
21
Special effects:  motion capture
22
Sports
23
Smart cars
  • Mobileye
    • Vision systems currently in high-end BMW, GM, Volvo models
    • By 2010:  70% of car manufacturers.
    • Video demo
24
Vision-based interaction (and games)
25
Vision in space
26
Robotics
27
Medical imaging
28
Current state of the art
  • You just saw examples of current systems.
    • Many of these are less than 5 years old


  • This is a very active research area, and rapidly changing
    • Many new apps in the next 5 years


  • To learn more about vision applications and companies
    • David Lowe maintains an excellent overview of vision companies
      • http://www.cs.ubc.ca/spider/lowe/vision.html



29
This course
  • http://www.cs.washington.edu/education/courses/cse455/08wi/
30
Project 1:  intelligent scissors
31
Project 2:  panorama stitching
  • http://www.cs.washington.edu/education/courses/455/06wi/projects/project2/results.html


32
Project 3:  3D shape reconstruction
33
Project 4:  Face Recognition
34
Grading
  • Programming Projects (70%)
    • image scissors
    • panoramas
    • 3D shape modeling
    • face recognition
  • Midterm (15%)
  • Final (15%)
35
General Comments
  • Prerequisites—these are essential!
    • Data structures
    • A good working knowledge of C and C++ programming
      • (or willingness/time to pick it up quickly!)
    • Linear algebra
    • Vector calculus


  • Course does not assume prior imaging experience
    • computer vision, image processing, graphics, etc.