School of Computer Science

Module 06-19339 (2012)

Computational Vision

Level 2/I

Hamid Dehghani Semester 2 10 credits
Co-ordinator: Hamid Dehghani
Reviewer: Ales Leonardis

The Module Description is a strict subset of this Syllabus Page.

Aims

The aims of this module are to:

  • provide a general introduction to computer vision
  • give an overview of computational models of visual processing in animals
  • introduce a number of different frameworks and representations for vision
  • familiarise the student with a number of techniques and algorithms in computer vision
  • provide a foundation for further study in the area of computer vision

Learning Outcomes

On successful completion of this module, the student should be able to:

  • make informed choices about which sort of algorithms to apply to solve specific problems
  • use standard vision libraries or software to construct working vision systems
  • apply algorithms to simplified problems by hand
  • discuss the advantages and drawbacks of different methods, explaining their working

Teaching methods

2 hrs lectures per week, 1 hr lab/exercise class


Assessment

  • Sessional: 1.5 hr examination (70%), continuous assessment (30%).
  • Supplementary: By examination only.

Detailed Syllabus

  1. Taught topics include (but are not limited to):
    • Introduction to Computational and Human Vision
    • Human Vision
    • Edge Detection
    • Noise Filtering
    • Hough Transform
    • ROC Analysis
    • Motion
    • Feature Detection
    • Cross Correlation
    • Face Recognition
    • Objecct Recognition
  2. Laboratory Excercises:
    • Matlab Tutorial
    • Edge Detection
    • Noise Filtering
    • Hough Transform
    • Eigenfaces

Programmes containing this module