Page 1 of 1

Module Code - Title:


Year Last Offered:


Hours Per Week:













Grading Type:


Prerequisite Modules:

Rationale and Purpose of the Module:

This module is a core module for the MSc in Artificial Intelligence. The aim is to gain a detailed insight into image formation, formats and processing.


1. Image formation: Pinhole camera, lenses, aberrations. 2. Image formats: BW, Greyscale, Colour (RGB, HSB/HSV). Image storage: lossless & lossy. 3. Point operations on images: Histograms, contrast enhancement, histogram equalization. 4. Image filtering: Linear filters, convolution, smoothing, Gaussian filters. Nonlinear filtering: median filter. 5. Finding edges: Prewitt, Sobel, Canny edge detectors. 6. Optimal binarization: Otsu thresholding. Operations on binary images. 7. Segmentation: Watershed transform. 8. Feature detection: Hough transform for lines & circles (& general shapes). 9. Finding regions of interest (corners, etc.). Harris operator. Region descriptors, region matching, image alignment. SIFT / SURF. 10. Homographies: Calculating/applying image perspective transforms.

Learning Outcomes:

Cognitive (Knowledge, Understanding, Application, Analysis, Evaluation, Synthesis)

1. Describe the major algorithms and techniques employed in machine vision systems. 2. Critique approaches to machine vision, outlining the strengths and weaknesses of common approaches. 3. Design and implement computer programs to perform low-level machine vision operations: filtering, edge-detection, thinning, photometric stereo, shape-from-shading; in a suitable computer language. 4. Design and implement computer programs to perform high-level machine-vision operations: segmentation, labeling, classification and detection; in a suitable computer language.

Affective (Attitudes and Values)

1. Given a machine vision problem, identify and defend an appropriate technique to tackle it. 2. Use an objective approach to the selection of machine vision algorithms to solve specific problems.

Psychomotor (Physical Skills)


How the Module will be Taught and what will be the Learning Experiences of the Students:

The module will be delivered using a blended learning approach using on-line lectures, labs and tutorials.

Research Findings Incorporated in to the Syllabus (If Relevant):

Prime Texts:

Gonzales & Woods (2017) Digital Image Processing , Pearson
Nixon & Aguado (2012) Feature Extraction and Image Processing for Computer Vision , Academic Press
Birchfield (2018) Image Processing and Analysis , Cengage Learning

Other Relevant Texts:

Szeliski (2011) Computer Vision: Algorithms & Applications , Springer
Sonka, Hlavac, Boyle (2015) Image Processing, Analysis & Machine Vision , Cengage Learning
Solomon & Breckon (2011) Fundamentals of Digital Image Processing , Wiley-Blackwell
Davies (2018) Computer Vision , Academic Press

Programme(s) in which this Module is Offered:

Semester - Year to be First Offered:

Module Leader: