- Machine Learning
-
Machine Learning
This course covers methods for machine learning from signals and data, including statistical pattern recognition methods, neural networks, and clustering.
Read More
Machine Learning
Summary:
This course covers methods for machine learning from signals and data, including statistical pattern recognition methods, neural networks, and clustering.
Credits:
15.0
Aims:
The aim of the course is to give students an understanding of machine learning methods, including pattern recognition, clustering and neural networks, and to allow them to apply such methods in a range of areas.
Objectives:
Recall a range of machine learning techniques and algorithms, including neural networks and statistical methods
Use concepts from probability theory in machine learning
Derive and analyse properties of machine learning methods
Discuss the relative merits of different machine learning techniques and approaches
Apply machine learning methods to the analysis of signals and data
Books:
Pattern Classification by Duda Hart and Stork; 2nd Edition; Wiley 2001; ISBN 0471056693
- Advanced Transform Methods
-
Advanced Transform Methods
Time-frequency transforms are an important tool in the analysis and processing of signals and images. These transforms include the Fourier transform, spectrogram, discrete cosine transform, wavelet transform, and Wigner-Ville distribution. This course will introduce these various transforms and explore how they are suitable for different signal and image processing applications.
Read More
Advanced Transform Methods
Summary:
Time-frequency transforms are an important tool in the analysis and processing of signals and images. These transforms include the Fourier transform, spectrogram, discrete cosine transform, wavelet transform, and Wigner-Ville distribution. This course will introduce these various transforms and explore how they are suitable for different signal and image processing applications.
Credits:
15.0
Pre-requisites:
ELE502 or ELEM020
Aims:
This course aims to introduce transform and sub-band techniques as a pre-cursor to compression and other applications. It is the first step beyond the fundamentals of Digital Signal processing.
Objectives:
Recall a range of joint time-frequency transforms.
Discuss the relative merits of different transforms.
Employ the common mathematical framework underlying many transform methods.
Derive various properties of different transforms.
Use high performance mathematical visualization software (e.g. Matlab) to implement these transforms.
Apply these transforms to signal and image processing problems, such as compression or denoising.
Core Skills:
Analyse information using mathematical models
Books:
A Wavelet Tour of Signal Processing, Third Edition: The Sparse Way, by S.G. Mallat; Academic Press, ISBN: 13: 978-0-12-374370-1
- Introduction to Computer Vision
-
Introduction to Computer Vision
In recent years, research in computer vision has made significant progress.This is largely driven by the recognition that effective visual perceptionis crucial in understanding intelligent behaviour - unless we understand how we perceive, we will never understand how we reason
The first part of the course will introduce the relevant concepts and techniques in machine learning.
In the second part we will show how these techniques can be applied to various areas in computer vision.
Read More
Introduction to Computer Vision
Summary: In recent years, research in computer vision has made significant progress.This is largely driven by the recognition that effective visual perceptionis crucial in understanding intelligent behaviour -
unless we understand how we perceive, we will never understand how we reason
The first part of the course will introduce the relevant concepts and techniques in machine learning.
In the second part we will show how these techniques can be applied to various areas in computer vision.
Credits: 15.0
Pre-requisites: Elementary calculus, linear algebra, statistics and programming in C++ or JAVA or Matlab.
Aims: - To give an updated account of both established and ongoing research in computer vision, statistical learning theories, data mining and clustering in multivariate space. Applications in human face, gesture and visual behaviour recognition will be used to illustrate the workings in some of the state-of-the-art machine vision and imaging systems.
Objectives: The course will cover the following topics
- Relevant probability and information theory
- Experimental set-up of machine learning
- Hidden Markov modeling
- Clustering and classification
- Neural Networks
Core Skills: the ability to adapt mathematical and statistical concepts to the various research issue in computer vision.
- Computer Graphics
-
Computer Graphics
This course is concerned primarily with computer graphics systems and in particular 3D computer graphics. The course will include revision of fundamental raster algorithms such as polygon filling and quickly move onto the specification, modeling and rendering of 3D scenes. In particular the following topics may be covered: viewing in 2D,data structures for the representation of 3D polyhedra, viewing in 3D, visibility and hidden surface algorithms, illumination computations. Some attention will be paid to human perception of colour and interactive 3D such as virtual reality.
Read More
Computer Graphics
Summary:
This course is concerned primarily with computer graphics systems and in particular 3D computer graphics. The course will include revision of fundamental raster algorithms such as polygon filling and quickly move onto the specification, modeling and rendering of 3D scenes. In particular the following topics may be covered: viewing in 2D,data structures for the representation of 3D polyhedra, viewing in 3D, visibility and hidden surface algorithms, illumination computations. Some attention will be paid to human perception of colour and interactive 3D such as virtual reality.
Credits:
15.0
Pre-requisites:
It is essential that students have good programming ability, and a willingness to learn some mathematics.
