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 (NFQ Level: 8, ECTS Credits: 7.5) 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 and analysis, industrial/machine vision, video data processing, biomedical engineering, imaging science, sensor technology, multimedia and enhanced reality systems. It 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.

Notes and associated material are copyright, as such reuse or redistribution of this material (partial or otherwise) is strictly prohibited. Redistribution of username/password access to this material to non-registered students is also prohibited. All user access is logged for analytical and verification purposes. 

Course Outline

Module link (password required to access content).

The focus of this module (NFQ Level: 9, ECTS Credits: 7.5) is to produce graduates with a deeper theoretical and practical understanding of the issues that underpin computer vision.

Computer vision applications have significantly expanded over the last decade and this core skill set is always in high demand by employers. It will build on the basic concepts with a view to delving deeper into core computer vision, machine learning and deep learning topics. As well as examining traditional computer vision concepts (ie feature extraction and machine learning) a key focus of the module will be on deep learning as applied to computer vision. We will examine the core concepts behind deep learning for computer vision with a specific focus on Convolutional Neural Networks (CNN). Students will learn how to design and tune such networks in a range of practical applications. In addition we will examine a range of CNN architectures ranging from AlexNet upto the current state of the art in this ever expanding field. Deep learning based computer vision forms the core of many of the recent developments in this field and has been widely adopted as a core AI tool by all the key industrial players such as Google, Facebook, IBM, Apple, Baidu ... as well as a wide range of highly innovative startups. All computer vision and deep learning concepts will be reinforced by guided practical work and case studies.

This module is primarily aimed at those who aim to undertake research in computer vision or require a deeper understanding of the subject to address commercial computer vision development. Computer vision applications span a wide range of disciplines including industrial/machine vision, video data processing, biomedical engineering, healthcare, astronomy, imaging science, sensor technology, multimedia and enhanced reality systems.

This module will require basic programming skills. We will develop solutions within a Python based development environment. Specifically we will use the open source and widely adopted scikit-image, opencv and scikit-learn libraries in designing advanced computer vision and machine learning solutions. Building on this we will develop our deep learning solutions within the very popular Keras (a high-level python based neural networks API) Tensorflow (an open-source software library for Machine Intelligence) environment. 

Course Outline

Module link (password required to access content).