Course coordinator
Dr Shreya Ghosh
Course overview
- Study period
- Semester 1, 2026 (23/02/2026 - 20/06/2026)
- Study level
- Undergraduate
- Location
- St Lucia
- Attendance mode
- In Person
- Units
- 2
- Administrative campus
- St Lucia
- Coordinating unit
- Elec Engineering & Comp Science School
Image sensors, colour models, discrete cosine transform, image & video compression. Computer vision, morphological techniques, watershed transform, skeletonisation, image segmentation, active contours.
The course is divided into two segments. The first segment focuses on fundamental Image Processing and traditional Video Computer Vision techniques and applications. The ultimate goal of Computer Vision is to enable computers to extract high-level information from the world through images, similarly to how humans perceive and interpret visual information. The second segment covers some of the remarkable advancements in recent years related to the advent of Deep Neural techniques.
The course delivery is designed to be hands-on and practical, with students required to implement algorithms using either Matlab or Python to demonstrate their comprehension of the course material. Additionally, the course highlights the research strengths in Image Processing and Computer Vision at the University of Queensland, including areas such as Digital Pathology and Robust Face Recognition.
Course requirements
Prerequisites
You'll need to complete the following courses before enrolling in this one:
ELEC3004
Incompatible
You can't enrol in this course if you've already completed the following:
ELEC3601 or ELEC4600 or ELEC7463 or ELEC7602 or ELEC7608
Course contact
Course staff
Lecturer
Dr Shreya Ghosh
Dr Lei Guo
Timetable
The timetable for this course is available on the UQ Public Timetable.
Aims and outcomes
It is expected that upon successful completion of the course, students will have developed the ability to code and understand advanced image processing and computer vision algorithms. The ability to code image processing and computer vision programs reinforces a solid understanding of the algorithms and gives the student a solid skill base for their future career.
Learning outcomes
After successfully completing this course you should be able to:
LO1.
Demonstrate practical skills in implementing real-time image processing and computer vision systems in Matlab - Application
LO2.
Apply your theoretical framework to understand new developments in image processing and computer vision - Analysis Level
LO3.
Apply your problem solving skills in image processing and computer vision through an emphasis on practical usage, rather than mere discussion of algorithms - Analysis Level
LO4.
Demonstrate solid understanding of the theory through coding and implementation of image processing and computer vision algorithms in Matlab - Synthesis Level
LO5.
Demonstrate an international perspective on the field through the advanced topics delivered by guest lecturers and recognized researchers - Evaluation Level
LO6.
Demonstrate the ability to solve classification and other Computer Vision problems with Deep Learning techniques.
Assessment
Assessment summary
| Category | Assessment task | Weight | Due date |
|---|---|---|---|
| Computer Code, Essay/ Critique, Tutorial/ Problem Set |
Assignment 1 - Computer Vision
|
20% |
20/03/2026 4:00 pm |
| Computer Code, Essay/ Critique, Tutorial/ Problem Set |
Assignment 2 - Computer Vision and Deep Learning
|
20% |
17/04/2026 4:00 pm |
| Computer Code, Essay/ Critique, Tutorial/ Problem Set |
Assignment 3 - Computer Vision and Deep Learning
|
20% |
15/05/2026 4:00 pm |
| Examination |
Final Exam
|
40% |
End of Semester Exam Period 6/06/2026 - 20/06/2026 |
A hurdle is an assessment requirement that must be satisfied in order to receive a specific grade for the course. Check the assessment details for more information about hurdle requirements.
Assessment details
Assignment 1 - Computer Vision
- Mode
- Written
- Category
- Computer Code, Essay/ Critique, Tutorial/ Problem Set
- Weight
- 20%
- Due date
20/03/2026 4:00 pm
- Other conditions
- Student specific.
- Learning outcomes
- L01, L03, L04, L06
Task description
A Computer Vision and Image Processing assignment. See Blackboard for details.
This task has been designed to be challenging, authentic and complex. Whilst students may use AI and/or MT technologies, successful completion of assessment in this course will require students to critically engage in specific contexts and tasks for which artificial intelligence will provide only limited support and guidance. A failure to reference generative AI or MT use may constitute student misconduct under the Student Code of Conduct. To pass this assessment, students will be required to demonstrate detailed comprehension of their written submission independent of AI and MT tool.
Submission guidelines
Upload via Blackboard.
