Lecturer:
David Young,
room Pevensey 3 3R401 (past end of 5C corridor in Informatics), email
d.s.young@sussex.ac.uk.
Office hour Tuesday 3.00-3.50.
Tutors:
To introduce students to Computer Vision, an area of increasing importance in the technologies of robotics and human-computer interaction, and which raises computational issues not met elsewhere in our degree programmes.
To give an understanding of some of the central issues in computer vision, including its relationship to some aspects of biological vision, and to develop the skills needed to write simple applied computer vision programs using a suitable package.
Ability to program in a procedural programming language.
The course introduces the field of computer vision and its relation to research on natural vision systems. Topics include the functions of vision, early processing of images, the determination and representation of 3-D surface shape (e.g. by stereopsis), and object recognition. An introduction to a suitable software package will be given.
See below.
All lab classes are in room Pevensey 2, 5A17/18.
You have one 1-hour lab class each week on Thursday at 4 or 5 pm. See Sussex Direct for your group and time. Lab classes start in week 2.
You have one 2-hour seminar each week in Pevensey 1 2C1 on Fridays from 2.00 to 3.50, starting in week 1.
Further information is here.
The main sequence of teach files can be found by following the links
marked 
in the lecture timetable
below. If possible, look at the files in advance of the relevant
lectures.
The teach files may still contain examples in Pop-11. You should not find this a problem (they are accessed worldwide by people who do not know the language) - simply treat the Pop-11 as a kind of pseudocode, and use the text and images.
This course is assessed by coursework (50%) and unseen examination (50%).
The first part of the coursework (up to week 6) is specified here.
The second part of the coursework (due in week 10) is specified here.
The programming will be carried out in the Matlab environment; although help will be provided, you are expected to familiarize yourself with this useful tool. Click here to get going.
The course is assessed entirely by a 3.5 hour unseen examination in the summer term. Previous papers may be found here.
| Tuesday | 2.00-2.50 | JMS 1A1 | Starting week 1, 9 Jan |
| Friday | 10.00-10.50 | JMS 1A1 |
The slides used in the lectures are available online.
Click on the screen symbol 
for a version in PDF format
suitable for viewing online (using Adobe Acrobat Reader). Click on the
printer symbol 
for
a version suitable for printing, 4 slides
to a page, also in PDF format.
Links to web pages for specific lectures can be found by clicking on the
right arrows symbol .
The photographs used to illustrate general points in the first two lectures can be viewed here.
| Week | Day | No. | Topic | Slides | Links |
|---|---|---|---|---|---|
| 1 | Tue | 1 | Introduction to computer vision |
|
|
| 1 | Fri | 2 | Image formation and representation |
|
|
| 2 | Tue | 2a | Introduction to Matlab |
|
|
| 2 | Fri | 3 | Convolution and related operations |
|
|
| 3 | Tue | 4 | Smoothing, differencing and scale space |
|
|
| 3 | Fri | 5 | Edges, binary images, and regions |
|
|
| 4 | Tue | 6 | The Hough transform |
|
|
| 4 | Fri | 7 | Active contours |
|
|
| 5 | Tue | 8 | Introduction to 3-D vision |
|
|
| 5 | Fri | 9 | Stereopsis |
|
|
| 6 | Tue | 10 | Optic flow estimation |
|
|
| 6 | Fri | 11 | Optic flow interpretation |
|
|
| 7 | Tue | No lecture | |||
| 7 | Fri | Coursework part 1 feedback | |||
| 8 | Tue | 12 | Active vision |
|
|
| 8 | Fri | 13 | Object recognition and shape representation 1 |
|
|
| 9 | Tue | 14 | Object recognition and shape representation 2 |
|
|
| 9 | Fri | 15 | Issues in Computer Vision research |
|
|
| 10 | Tue | 16 | Revision class - examination questions | |
|
| 10 | Fri | No lecture |
There is no single book which covers the course. You should look for books which appeal to your own interests and approach. Additional reading, extending the framework of the lectures and teach files, will help you a great deal in the examination.
Sonka et al. is probably the best all-round introduction to straightforward machine vision. Trucco & Verri is up to date, very good, but quite mathematical. Marr is a classic text which presents one of the few attempts to outline a general theory of vision. The chapter in Sharples et al. is a practical introduction, but is limited in scope. Bruce & Greenis a useful and interesting book for those who are as interested in natural vision as in machine vision, but does not deal with many important computational techniques.
Callan, R. (2003) Artificial Intelligence. Basingstoke: Palgrave Macmillan. Chapter 21.
