Skip to navigation | Skip to main content | Skip to footer

Current postgraduate taught students

COMP60442: Advanced Machine Vision (2007-2008)

This is an archived syllabus from 2007-2008

Advanced Machine Vision
Level: 6
Credit rating: 15
Pre-requisites: Basic knowledge of linear algebra, basic calculus, programming experience (C/C++ or Matlab programming)
Co-requisites: No Co-requisites
Lectures: 1 day per week (5 weeks)
Lecturers: Aphrodite Galata, Chris Taylor, Neil Thacker
Course lecturers: Aphrodite Galata

Chris Taylor

Neil Thacker

Additional staff: view all staff
Sem 2 w25,29-32 Lecture 2.19 Thu 09:00 - 17:00 -
Assessment Breakdown
Exam: 0%
Coursework: 0%
Lab: 0%


This unit will give students a foundation in the subject of machine vision. This will involve gaining familiarity with algorithms for low-level and intermediate-level processing and considering the organisation of practical systems. Particular emphasis will be placed on the importance of representation in making explicit prior knowledge, control strategy and interpretting hypotheses.

This course unit treats vision as a process of inference from noisy and uncertain data and emphasizes probabilistic and statistical approaches. As such, it will also give students a foundation in the statistical methods of image analysis.

Topics covered in the course include perception of 3D scene structure from stereo; image filtering, smoothing, edge detection; segmentation and grouping; learning, recognition, and search; tracking and motion estimation; behaviour modelling.

Emphasis will also be placed on the importance of understanding algorithmic stability and optimality as a framework for algorithmic design and research methodology.

This course unit is designed for students that are interested in Computer Vision, Artificial Intelligence, or Machine Learning. This course unit is also appropriate for students with an interest in Computer Graphics.


To introduce the basic concepts and algorithmic tools of computer vision.
To introduce the problems of building practical vision systems.
To explore the role of representation and inference.
To explore the statistical processes of image understanding and develop an understanding of advanced concepts and algorithms.
To discuss novel approaches to designing vision systems that learn.
To develop skills in evaluation of algorithms for the purposes of understanding research publications in this area.

Learning Outcomes

A student completing this course unit should:
have an understanding of commmon machine vision algorithms. (A)

have a knowledge of the statistical design of algorithms. (A and B)

have a knowledge of the properties of image data and be able to solve problems about extraction of features and other quantitative information. (A and B)

be able to design basic systems for image analysis and evaluate and justify the design. (B)

be able to write a program for the analysis of image data and prepare a technical report on the evaluation of this program on suitable test data. (C)

be able to work effectively as a member of a group to prepare presenations describing complex machine vision algorithms to their peers. (D)

Assessment of Learning outcomes

Learning outcomes (1), (2) and (3) are assessed by examination,
learning outcome (4) and (5) by examination and in the laboratory and
learning outcomes (6) in tutorials.

Contribution to Programme Learning Outcomes

This course contributes to learning outcomes; A1, A2, B3, C2, D2

Reading List

All supporting material and the directed reading list can be found at

Special resources needed to complete the course unit:

The course requires access to a MATLAB toolkit including image processing course units and access to a suitable environment for web access and programming.