CT6057 - Computer Vision (2025/26)
| Module specification | Module approved to run in 2025/26 | ||||||||||||
| Module title | Computer Vision | ||||||||||||
| Module level | Honours (06) | ||||||||||||
| Credit rating for module | 15 | ||||||||||||
| School | School of Computing and Digital Media | ||||||||||||
| Total study hours | 150 | ||||||||||||
|
|||||||||||||
| Assessment components |
|
||||||||||||
| Running in 2025/26(Please note that module timeslots are subject to change) |
|
Module summary
Computer vision is widely used across industries to automate processes, enhance efficiency, and improve decision-making. In healthcare, it plays a crucial role in medical imaging diagnostics, while in the automotive industry, it powers self-driving cars by enabling object detection and navigation. Manufacturing relies on computer vision for quality control, ensuring consistency and defect detection in production lines, while retail leverages it for cashier-less stores and customer analytics. Additionally, robotics heavily depends on computer vision for navigation, object recognition, and task automation in warehouses, factories, and even space exploration. By enabling intelligent automation and real-time analysis, computer vision continues to transform various industries.
This module aims to equip students with the knowledge and skills to analyse, design, and develop image processing algorithms commonly used in commercial computer vision systems. It covers fundamental principles, mathematical foundations, algorithmic implementations, and practical configurations of computer vision technology. Upon successful completion, students will be able to professionally evaluate the key components of computer vision systems and apply their knowledge to real-world applications.
Syllabus
Introduction to human, machine and computer vision
Image formation, representation and properties
image file formats
Image pre-processing and mathematical operations
Image segmentation
Shapes, objects and texture for computer vision
Multiple images and stereo vision
Critical reflection on a set of computer vision algorithms, tools, techniques and/or applications
Programming environment or IDE (Integrated Development Environment) (e.g. Matlab, Java, Python) and associated accessories for computer vision
Coding skills and documentation
Balance of independent study and scheduled teaching activity
Students will develop thorough understanding of fundamental theory and underlying mathematics behind the image processing algorithms of computer vision systems through schedule lectures and guided independent learning aided with recommended reading list.
The laboratory sessions/ supervised workshops are provided to support students in gaining practical experience in effective use of professional programming environment or IDE (Integrated Development Environment) and associated accessories in implementing algorithmic solutions for computer vision systems.
Appropriate blended learning approaches and technologies such as the University’s VLE (WebLearn), library resources, CPED (Centre for Professional and Educational Development) and specialised laboratory resources will be used to facilitate and support student learning to:
• deliver content;
• encourage active learning;
• impart soft skills
• provide formative and summative assessments with appropriate and timely feedback;
• enhance student engagement and learning experience.
Students are encouraged to keep reflective commentaries on their weekly learning activities and tasks carried out during scheduled learning and teaching as well as during guided independent learning.
Students are expected and encouraged to work individually as well as in groups to complete their laboratory exercises and group essay.
Students have opportunity of (i) quick consultation with the module leader during his/her office hours; and (ii) booking one to one session with academic mentor(s).
Learning outcomes
On successful completion of this module students should be able to:
LO1. Demonstrate a thorough understanding of the fundamental theories, underlying mathematics, and image processing algorithms of computer vision systems, alongside their practical applications in algorithmic solutions.
LO2. Critically analyse and reflect on selected algorithms, tools, techniques, or applications governing computer vision systems, working collaboratively in teams to evaluate environmental and societal impacts and propose solutions to minimize adverse effects.
LO3. Utilize professional programming environments or IDEs and apply appropriate computational and analytical techniques to model complex problems, mitigate vulnerability risks, and implement effective algorithmic solutions while recognizing technique limitations.
LO4. Exhibit professional commitment as an entry-level systems engineering graduate by employing resource-optimized coding, quality documentation, risk assessment, and ethical computer practices.