Charniak E. & McDermott D. (1985) Introduction to Artificial Intelligence. Reading, MA: Addison-Wesley. [QZ 1240 Cha]. Chapter 3.
Fischler M.A. & Firschein O. (1987) The Eye, the Brain, and the Computer. Reading, MA: Addison-Wesley. [QZ 1250 Fis]
Hunt B.R., Lipsman R.L. & Rosenberg J.M. (2001) A Guide to Matlab for Beginners and Experienced Users. Cambridge: CUP.
Mayhew J. & Frisby J. (1984) Computer vision. In T. O Shea & M. Eisenstadt (Eds.), Artificial Intelligence: Tools, Techniques and Applications (pp. 301-357) New York: Harper & Row. [QZ 1240 Art]
Sharples M., Hogg D., Hutchison C., Torrance S. & Young D. (1989) Computers and Thought: An Introduction to Cognitive Science and Artificial Intelligence. MIT Press - Bradford Books. [QZ 1250 Com]. Chapter 9.
Winston P.H. (1981) Artificial Intelligence (2nd ed.) Reading, MA: Addison-Wesley. [QZ 1240 Win]. Chapter 3.
Boyle R.D. & Thomas R.C. (1988) Computer Vision: A First Course. Oxford: Blackwell Scientific. [TA 1632 Boy]
Frisby J.P. (1979) Seeing: Illusion, Brain and Mind. Oxford: Oxford University Press. [QZ 314 Fri]
Gonzalez R.C., Woods R.E. & Eddins S.L. (2004) Digital Image Processing Using Matlab. Upper Saddle River, NJ: Pearson.
Marr D. (1982) Vision: a Computational Investigation into the Human Representation and Processing of Visual Information. San Francisco: W.H. Freeman. [QZ 1240 Mar]
Morris T. (2004) Computer Vision and Image Processing Basingstoke: Palgrave Macmillan
Nalwa V.S. (1993) A Guided Tour of Computer Vision. Reading, MA: Addison-Wesley. [QE 1880 Nal]
Shapiro L.G. & Stockman G.C. (2001) Computer Vision. London etc.: Prentice Hall
Sonka M., Hlavac V. & Boyle R. (1993) Image Processing, Analysis and Machine Vision. London: Chapman & Hall Computing. [TA 1632 Son]
Trucco E. & Verri A. (1998) Introductory Techniques for 3-D Computer Vision. Upper Saddle River NJ: Prentice Hall. [TA 1634 Tru]
Aloimonos Y. (1993) (Ed.) Active Perception. Hillsdale NJ: Lawrence Erlbaum. [TA 1634 Alo]
Ballard D.H. & Brown C.M. (1982) Computer Vision. Englewood Cliffs, NJ: Prentice-Hall. [QZ 314 Bal]
Blake A. & Yuille A. (1992) (Eds.) Active Vision. Cambridge, MA: MIT Press. [TA 1632 Act]
Brady, M. (1981) (Ed.) Computer Vision. Amsterdam: North-Holland. [QZ 1240 Art]
Brown C.M. (1988) (Ed.) Advances in Computer Vision (2 Vols) Hillsdale, NJ: Lawrence Erlbaum. [QE 1 Adv]
Fischler M.A. & Firschein O. (1987) (Eds.) Readings in Computer Vision: Issues, Problems, Principles and Paradigms. Los Altos, CA: Morgan-Kaufmann. [TA 1632 Rea]
Forsyth D.A. & Ponce J. (2003) Computer Vision: A Modern Approach. Upper Saddle River, NJ: Pearson Education.
Gibson J.J. (1966) The Senses Considered as Perceptual Systems. Boston: Houghton Mifflin. [QZ 310 Gib]
Gibson J.J. (1979) The Ecological Approach to Visual Perception. Boston: Houghton Mifflin. [QZ 314 Gib]
Gonzalez R.C. & Woods R.E. (1992) Digital Image Processing. Reading, MA: Addison Wesley. [QE 1890 Gon]
Haralick R.M. & Shapiro L.G. (1992) Computer and Robot Vision (2 Vols) Reading, MA: Addison-Wesley. [TA 1632 Har]
Horn B.K.P. (1986) Robot Vision. Cambridge MA: MIT Press. [TJ 211.3 Hor]
Pentland A.P. (1986) (Ed.) From Pixels to Predicates: Recent Advances in Computational and Robotic Vision. Norwood NJ: Ablex. [TA 1632 Fro]
Richards W. & Ullman S. (1987) (Eds.) Image Understanding 1985-86. Norwood NJ: Ablex. [QZ 1390 Ima]