Outline

1
Outline

• Announcements
• Syllabus
• General Introduction to Computer Vision
• Background
• Applications
• Related areas

2
Announcements

• Textbook and class materials
• There is no textbook for you to buy for this
  class (The textbook will be published in Feb.
  2001 and you can put an order from Amazon.com at
  67.00 if you wish to)
• The textbook is available online and we will use
  some chapters from it
• I will make the papers from literature either
  available from the class web page or in hardcopy

3
Announcements cont.

• About this class
• In this class, I will present methodologies and
  techniques in computer vision research with
  potential applications
• You need to participate the class discussion by
  sharing your thinking and ideas
• Attendance is required and is part of the grading

4
Announcements cont.

• Research paper option
• You need to write two research papers for this
  class
• You need to present your papers to the class
• A research paper can be a literature review of a
  particular topic or a paper that is interesting
  to you
• You need to talk to me about your topics

5
Announcements cont.

• Programming assignment option
• You need to do a project that is interesting to
  you
• I will provide you some basic functions as
  reading/writing images, filtering, and other
  functions I have
• You need to write a report about your project,
  present and demonstrate your project to the class
• You need to give me an outline of your project
  before you start working on it

6
General Introduction to Visual Perception

• Visual perception
• The process of acquiring knowledge about the
  environmental objects and events by extracting
  information from the light they emit or reflect
• Visual perception is a very complicated process,
  involving different processes such as memory
• Visual perception is the most useful source for
  information as about 50 of the brain is devoted
  to visual processing

7
Visual Pathway
8
Eye-Camera Analogy

• The eye is much like a camera
• Both form an upside-down image by admitting light
  through a variable-sized opening and focusing it
  on a two-dimensional surface using a transparent
  lens

9
Illusion
10
Illusion cont.
11
Ambiguous Figure
12
Visual Perception

• The goal of visual perception is to make
  assertions about the actual state of the
  surrounding world based on the limited and
  incomplete information encoded in the neural
  states

13
Visual Perception cont.
14
Computer Vision

• The goal is to design a computer system which
  makes inference from images or image sequences
• Produce a description of an image or an image
  sequence based on the numerical representation of
  images
• It is a very difficult problem

15
Exercise 1
16
Computer Vision Applications

• Military applications
• Automated target recognition

17
Geographic Information from Images

• An image of Washington, D.C. area

18
Medical Image Analysis

• Medical image analysis
• Characterize different types of tissues in
  medical images for automated medical image
  analysis

19
Computer Vision Applications cont.

• Civilian applications
• Biometrics
• From faces, fingerprints, iris patterns .....
• It has many applications such as ATM withdrawal,
  credit card managements .....

20
Computer Vision Applications cont.

• Iris pattern recognition http//www.cl.cam.ac.uk/u
  sers/jgd1000/iris_recognition.html
• Companies in several countries are now using
  these algorithms in a variety of products.
  Information about them can be found on the
  following websites
• Iridian Technologies, USA
• IrisAccess LG Corp, South Korea
• IrisPass OKI Electric Industries, Japan
• EyeTicket Eyeticket Corporation, USA (ticketless
  air travel)
• NCR CashPoint Machines NCR Corp, UK
• Diebold ATMs Diebold Inc., USA
• British Telecommunications, UK
• The Nationwide Building Society, UK

21
Computer Vision Applications cont.
22
Video Editing

• Blues screen technique
• Have the foreground subject video-graphed in
  front of an evenly lit monochromatic (blue or
  green) background
• Replace all the selected background in the
  picture with another background image

23
Blue Screen Editing cont.
24
Video Sequence Analysis
25
Face Recognition

• Given some examples of faces, identify a person
  under different pose, lighting, and expression
  conditions

26
Object Recognition

• Examples of the COIL database

27
Related Areas

• Computer Science
• Artificial intelligence
• Neural networks
• Pattern recognition
• Statistics
• Mathematics
• Psychology
• Physiology
• Neurophysiology

28
Grand Challenge

• Computational models that can mimic biological
  perception
• Biological systems have available through their
  senses only very limited information about the
  external word
• How can an incomplete description, encoded within
  neural states, be sufficient to direct the
  survival and successful adaptive behavior of a
  living system?