|
| Module Availability |
Autumn Semester |
|
|
| Assessment Pattern |
|
Components of Assessment
|
Method(s)
|
Percentage Weighting
|
|
Examinations
|
2 hour unseen paper.
|
85%
|
|
Lab Report
|
Answer all questions in the lab specification
|
15%
|
|
Part-time Students
|
No need to do the Lab Report. Examination counts for 100%
|
100%
|
Qualifying Condition(s)
A weighted aggregate mark of 50% is required to pass the module |
|
|
| Module Overview |
|
This course offers an introduction to image processing and computer vision for those interested in the science and technology of machines that see. It provides background and the theory for building artificial systems that manipulate videos and images and alter or analyse their information content.
|
|
|
|
| Prerequisites/Co-requisites |
None |
|
|
| Module Aims |
The aim of this module is to offer an in depth course on the principles of Image Processing and Computer Vision which form the foundation for a variety of disciplines like Digital Photography, Robot Vision, Remote Sensing, Medical Imaging, Digital Broadcast, Image and Video Archiving, Multimedia Technologies etc. |
|
|
| Learning Outcomes |
By the end of the module students will:
* have a systematic understanding of Image Processing issues
* be able to formulate problems in image processing in a Mathematical way and solve them to achieve optimality in performance.
* will be able to analyse complex problems in image processing and computer vision, understand the concepts behind them and come up with possible algorithmic solutions.
|
|
|
| Module Content |
|
[1-2] Introduction - Definition of an image, digitisation, criteria for sampling and quantisation.
[3-6] Human Vision System - Physiology of the human vision system. Psychophysical experiments, results and implications. Visual perception, Dichromatic reflection model, Colour.
[7-9] Image Transformations - Matrix and vector representation of images. Orthonormal bases. Linear operators. 2D transforms. Singular Value Decomposition of matrices. 2D Finite Fourier, Walsh, Hadamard and Haar transforms. Karhunen-Loeve transform and principal component analysis.
[10-12] Image Enhancement - Histogram modification. Smoothing. Sharpening. Other enhancement filters.
[13-15] Image scale space representation - basic scale-space theory, Gaussian kernel and its derivatives, scale-space pyramids, interpolation.
[16-18] Geometry of Vision - Camera model. Homogenous coordinates. Geometric image transformations. Camera calibration, Stereo Vision.
[19-21] Feature Detection - Basic image structures. Feature detection algorithms. Image descriptors. Similarity measures.
[22-24] 2D pattern representation. Hough transform. Shape detection. Matching algorithms. RANSAC. Registration and Image Restoration.
[25-27] Segmentation – Thresholding. Split and merge algorithms. Region growing. Recent segmentation methods. Clustering algorithms.
[28-30] Motion Analysis – Motion estimation techniques. Tracking. Motion based segmentation. Problem Class.
|
|
|
|
| Methods of Teaching/Learning |
Lectures: 10 weeks, 10x 3h
Labs: Matlab (image processing) exercise to consolidate the lecture material, 2 weeks, 2 x 3h
|
|
|
| Selected Texts/Journals |
|
Gonzales RC., Woods P., Digital Image Processing, 2002. 0-201-600781
Gonzales RC., Woods P., Eddings, Digital Image Processing using Matlab, 2004
Petrou,M., and Bosdogianni, P., Image Processing: the fundamentals, 2000.
|
|
|
| Last Updated |
29th July 2009 |
|
