COMP3204 Computer Vision
Module Overview
The challenge of computer vision is to develop a computer based system with the capabilities of the human eye-brain system. It is therefore primarily concerned with the problem of capturing and making sense of digital images. The field draws heavily on many subjects including digital image processing, artificial intelligence, computer graphics and psychology. This course will explore some of the basic principles and techniques from these areas which are currently being used in real-world computer vision systems and the research and development of new systems.
Aims and Objectives
Module Aims
- To develop the students' understanding of the basic principles and techniques of image processing and image understanding. - To develop the students' skills in the design and implementation of computer vision software.
Learning Outcomes
Knowledge and Understanding
Having successfully completed this module, you will be able to demonstrate knowledge and understanding of:
- Human and computer vision systems
- Current approaches to image formation and image modelling
- Current approaches to basic image processing and computer vision
Subject Specific Intellectual and Research Skills
Having successfully completed this module you will be able to:
- Analyse and design a range of algorithms for image processing and computer vision
- Develop and evaluate solutions to problems in computer vision
Subject Specific Practical Skills
Having successfully completed this module you will be able to:
- Implement basic image processing algorithms
Syllabus
- The human eye-brain system as a model for computer vision - Image formation: sampling theorem, Fourier transform and Fourier analysis - Image models - Basic image processing: Sampling and quantisation, Brightness and colour, Histogram operations, Filters and convolution, Frequency domain processing - Edge detection - Boundary and line extraction - Building machines that see: constraints, robustness, invariance and repeatability - Fundamentals of machine-learning: classification and clustering - Understanding covariance, eigendecomposition and PCA - Feature extraction - Interest point detection - Segmentation - 2-D Shape representation - Local features - Image matching - Large-scale image search and feature indexing - Understanding image data and performing classification and recognition - 3D vision systems - Recovering depth from multiple views - Practical examples, including: biometric systems (recognising people), industrial computer vision, etc.
Learning and Teaching
| Type | Hours |
|---|---|
| Lecture | 24 |
| Follow-up work | 12 |
| Tutorial | 12 |
| Preparation for scheduled sessions | 12 |
| Completion of assessment task | 25 |
| Revision | 10 |
| Wider reading or practice | 55 |
| Total study time | 150 |
Resources & Reading list
Gonzalez et al (2008). Digital Image Processing.
Sonka, Hlavac & Boyle (2008). Image Processing, Analysis and Machine Vision.
Nixon, M.S. and Aguado, A.S. (2012). Feature Extraction & Image Processing.
Stockman and Shapiro (2001). Computer Vision.
Assessment
Summative
| Method | Percentage contribution |
|---|---|
| Analysis | 10% |
| Coursework | 20% |
| Examination (2 hours) | 60% |
| Practical assessment | 10% |
Referral
| Method | Percentage contribution |
|---|---|
| Examination | 100% |
Repeat Information
Repeat type: Internal & External