Module Code - Title:
CE5011
-
MACHINE VISION & IMAGE PROCESSING
Year Last Offered:
2025/6
Hours Per Week:
Grading Type:
N
Prerequisite Modules:
Rationale and Purpose of the Module:
This module will introduce students to the principles of Machine Vision & Image Processing. Key topics such as linear image processing, feature detection and basic object detection are introduced.
Practical examples of these techniques are included in the laboratories for this module to increase student engagement with this material. This module acts as a precursor to advanced vision modules which require a good understanding of these key principles.
Syllabus:
1. Introduction to Machine/Computer Vision.
Image formation, camera basics, computer representation of images.
Linear Image processing, morphology operations & basic edge detection.
Canny Edge Detection and Hough Transform.
Clustering and Image Segmentation (K-means, Watershed & Mean shift Algorithms).
Case studies of Automated Inspection with Machine Vision.
2. Feature Detection, Descriptors and applications.
Corner Detection (Harris Algorithm)
Laplacian of Gaussian and blob detectors.
Feature Descriptors (SIFT & binary descriptors)
Feature Matching with Descriptors.
3. Basics of Machine Learning for vision.
Machine Learning Introduction (Types of Classifiers SVM, CNN)
Principle Component Analysis and Eigenfaces & Fisher faces.
Classical Methods of Object Detection.
Sliding window based Viola Jones & Histogram of Orientated Gradients algorithms.
Bag of Features for image classification and retrieval.
4. Introduction to use of Deep Learning in Machine & Computer Vision
Learning Outcomes:
Cognitive (Knowledge, Understanding, Application, Analysis, Evaluation, Synthesis)
On successful completion of this module, students will be able to:
1. Demonstrate an understanding of basic image processing, morphology operations and edge
detection algorithms.
2. Understand reasons for feature detection, basic detector algorithms and the application of
these detectors.
3. Understand basic principles of machine learning and it's application to machine vision.
4. Apply sliding window based object detection algorithms to different tasks.
5. Be aware of the application of Deep learning to key problems in machine vision.
Affective (Attitudes and Values)
On successful completion of this module, students will be able to:
1. Determine how to apply computer vision techniques to a machine vision problem.
2. Be able to effectively use python packages (OpenCV and SKLearn) for machine vision.
Psychomotor (Physical Skills)
On successful completion of this module, students will be able to: n/a
How the Module will be Taught and what will be the Learning Experiences of the Students:
The module will be delivered in a online learning format, with online pre-recorded video lectures and interactive Q+A tutorials. The students will also complete a series of coding exercises either in in their own time with online moderator support.
Research Findings Incorporated in to the Syllabus (If Relevant):
Prime Texts:
D.A. Forsyth, J. Ponce (2011)
Computer Vision: A Modern Approach (2nd Edition),
, Prentice
Hall
R. Szeliski (2010)
Computer Vision: Algorithms & Applications 2nd ed.
, https://szeliski.org/Book/
Other Relevant Texts:
Programme(s) in which this Module is Offered:
PDCVSYTPA - Computer Vision Systems
Semester(s) Module is Offered:
Autumn
Module Leader:
eoin.grua@ul.ie