Deferral or extension
You may be able to apply for an extension.
The maximum extension allowed is 7 days. Extensions are given in multiples of 24 hours.
Extensions are limited to 7 days as feedback will be provided within 14 days.
Late submission
A penalty of 10% of the maximum possible mark will be deducted per 24 hours from time submission is due for up to 7 days. After 7 days, you will receive a mark of 0.
Assignment 2 - Computer Vision and Deep Learning
- Mode
- Written
- Category
- Computer Code, Essay/ Critique, Tutorial/ Problem Set
- Weight
- 20%
- Due date
17/04/2026 4:00 pm
- Other conditions
- Student specific.
- Learning outcomes
- L01, L03, L04, L06
Task description
Computer Vision and Deep Learning assignment. See Blackboard for details.
This task has been designed to be challenging, authentic and complex. Whilst students may use AI and/or MT technologies, successful completion of assessment in this course will require students to critically engage in specific contexts and tasks for which artificial intelligence will provide only limited support and guidance. A failure to reference generative AI or MT use may constitute student misconduct under the Student Code of Conduct. To pass this assessment, students will be required to demonstrate detailed comprehension of their written submission independent of AI and MT tool.
Submission guidelines
Upload to Blackboard.
Deferral or extension
You may be able to apply for an extension.
The maximum extension allowed is 7 days. Extensions are given in multiples of 24 hours.
Extensions are limited to 7 days as feedback will be provided within 14 days.
Late submission
A penalty of 10% of the maximum possible mark will be deducted per 24 hours from time submission is due for up to 7 days. After 7 days, you will receive a mark of 0.
Assignment 3 - Computer Vision and Deep Learning
- Mode
- Written
- Category
- Computer Code, Essay/ Critique, Tutorial/ Problem Set
- Weight
- 20%
- Due date
15/05/2026 4:00 pm
- Other conditions
- Student specific.
- Learning outcomes
- L01, L02, L03, L04, L05, L06
Task description
Computer Vision and Deep Learning assignment. See Blackboard for details.
This task has been designed to be challenging, authentic and complex. Whilst students may use AI and/or MT technologies, successful completion of assessment in this course will require students to critically engage in specific contexts and tasks for which artificial intelligence will provide only limited support and guidance. A failure to reference generative AI or MT use may constitute student misconduct under the Student Code of Conduct. To pass this assessment, students will be required to demonstrate detailed comprehension of their written submission independent of AI and MT tool.
Submission guidelines
Upload to Blackboard.
Deferral or extension
You may be able to apply for an extension.
The maximum extension allowed is 28 days. Extensions are given in multiples of 24 hours.
Late submission
A penalty of 10% of the maximum possible mark will be deducted per 24 hours from time submission is due for up to 7 days. After 7 days, you will receive a mark of 0.
Final Exam
- Hurdle
- Identity Verified
- In-person
- Mode
- Written
- Category
- Examination
- Weight
- 40%
- Due date
End of Semester Exam Period
6/06/2026 - 20/06/2026
- Other conditions
- Time limited, Secure.
- Learning outcomes
- L02, L03, L06
Task description
The final end-of-semester exam will test understanding of the concepts covered over the entire course. The exam will be an invigilated on-campus exam that meets the identity verified assessment requirement. The format will be Multiple-choice and Short answer. It is closed book exam.
This assessment task is to be completed in-person. The use of generative Artificial Intelligence (AI) or Machine Translation (MT) tools will not be permitted. Any attempted use of AI or MT may constitute student misconduct under the Student Code of Conduct.
Hurdle requirements
Students must achieve at least 40% on the final exam to pass the course.Exam details
| Planning time | 10 minutes |
|---|---|
| Duration | 120 minutes |
| Calculator options | Any calculator permitted |
| Open/closed book | Closed book examination - no written materials permitted |
| Exam platform | Paper based |
| Invigilation | Invigilated in person |
Submission guidelines
Deferral or extension
You may be able to defer this exam.
