CS292 Computational Vision and Language

1
CS292 Computational Vision and Language

• Week 1 - 2

2
Visual Perception

• The main focus will be on the processing of the
  raw information that they provide.
• The basic approach understand how sensory
  stimuli are created by the world, and then ask
  what must the world have been like to produce
  this particular stimulus?

3
Colour image and video sequence

• colour can be conveyed by combining different
  colours of light, using three components (red,
  green and blue) R r(x,y) G g(x,y) B
  b(x,y), where R, G, B are defined in a similar
  way to F.
• The vector (r(x,y), g(x,y), b(x,y)) defines the
  intensity and colour at the point (x,y) in the
  colour image.
• A video sequence is, in effect, a time-sampled
  representation of the original moving scene.
• Each frame in the sequence is a standard colour,
  or monochrome image and can be coded as such.
• a monochrome video sequence may be represented
  digitally as a sequence o 2-D arrays F1, F2,
  F3..FN.

4
Java example on image representation and
resolution, try this in the lab class
5
Image Resolution

• How many pixels
• spatial resolution
• How many shades of grey/colours
• amplitude resolution
• How many frames per second
• temporal resolution

6
Spatial Resolution
n, n/2, n/4, n/8, n/16 and n/32 pixels per unit
length
7
amplitude resolution-Shades of Grey
8, 4, 2 and 1 bit images.
8
Temporal Resolution

• how much does an object move between frames?
• Can motion be understood unambiguously?
• Nyquists Theorem
• A periodic signal can be reconstructed if the
  sampling interval is half the period
• An object can be detected if two samples span its
  smallest dimension

9
Colour Representation

• three primaries could approximate many colours
• red, green, blue
• C rRgGbB
• Other Colour Models
• YMCK
• HSI
• YCrCb

10
Objectives of vision part

• Understand the fundamentals in machine
  perception
• Understand components in vision systems
• Be familiar with common operations for processing
  images
• Be able to implement simple image processing
  operations
• Be able to implement simple object recognition
• Evaluate a vision system
• additionally encourage the students to practise
  more basic and advanced Java programming

11
Week lectures Labs
1 Introduction and simple operations brightness, contrast, enlarge, averaging, subtraction
2 (LP) Image processing and transform 1 brightness, contrast, enlarge, averaging, subtraction
3 (LP) Image processing and transform 2 Convolution and histogram
4 (LP) Segmentation (1) segmentation
5 (LP) Classification and Recognition Object recognition
6 (LP) Reading week
7 (LP) Language 1
8 (LP) Language 2
9 (LP) Language 3
10 (LP) Language 4
11 revision

12
Deadlines

• To Undergraduate Office
• First assignment week 5,    Monday 12th Feb
  2007, 1200noon.
• Second assignment week 7,    Monday 26th Feb
  2007, 1200noon
• Third assignment week 10,  Monday 19th March
  2007, 1200noon

13
Assessment
Components of Assessment Method(s) weighting
Coursework for vision part Program results and short reports 35
Coursework for language part report 15
Examination A 2-hour examination (one question on vision, two on language) 50
14
Recommended Texts

• Nick Efford, Digital Image Processing, A
  Practical Introduction using Java (2000), Addison
  Wesley, ISBN 0201596237.
• Tim Morris (2004), Computer Vision and Image
  Processing, Palgrave MacMillan, ISBN 0333994515
• Patrick H Winston, (1992), Artificial
  Intelligence (Third Edition), Addison Wesley
  Publishers Co. ISBN 0201533774
• Rob Callan (2003), Artificial Intelligence,
  Palgrave MacMillan, ISBN 0333801369
• Linda G. Shapiro, George C. Stockman (2001),
  Computer Vision, Prentice-Hall, Inc, ISBN
  0-13-030796-3