- Department: Computer Science
- Module co-ordinator: Prof. Edwin Hancock
- Credit value: 20 credits
- Credit level: H
- Academic year of delivery: 2016-17
- See module specification for other years: 2017-18
Pre-requisite modules
Co-requisite modules
- None
Prohibited combinations
Occurrence | Teaching cycle |
---|---|
A | Autumn Term 2016-17 to Spring Term 2016-17 |
The aim of this module is to cover the main theories and techniques used in computer vision.
It commences with a description of the main signal processing techniques used to perform image processing and extract low-level visual features. Next, it covers topics from intermediate level vision including image segmentation, motion analysis and shape analysis. A set of three lectures present image compression, motion estimation and digital watermarking. The third part of the course focusses on issues of three dimensional object perception from 2D imagery. The final part of the course is concerned with object recognition and image understanding. Each of these aspects of the course will be supported by practical examples and case-studies.
1. To understand and be familiar with the mathematical and theoretical foundations of image processing and computer vision. These include 2D signal processing, perspective geometry, the physics of image formation and constraint satisfaction techniques.
2. To develop a practical appreciation of the main algorithms and methods for image processing, image segmentation, 3D scene analysis and object recognition.
3. Gain an awareness of the main theories of computational vision, including the work of Marr and Gibson.
4. To understand the uses and limitations of image processing computer vision through practical case studies
Task | Length | % of module mark |
---|---|---|
University - closed examination Computer Vision (CVIS) |
2 hours | 100 |
None
Task | Length | % of module mark |
---|---|---|
University - closed examination Computer Vision (CVIS) |
2 hours | 100 |
1. Model solutions to practical problems.
2 Model answers for past open and closed assessments.
** Forsyth and Ponce Computer Vision a Modern Approach Prentice Hall
** Anil K. Jain Fundamentals of Digital Image Processing Prentice Hall
** Rafael C Gonzalez and P. A. Wintz Digital Image Processing Prentice Hall
** Haralick R and Shapiro L Computer and Robot Vision Addison Wesley
** Kenneth R. Castleman Digital Image Processing Prentice Hal