Aims:
The aim of this course is to introduce the fundamental concepts of 3D computer graphics. This encompasses describing a 3D scene (modelling and data structures), constructing views, rendering, and illumination. This requires a thorough understanding of algorithms and graphics systems programming.
Objectives:
By the end of this course students will have constructed from scratch a program that encapsulates many of the major ideas of computer graphics. Students will understand and be able to reason about and implement many of the major algorithms of 3D computer graphics.
Core Skills:
This course will help students develop a range of skills such as problem solving through exercises and courseworks of increasing difficulty, written and oral communication skills and will improve their skills in working with others fostered through justification of their own approaches and choices in discussions with teaching assistants and other fellow students.
Books:
Essential text book: Foley, J.D., van Dam, A., Feiner, S.K., Hughes, J.F.,Phillips, R.L.,(1994) Introduction to Computer Graphics, Addison-Wesley publishers. A complete reading list is available in the web pages for this course.
- C++ For Image Processing
-
C++ For Image Processing
This course gives students a practical introduction to C++ and uses this programming language to examine applications in low level image processing. Areas covered include image representation examining perception, sampling and display, and image transforms and image enhancement using point and spatial operations. Also considered are image processing methods such as convolution, frequency filtering and image restoration, compression and segmentation.
Read More
C++ For Image Processing
Summary:
This course gives students a practical introduction to C++ and uses this programming language to examine applications in low level image processing. Areas covered include image representation examining perception, sampling and display, and image transforms and image enhancement using point and spatial operations. Also considered are image processing methods such as convolution, frequency filtering and image restoration, compression and segmentation.
Credits:
15.0
Pre-requisites:
Some previous Mathematical background such as A level. NB Students who have already taken and passed DCS339 at undergraduate level 3 may not take this masters version.
Aims:
The main purpose of this course is to provide an introduction to basic concepts and methodologies for digital image processing.
Objectives:
Be able to use effectivly the C++ programming language
Be able to implement low level image processing algorithms.
Understand image file formats
Implement contrast enhancement by histogram manipulation
Know frequency domain transform methods
Use filtering algorithms for image smoothing and sharpening
Ability to undertake independent advanced scholarship
Ability to interpret/ conceptualise/ independently evaluate techniques and applications of techniques in this field of study
An awareness of the wider context and critical issues surrounding this field of study
Core Skills:
This course will help students develop a range of skills such as problem solving through exercises and courseworks of increasing difficulty, written and oral communication skills and will improve their skills in working with others fostered through justification of their own approaches and choices in discussions with teaching assistants and other fellow students.
Books:
Text books:
Digital Image Processing (2nd Edition), by Rafael C. Gonzalez, and Richard E. Woods, 793 pages, Prentice Hall, 2002, ISBN: 0201180758.
C++: The Complete Reference, (4th Edition), by Herbert Schildt, 1056 pages, McGraw-Hill Osborne Media, 2002, ISBN: 0072226803.
Reading:
Digital Image Processing using MATLAB, by Rafael C. Gonzalez, and Richard E. Woods, 793 pages, Prentice Hall, 2002, ISBN: 0201180758.
Simplified Approach to Image Processing, A: Classical and Modern Techniques in C, by Randy Crane, (Hewlett-Packard Professional Books), 336 pages, Prentice Hall, 1996, ISBN: 0-13-226416-1
Fundamentals of Digital Image Processing, by Anil K. Jain, 592 pages, Prentice Hall, 1988, ISBN: 0133361659.
Algorithms for Image Processing and Computer Vision, by J. R. Parker, 432 pages(with CD-ROM), John Wiley & Sons, 1996, ISBN: 0471140562.
- Techniques for Computer Vision
-
Techniques for Computer Vision
The course will cover the following topics:
The Discrete Fourier Transform and the frequency content of images
The design and use of Gabor filters
Principal Component Analysis for denoising and compression
Unsupervised classification via feature space clustering
Texture segmentation with Gabor filters
Image mosaicing
Read More
Techniques for Computer Vision
Summary: The course will cover the following topics:
The Discrete Fourier Transform and the frequency content of images
The design and use of Gabor filters
Principal Component Analysis for denoising and compression
Unsupervised classification via feature space clustering
Texture segmentation with Gabor filters
Image mosaicing
Credits:
15.0
Pre-requisites:
AMCM-053 C++ for Image Processing
Aims:
Providing students with an understanding of techniques in pattern recognition that are close to the state of the art.
Giving students hands-on experience with the use of filters, classification techniques and algorithms related to pattern recognition.
Objectives:
At the end of this course students will have an understanding of modern approaches to pattern recognition.
In the course of the laboratories, the students will have assembled basic but functional systems for pattern recognition. This should enable them to design a practical system by recognizing the functionalities needed, and what types of techniques are available for implementing them.
Core Skills:
Analytic thinking, presentation and technical report writing skills.
