ACS6123 Intelligent and Vision Systems

Module Description (subject to change)

Recent developments in intelligent and vision systems propose to revolutionise the way we tackle and solve complex real-world challenges associated with modelling, control and optimisation for a variety of applications, e.g. security, transportation systems, robotics and medicine. In turn approaches for developing intelligent and vision systems have seen their capabilities being challenged by such applications in terms of robustness and their ability to deal with uncertainties. It is worth noting that the word intelligent here refers to the concept of ‘machine learning’ whereby the associated structures are ‘learning’, ‘adaptive’, ‘flexible’, and ‘generalising’. Machine vision and the corresponding algorithms have enabled systems to be more autonomous and as a result they paved the way to even more synergies to be formed with other paradigms, e.g. machine learning paradigms. In this module students will experience the machine-learning/vision synergy and learn about state-of-the-art concepts in intelligent and vision systems from the underlying theory through to solving complex open-ended problems and how to evaluate the performance improvements gained from these approaches.

Credits: 15 (Spring semester)

Module Leader

Lyudmila Mihaylova

Professor Lyudmila Mihaylova

Amy Johnson Building

If you have any questions about the module please talk to me during the lectures or the labs in the first instance. It is likely that other students will learn from any questions you ask as well, so don’t be afraid to ask questions.

Outside of lectures please contact me via email, or drop in to see me.

Other teaching staff

Professor Mahdi MahfoufProfessor Mahdi Mahfouf

Learning Outcomes

Learning Outcomes

By the end of the module students will be able to:

  1. Explain the importance of and need for intelligent and vision systems in a wide range of industrial and research applications, the relative merits and limitations of adopting such systems compared to other state-of-the-art solutions [US1,E4];
  2. Describe and explain the main components, architectures and design issues in developing intelligent and machine vision systems and future technological challenges and opportunities [USm,US2, Em2];
  3. Explain and apply the various methodologies and be able to compare them with conventional tools of processing [US2m,E1, E1m];
  4. Select and use appropriate architectures, algorithmic, computational and experimental tools (including those from the research literature) to provide innovative solutions to complex, unfamiliar, open-ended intelligent and machine vision systems subject to a variety of technological constraints [US3,E3];
  5. Demonstrate creative and critical thinking in providing and evaluating solutions to complex intelligent and vision systems and effectively communicate and analyse such solutions [E4, E5];
  6. Effectively present appropriate design methodology, analysis and critical evaluation of solutions and any limitations and constraints of such solutions in the form of a technical report to a standard that a suitably qualified person could follow and use to obtain similar findings [E4, E5].


  • Image and video processing goals, its applications to intelligent systems.
  • Image formation in the eye and in the video camera.
  • Common image features: colour, edges, texture and shape.
  • Colour histogram, pixel point processing.
  • Multi-image pixel point processing.
  • Image segmentation.
  • Image analysis.
  • Image synthesis.
  • Optical flow.
  • Methods for automatic object detection in video sequences.
  • Object tracking in video.
  • Augmented and virtual reality.
  • Fuzzy representation of uncertainty.
  • Classical sets and fuzzy sets.
  • Properties of classical and fuzzy sets.
  • Classical and fuzzy relations - cardinality, operations, properties.
  • Membership functions and value assignments.
  • Conversion of fuzzy to crisp relations and defuzzification methods.
  • Classical and fuzzy logic. Approximate reasoning.
  • Fuzzy rule-based systems.
  • Fuzzy decision-making.
  • Fuzzy pattern recognition via fuzzy clustering techniques.
  • Fuzzy predictive modelling and system identification, fuzzy control systems, neural-fuzzy systems, Self-Organising Fuzzy Control (SOFLC), genetic-based fuzzy systems.

Teaching Methods

Learning and Teaching Methods

The module will be taught through a combination of lectures, tutorial classes and laboratory sessions. The lectures will be used to teach the main research and industrial motivations, theoretical background and technical concepts of topics in intelligent and vision systems (learning outcomes 1-3, 5). Tutorial and laboratory classes will be used to develop the students’ confidence and skills in using appropriate computational and experimental tools for solving problems in intelligent and vision systems including understanding the limitations of such solutions (learning outcomes 3, 4). Students will undertake two open ended design tasks to provide solutions to intelligent and machine vision problems from industry and/or research (learning outcomes 3-5).

  • Lectures: 30 hours
  • Tutorials: 6 hours
  • Laboratories: 6 hours
  • Independent Study: 106 hours
Teaching Materials

Learning and Teaching Materials

All required materials will be available via Blackboard (MOLE).



The module will be assessed by:

  1. A 2 hour exam worth 60% assessing in depth knowledge of motivations, theoretical background and technical concepts of topics in intelligent and machine vision systems.
  2. Assignment: Computer Vision (40%)

Students will have the opportunity to resit. The module resit mark will be based on the resit exam plus the original assignment marks.



You will have an opportunity to view marked Exam Scripts once Exam results have been confirmed by the Faculty and released to students. The date of this Review session will be announced by the Departmental Office.

You will be able to look at the exam paper and a sample solution on the Blackboard (MOLE) page for this module. The paper and solution will be available after the exam period.

Student Evaluation

Student Evaluation

The department has a standard procedure for collecting student feedback on every taught module and communicating the results and staff comments back to the students.

You can view the latest Department response to the survey feedback here.

Recommended Reading

Recommended Reading

  • R. Gonzalez, R. Woods, S. Eddins: Digital Image Processing Using Matlab, Pearson Prentice Hall, 2009.
  • D.A. Forsyth and J. Ponce, Computer Vision: A Modern Approach, Second Edition, Prentice Hall, 2012
  • T. Bowmans, Traditional and Recent Approaches in Background Modeling for Foreground Detection: An Overview, Computer Science Review, Vol. 11, May 2014, pp. 31-66
  • T. Ross, Fuzzy Logic with Engineering Applications, 3rd Edition, Wiley, 2010
  • S. S. Farinwata, D. Filev, R. Langari: Fuzzy control, Wiley, 2000
  • B. Kosko: Fuzzy Engineering, Prentice Hall, 1997