Course grading
Full criteria for each grade is available in the Assessment Procedure.
| Grade | Cut off Percent | Description |
|---|---|---|
| 1 (Low Fail) | 0 - 19 |
Absence of evidence of achievement of course learning outcomes. |
| 2 (Fail) | 20 - 46 |
Minimal evidence of achievement of course learning outcomes. |
| 3 (Marginal Fail) | 47 - 49 |
Demonstrated evidence of developing achievement of course learning outcomes |
| 4 (Pass) | 50 - 64 |
Demonstrated evidence of functional achievement of course learning outcomes. |
| 5 (Credit) | 65 - 74 |
Demonstrated evidence of proficient achievement of course learning outcomes. |
| 6 (Distinction) | 75 - 84 |
Demonstrated evidence of advanced achievement of course learning outcomes. |
| 7 (High Distinction) | 85 - 100 |
Demonstrated evidence of exceptional achievement of course learning outcomes. |
Additional course grading information
Students must achieve at least 40% on the final exam to pass the course. The final mark will be rounded before grading.
Final Marks (100%) = Assignment 1 (20%) + Assignment 2 (20%) + Assignment 3 (20%) + Final exam (40%)
Supplementary assessment
Supplementary assessment is available for this course.
Additional assessment information
Use of Generative AI Tools
This course is aimed at students understanding and being able to effectively apply Computer vision and Deep Learning concepts to different and novel contexts.
Assessment in this course have been designed to be challenging, authentic and complex. Whilst students may use Generative AI technologies in some assessments, successful completion of assessment in this course will require students to critically engage in specific contexts and tasks for which artificial intelligence will provide only limited support and guidance. Generative AI Tools and techniques may be utilized as supportive elements. However, there are boundaries to your usage of Generative AI Tools. Going beyond those boundaries amounts to an academic integrity issue. Further, you will need to acknowledge your use of Generative AI tools in each assessment where you are permitted to use those tools (see below for more information on what is required for these acknowledgements). Failure to appropriately and completely acknowledge your use of Generative AI tools in an assessment also amounts to an academic integrity issue.
It is essential to recognise that the primary objectives of this course and the assessment that you will complete is for you to demonstrate your achievement of the learning objectives outlined in section 2.2 above as well as UQ’s Graduate Attributes as are relevant to this course.
Having Troubles?
If you are having difficulties with any aspect of the course material, you should seek help and speak to the course teaching staff.
If external circumstances are affecting your ability to work on the course, you should seek help as soon as possible. The University and UQ Union have organisations and staff who are able to help; for example, UQ Student Services are able to help with study and exam skills, tertiary learning skills, writing skills, financial assistance, personal issues, and disability services (among other things).
Complaints and criticisms should be directed in the first instance to the course coordinator. If you are not satisfied with the outcome, you may bring the matter to the attention of the School of EECS Director of Teaching and Learning.
Learning resources
You'll need the following resources to successfully complete the course. We've indicated below if you need a personal copy of the reading materials or your own item.
Library resources
Library resources are available on the UQ Library website.
Additional learning resources information
Suggested Reading:
Deep Learning with Python, Second Edition By: Francois Chollet
Published: 21st December 2021, ISBN: 9781617296864, Number Of Pages: 400
Kindle Edition is fine
Deep Learning for Coders with fastai and PyTorch: AI Applications Without a PhD by: Jeremy Howard and Sylvain Gugger.
Publisher : O'Reilly Media, Inc, USA (18 August 2020)
Kindle Edition is fine
Understanding Deep Learning Hardcover – 3 January 2024 by Simon J.D. Prince (Author)
Publisher : MIT Press (3 January 2024)
Kindle Edition is fine
Learning activities
The learning activities for this course are outlined below. Learn more about the learning outcomes that apply to this course.
Filter activity type by
Please select
| Learning period | Activity type | Topic |
|---|---|---|
Multiple weeks From Week 1 To Week 13 |
Lecture |
Lecture Series Covers required information on Computer Vision and Image Processing Learning outcomes: L01, L02, L03, L04, L05, L06 |
Multiple weeks From Week 2 To Week 13 |
IT Computing |
Practical in Computer Laboratory Coding solutions in MATLAB or Python to demonstrate understanding of the lecture material. Learning outcomes: L01, L02, L03, L04, L06 |
Policies and procedures
University policies and procedures apply to all aspects of student life. As a UQ student, you must comply with University-wide and program-specific requirements, including the:
- Student Code of Conduct Policy
- Student Integrity and Misconduct Policy and Procedure
- Assessment Procedure
- Examinations Procedure
- Reasonable Adjustments for Students Policy and Procedure
- AI for Assessment Guide
Learn more about UQ policies on my.UQ and the Policy and Procedure Library.
School guidelines
Your school has additional guidelines you'll need to follow for this course: