Registry
Module Specifications
Archived Version 2017 - 2018
| |||||||||||||||||||||||||||||||||||||||||
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. | |||||||||||||||||||||||||||||||||||||||||
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 Project2.5 ECT individual image processing and analysis project.IntroductionIntroduction 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 TechniquesImage 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.MorphologyStudy 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.TransformsGlobal Image Transforms, Interpolation, Hough (Linear, Circular, Generalised), Two-Dimensional Discrete Fourier Transform, DFT Filtering, Discrete Cosine Transform, Worked Examples.Classification & Performance CharacterizationClassification/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.ColourHuman/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.TextureStructural 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 DetectionCorner Detection, SUSAN Corner/Edge Detector, Marr-Hildreth Edge Detector, Canny Edge Detector, Comparison of Edge Detectors.EthicsWhy are we Concerned?, Relevant Codes, Guidelines for the Proper Acquisition and Manipulation of Scientific Digital Images, Case Studies. | |||||||||||||||||||||||||||||||||||||||||
| |||||||||||||||||||||||||||||||||||||||||
Indicative Reading List
| |||||||||||||||||||||||||||||||||||||||||
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 | |||||||||||||||||||||||||||||||||||||||||
Archives: |
|