Image Processing (521H3)
Note to prospective students: this content is drawn from our database of current courses and modules. The detail does vary from year to year as our courses are constantly under review and continuously improving, but this information should give you a real flavour of what it is like to study at Sussex.
We’re currently reviewing teaching and assessment of our modules in light of the COVID-19 situation. We’ll publish the latest information as soon as possible.
Image Processing
Module 521H3
Module details for 2024/25.
15 credits
FHEQ Level 7 (Masters)
Module Outline
Image Processing provides you with an introduction to advanced image processing and computer vision topics. Computer vision is increasing used as a powerful method to enable computers to understand the world around them. It has applications in many areas including autonomous factory production, security, biomedical imaging, autonomous vehicles and robotics.
This module will introduce the concepts, starting with basic operations and finish with state-of-the-art deep learning architectures that enable computers to identify, track and understand objects in the real world. It will consist of a series of lectures and project labs. In the labs, you will learn how to solve a real world problem using Matlab’s Image Processing toolbox.
Capturing a good quality image is an important first step so you will learn about the lens optics, camera technology, and noise removal processes. You will then cover medium level processes such as edge detection, segmentation, blob analysis and colour processing. Once these have been mastered you will study the higher level subjects such pattern matching, key point descriptors and deep learning convolutional neural networks.
Module Topics:
An introduction to Image Processing and elements of Computer Vision.
Subjects Include
• Camera technologies; lenses for machine vision; image formation and resolution.
• De-noising images
• Histogram manipulations.
• Linear invariant systems in two dimensions. The discrete convolution operator.
• First and second order differential edge detection operators; edge filling techniques;
• The Hough transform.
• Scene segmentation methods and morphological operators.
• Colour transforms
• Pattern recognition techniques: shape descriptors; Fourier descriptors; template matching, SIFT
• Common classification methods for object recognition
• Examples of computer vision and image processing systems in industry.
AHEP4 Learning Outcomes
M1, M2, M3, M6, M8, M11, M12
Library
Digital image processing - Gonzalez, Rafael C., Woods, Richard E., 1992
Microscope image processing - Wu, Qiang, Merchant, Fatima Aziz, Castleman, Kenneth R., c2008
Fundamentals of Digital Image Processing - Chris Solomon, Stuart Gibson, December 21, 2007
Digital image processing: using MATLAB - Gonzalez, Rafael C., Woods, Richard E., Eddins, Steven L., c2004
Module learning outcomes
Design and critically analyse an optical camera system for capturing images and apply to processing the image for a given task.
Design and critically assess methods for the segmentation of different types of image or video stream.
Demonstrate systematic knowledge of the principles of two dimensional convolution operators and their relationship to image processing tasks.
Design and critically analyse a image processing algorithm for a given real world task.
| Type | Timing | Weighting |
|---|---|---|
| Coursework | 25.00% | |
| Coursework components. Weighted as shown below. | ||
| Software Exercise | T2 Week 11 | 100.00% |
| Computer Based Exam | Semester 2 Assessment | 75.00% |
Timing
Submission deadlines may vary for different types of assignment/groups of students.
Weighting
Coursework components (if listed) total 100% of the overall coursework weighting value.
| Term | Method | Duration | Week pattern |
|---|---|---|---|
| Spring Semester | Laboratory | 1 hour | 00111111110 |
| Spring Semester | Lecture | 2 hours | 11111111111 |
How to read the week pattern
The numbers indicate the weeks of the term and how many events take place each week.
Dr Phil Birch
Assess convenor
/profiles/97416
Please note that the 5XÉçÇøÊÓƵ will use all reasonable endeavours to deliver courses and modules in accordance with the descriptions set out here. However, the 5XÉçÇøÊÓƵ keeps its courses and modules under review with the aim of enhancing quality. Some changes may therefore be made to the form or content of courses or modules shown as part of the normal process of curriculum management.
The 5XÉçÇøÊÓƵ reserves the right to make changes to the contents or methods of delivery of, or to discontinue, merge or combine modules, if such action is reasonably considered necessary by the 5XÉçÇøÊÓƵ. If there are not sufficient student numbers to make a module viable, the 5XÉçÇøÊÓƵ reserves the right to cancel such a module. If the 5XÉçÇøÊÓƵ withdraws or discontinues a module, it will use its reasonable endeavours to provide a suitable alternative module.