Module Specification
Module name: Visual perception and 2D/3D computer vision
Code: ICT35M3
Programme (Energy/ICT): ICT
ECTS: 6
Type Bachelor/Msc : MSc
Module name: Computer Vision
Scope and form: Lecture - 24 hours per semester / Tutorial - 12 hours per semester
Duration (weeks; Hours/week): 15 weeks, 3h/week
Type of assessment:
-
10% - Working with OpenImj to achieve basic computer vision analysis.
-
10% - Build basic technique.
-
20% - Group coursework .
-
60% - Exam, 2 hour(s).
Qualified Prerequisites: BSc in informatics or equivalent
General module objectives: The objective of the module are as follows: To develop the students' understanding of the basic principles and techniques of image processing and image understanding and to develop the students' skills in the design and implementation of computer vision software
Topics and short description:
-
Overview: The challenge of computer vision is to develop a computer based system with the capabilities of the human eye-brain system. It is therefore primarily concerned with the problem of capturing and making sense of digital images. The field draws heavily on many subjects including digital image processing, artificial intelligence, computer graphics and psychology. This module will explore some of the basic principles and techniques from these areas which are currently being used in real-world computer vision systems and the research and development of new systems.
-
Topics:
-
The human eye-brain system as a model for computer vision
-
Image formation: sampling theorem, Fourier transform and Fourier analysis
-
Image models
-
Basic image processing: Sampling and quantisation, Brightness and colour, Histogram operations, Filters and convolution, Frequency domain processing
-
Edge detection
-
Boundary and line extraction
-
Building machines that see: constraints, robustness, invariance and repeatability
-
Fundamentals of machine-learning: classification and clustering
-
Understanding covariance, eigendecomposition and PCA
-
Feature extraction
-
Interest point detection
-
Segmentation
-
2-D Shape representation
-
Local features
-
Image matching
-
Large-scale image search and feature indexing
-
Understanding image data and performing classification and recognition
-
3D vision systems
-
Recovering depth from multiple views
-
Practical examples, including: biometric systems (recognising people), industrial computer vision, etc
Learning outcomes:
Knowledge
|
Skills
|
Competences
|
Human and computer vision systems
|
Implement basic image processing algorithms
|
Analyse and design a range of algorithms for image processing and computer vision
|
Current approaches to image formation and image modelling
|
|
Develop and evaluate solutions to problems in computer vision
|
Current approaches to basic image processing and computer vision
|
|
|
Module recommended literature:
Core textbooks
Nixon, M.S. and Aguado, A.S. Feature Extraction & Image Processing, 3rd ed., Academic Press, 2012.
Other resource requirements (Background textbook):
Sonka, Hlavac & Boyle, Image Processing, Analysis and Machine Vision, 3rd ed., PWS Publishing, 2008.
Gonzalez et al., Digital Image Processing, 3rd ed., Pearson, 2008.
Stockman and Shapiro, Computer Vision, Prentice Hall, 2001.
: http://www.ecs.soton.ac.uk/module/COMP3204#overview
Special Considerations: Generically none for this module but should be commented on by the institution delivering the module.
http://www.saleie.york.ac.uk
Project Coordinator: Tony Ward, University of York Email: tony.ward@york.ac.uk
Share with your friends: |