Books:
Relevant research papers and online material.
Additional reading: R. C. Gonzales and R. E. Woods, Digital Image Processing, Pearson 2008 (or previous editions)
- High Performance Computing
-
High Performance Computing
The 12 week module involves 2 hours of timetabled lectures per week. Laboratory sessions are timetabled at 2 hours per week for 6 to 7 weeks only. The course syllabus adopts a hands-on programming stance. In addition it focuses on algorithms and architectures to familiarise students with message-passing systems ((MPI) as adopted by industry.
Parallel computing, which implies the simultaneous execution of several processes for solving a single problem, is a mainstream subject with wide ranging implications for computer architecture, algorithms design and programming. The UK has been at the forefront of this technology through its involvement in the development of several innovtive architectures. Queen Mary has been involved with Parallel Computing for more than a decade. In this course, students will be introduced to parallel computing and will gain first hand experience in relevant techniques.
Laboratory work will be based on the MPI (Message Passing Interfaces) standard, running on a network of PCs in the teaching laboratory.
The syllabus mirrors the recommended text book very closely. Other text-books are also listed below as sources of additional reading.
The course should be of interest to Computer Scientists and those following joint programmes (CS/Maths, CS/Stats). It is also suitable for Chemistry and Engineering students who are concerned with the application of high performance parallel computing for their particular field of study e.g. Simulation of chemical Behaviour.
Read More
High Performance Computing
Summary: The 12 week module involves 2 hours of timetabled lectures per week. Laboratory sessions are timetabled at 2 hours per week for 6 to 7 weeks only. The course syllabus adopts a hands-on programming stance. In addition it focuses on algorithms and architectures to familiarise students with message-passing systems ((MPI) as adopted by industry.
Parallel computing, which implies the simultaneous execution of several processes for solving a single problem, is a mainstream subject with wide ranging implications for computer architecture, algorithms design and programming. The UK has been at the forefront of this technology through its involvement in the development of several innovtive architectures. Queen Mary has been involved with Parallel Computing for more than a decade. In this course, students will be introduced to parallel computing and will gain first hand experience in relevant techniques.
Laboratory work will be based on the MPI (Message Passing Interfaces) standard, running on a network of PCs in the teaching laboratory.
The syllabus mirrors the recommended text book very closely. Other text-books are also listed below as sources of additional reading.
The course should be of interest to Computer Scientists and those following joint programmes (CS/Maths, CS/Stats). It is also suitable for Chemistry and Engineering students who are concerned with the application of high performance parallel computing for their particular field of study e.g. Simulation of chemical Behaviour.
Credits: 15.0
Pre-requisites: Some prior knowledge of networking and operating systems or similar, or by prior agreement of the module leader.
Aims: To introduce students to the paradigm of Parallel Computing, an awareness of its advantages and current limitations and allow the development of practical programming skills in a parallel computing environment
Objectives: Students will gain an understanding and practical knowledge of:
- Introduction to parallel computers,
- Introduction to message-passing systems,
- Introduction to parallel programming strategies,
- Methods for load balancing,
- Issues surrounding shared memory programming,
- An examination of parallel processing for numerical (e.g. parallel sorting) and image processing.
Core Skills: Technical report writing and presentaion, writing skills
Books: Recomended Texts
Parallel Programming
, Wilkinson and Allen; 2nd. Ed. ISBN 0-13-140563-2, 2005, Pearson/Prentice Hall.
Additional Reading Material
1. An Introduction to Parallel Computing: Design & Analysis of Algorithms, 2nd. Ed
, Grama et al., ISBN 020 164 8652
2. Parallel Programming: An Introduction
, Thomas Braunl (Prentice Hall)
3. Advanced Computer Architectures, A Design Space Aproach
, D Sima, T Fountain and P Kacsuk (Addison-Wesley 1997)
4. Parallel Computing 2
, Hockney and Jesshope (Adam HilgerLtd)
5. Introduction to Parallel Computing
, Ted G Lewis and Hesham El-Rewini (Prentice Hall 1992)
6. Parallel Computing, theory and practice
, Michael J Quinn(McGraw-Hill, Inc. 1994)
- Artificial Intelligence
-
Artificial Intelligence
The course introduces the student to techniques used in Artificial Intelligence including problem formulation, search, logic, probability and decision theory.
Read More
Artificial Intelligence
Summary:
The course introduces the student to techniques used in Artificial Intelligence including problem formulation, search, logic, probability and decision theory.
Credits:
15.0
Objectives:
Express problems as a search problem and identify the appropriate techniques for solving it.
Books:
Artificial Intelligence: A Modern Approach by Stuart Russell and Peter Norvig; 2nd Edition; Prentice Hall 2003; ISBN 0137903952
Extra Costs:
There are no additional costs to study this module, unless you exceed your print credit and choose to purchase additional print credit.
