Registry

Module Specifications

Archived Version 2017 - 2018

Module Title	Image Processing & Analysis with Project
Module Code	EE453
School	School of Electronic Engineering
Online Module Resources
Module Co-ordinator	Prof Paul F. Whelan	Office Number	S362
NFQ level	8	Credit Rating	7.5
Pre-requisite	None
Co-requisite	None
Compatibles	None
Incompatibles	None

Description

Most people are familiar with the concept of processing an image to improve its quality or the use of image analysis software tools to make basic measurements; but what are the ideas behind such solutions and why is knowledge of these concepts important in developing successful computer vision applications? This module will answer these questions by focusing on both the theoretical, mathematical and practical issues associated with a wide range of computer vision solutions. Such solutions relate to the fields of image processing & analysis, industrial/machine vision, video data processing, biomedical engineering, imaging science, sensor technology, multimedia and enhanced reality systems. This module will concentrate on developing the fundamentals necessary to design, develop and understand a wide range of basic imaging processing (image to image), image analysis (image to feature), image classification (feature to decision), performance characterisation (data to quantitative performance indicators) and computer vision (image to interpretation) solutions. All solutions have limitations and a key element of this module is to focus on how to approach the design, testing and evaluation of successful computer vision applications within an engineering framework. This module will make extensive use of an image analysis development environment to reinforce all the issues covers during the lectures. In addition to the common elements associated with EE425, this module will contain a significant image processing & analysis project.

Learning Outcomes

1. Recall, review and analyse the essential theories, algorithms, methodologies and techniques involved in computer vision.
2. Illustrate their ability to comprehend and interpret issues relating to the design of image processing & analysis techniques.
3. Synthesize and evaluate the relevant merits of competing computer vision techniques.
4. Apply computer vision techniques in a range of application scenarios.
5. Develop an understanding of the engineering issues involved in the commercial development of image processing and analysis solutions.
6. Demonstrate the ability to implement a image processing and analysis pipeline.

*Type*	*Hours*	*Description*
Workload	Full-time hours per semester
Lecture	24	This module is presented in a traditional format (lecture and continuous assessment) with significant practical support [including: long-format electronic notes and associated course text, pdf versions of the class slides, podcasts, image analysis development environment (used for the assignments and to illustrate computer vision concepts), self assessment questions and selected examples illustrating key concepts].
Tutorial	12	Homeworks, Worked Examples.
Laboratory	12	Laboratory support for coursework.
Independent Study	62.5	Project.
Independent Study	77	General revision and practice, Coursework, Online activity with module material.
Total Workload: 187.5

All module information is indicative and subject to change. For further information,students are advised to refer to the University's Marks and Standards and Programme Specific Regulations at: http://www.dcu.ie/registry/examinations/index.shtml

Indicative Content and Learning Activities

Project
2.5 ECT individual image processing and analysis project.

Introduction
Introduction Introduction to Matlab for Image Processing & Analysis, IPA Pipeline, Learning Outcomes, Module Protocol, Assessment Requirement, Matlab Code Development, Support Material & Website, Software Tools, Human/Computer/Machine Vision, Case Studies.

Basic Techniques
Image Representation, Pattern Recognition using Feature Extraction, Point-by-Point Operators, Thresholding, Convolution, Deconvolution, Linear Local Operators, Non-linear Local Operators, Gradient and Difference based Edge Detectors - Template Matching, N-tuple Operators, Measures of Similarity, Histograms, Look-up Tables, Binary Image Processing, Run Code, Freeman Chain Code, Simple Shape Descriptors, Concavity, Distance Metrics, Distance Transform, Video Sequence Processing - Graphic File Formats, Imaging Modalites Overview, Image Noise, Noise Metrics - Example applications and case studies.

Morphology
Study of Form and Structure, Binary Morphology, Erosion, Dilation, Duality, Idempotency, Opening, Closing, Skeletionization, Structuring Element Decomposition, Hit-and-Miss Transform, Grey Scale Morphology, Top-Hat Transform, Morphological Gradient, Point-Pairs SE, Covariance, Worked Examples.

Transforms
Global Image Transforms, Interpolation, Hough (Linear, Circular, Generalised), Two-Dimensional Discrete Fourier Transform, DFT Filtering, Discrete Cosine Transform, Worked Examples.

Classification & Performance Characterization
Classification/Clustering, Supervised vs Unsupervised, Feature Selection, Nearest Neighbour Classifier, K-Nearest Neighbour, K-Means Clustering, Maximum-likelihood Classifier, Automated Thresholding, Evaluation of Classifier Performance, Worked Examples. Algorithm Performance, Ground Truth, Receiver-Operator Characteristic Analysis, Hazards of Significance Testing/Screening, System Engineering Issues.

Colour
Human/Mammal Perception of Colour, Essential Rules of Colorimetry, Colour Spaces (RGB, Opponent Process Representation, Otha/Polar, HSI, YIQ/YUV), Colour Scattergrams, Coarse Colour Discrimination (Programmable Colour Filter), Applications (Green Screen, Tracking), Worked Examples.

Texture
Structural Approaches, Fourier Spectral Analysis, Auto-Correlation Function, Histogram Features, Grey Level Run Length Method, Grey Level Difference Method, Spatial Grey Level Dependence Method (Co-occurrence Matrix), Morphological Texture Analysis, Pseudo Monte-Carlo Method, Fractal Description of Texture, Worked Examples.

Interest Point Detection
Corner Detection, SUSAN Corner/Edge Detector, Marr-Hildreth Edge Detector, Canny Edge Detector, Comparison of Edge Detectors.

Ethics
Why are we Concerned?, Relevant Codes, Guidelines for the Proper Acquisition and Manipulation of Scientific Digital Images, Case Studies.

Assessment Breakdown
Continuous Assessment	50%	Examination Weight	50%

Type	Description	% of total	Assessment Date
Course Work Breakdown

Reassessment Requirement
Resit arrangements are explained by the following categories; 1 = A resit is available for all components of the module 2 = No resit is available for 100% continuous assessment module 3 = No resit is available for the continuous assessment component
Unavailable

Indicative Reading List

Paul F Whelan: 2010, Online Course long form notes (including self assessment questions) and class notes (slides),
Rafael C. Gonzalez, Richard E. Woods, Steven L. Eddins: 2009, Digital Image processing using MATLAB, Gatesmark Publishing, [S.I.], 0982085400]
Richard Szeliski: 0, Computer Vision: Algorithms and Applications, Springer, 9781848829343
Paul F. Whelan, Derek Molloy: 0, Machine Vision Algorithms in Java, Springer, 1-85233-218-2
E. R. Davies: 0, Machine vision, Amsterdam ; Elsevier, c2005., 0122060938]

Other Resources

27163, Module Software, Paul F Whelan, 2010, VSG Image Processing & Analysis Toolbox (VSG IPA TOOLBOX), Vision Systems Group, http://www.cipa.dcu.ie/code.html, 27164, Lecturer Website, Paul F Whelan, 0, paulwhelan.eu, http://paulwhelan.eu/,

Programme or List of Programmes

BMED	B.Eng. in Biomedical Engineering
DME	B.Eng. in Digital Media Engineering
ECE	BEng Electronic & Computer Engineering
ECSA	Study Abroad (Engineering & Computing)
ECSAO	Study Abroad (Engineering & Computing)
EE	BEng in Electronic Engineering
MECE	MEng Electronic & Computer Engineering
MEQ	Masters Engineering Qualifier Course
MTC	MEng in Telecommunications Engineering
SMPEC	Single Module Programme (Eng & Comp)

Archives: