Rhedir gan School of Computer Science and Electronic Engineering
20.000 Credyd neu 10.000 Credyd ECTS
This module aims to describe the concepts of image processing and computer vision. It will also enable students to process images and implement simple digital image processing and computer vision systems.
Indicative content includes:
- Image formation, image representation, fundamentals of human luminance and color vision, segmentation, re-sampling. Solving problems using a modern library such as OpenCV,
- Point operations, convolution, linear filters, morphological operators, image histograms, and histogram equalization, 2D image transformations, image pyramids.
- Edge detectors, Hough transform, segmentation, feature detectors, feature descriptors, feature matching.
- Digital camera, display devices. colour calibration, gamma correction, limitations of human visual perception.
- More advanced computer vision topics, e.g. person tracking, trajectory, surveillance, security, controlling processes (e.g., robots), navigation, comp-human interaction (e.g., gestures), automatic inspection. Ethical considerations incl. data collection/management, informed consent, privacy, surveillance.
Equivalent to the range 70%+. Assemble critically evaluated, relevent areas of knowledge and theory to constuct professional-level solutions to tasks and questions presented. Is able to cross-link themes and aspects to draw considered conclusions. Presents outputs in a cohesive, accurate, and efficient manner.
Equivalent to the range 60%-69%. Is able to analyse a task or problem to decide which aspects of theory and knowledge to apply. Solutions are of a workable quality, demonstrating understanding of underlying principles. Major themes can be linked appropriately but may not be able to extend this to individual aspects. Outputs are readily understood, with an appropriate structure but may lack sophistication.
Equivalent to 40%. Uses key areas of theory or knowledge to meet the Learning Outcomes of the module. Is able to formulate an appropriate solution to accurately solve tasks and questions. Can identify individual aspects, but lacks an awareness of links between them and the wider contexts. Outputs can be understood, but lack structure and/or coherence.
Effectively use image representations to solve computer vision problems
Use computer vision techniques to implement feature detection and tracking.
Construct software to process image data, both in a general sense and for Computer Vision.
Apply image processing filters and operators to achieve given goals of an imaging system.
Make informed decisions on the selection of imaging and display technologies for a task at hand.
Give examples of computer vision applications, associate them with CV algorithms.
|Image Processing Application||25.00|
|Computer Vision Application||25.00|
Strategaeth addysgu a dysgu
2 hours per tutorial/lecture per week
1x2 hours a week
- Rhifedd - Medrusrwydd wrth ddefnyddio rhifau ar lefelau priodol o gywirdeb
- Defnyddio cyfrifiaduron - Medrusrwydd wrth ddefnyddio ystod o feddalwedd cyfrifiadurol
- Hunanreolaeth - Gallu gweithio mewn ffordd effeithlon, prydlon a threfnus. Gallu edrych ar ganlyniadau tasgau a digwyddiadau, a barnu lefelau o ansawdd a phwysigrwydd
- Archwilio - Gallu ymchwilio ac ystyried dewisiadau eraill
- Dadansoddi Beirniadol & Datrys Problem - Gallu dadelfennu a dadansoddi problemau neu sefyllfaoedd cymhleth. Gallu canfod atebion i broblemau drwy ddadansoddiadau ac archwilio posibiliadau
Sgiliau pwnc penodol
- Identify emerging technologies and technology trends;
- Solve problems logically and systematically;
- Analyse and display data using appropriate methods and mathematical techniques;
- Demonstrate familiarity with relevant subject specific and general computer software packages.
- Problem solving strategies
- Deploy theory in design, implementation and evaluation of systems
- Knowledge and/or understanding of appropriate scientific and engineering principles
- Knowledge and understanding of mathematical principles
- Knowledge and understanding of computational modelling