Course overview
In this course, students will develop analytic knowledge and skills of machine learning and vision systems and digital image processing for use in mechatronic systems especially in manufacturing applications Components of machine vision systems, image acquisition, point and neighbourhood image enhancement, edge based and region based image segmentation, colour image processing, morphological image processing, image description and representation, machine learning fundamentals, Fuzzy logic, Neural networks, basic deep learning.
Course learning outcomes
- Explain and analyse essential concepts of a machine vision system (PO 1, 4) (EA 1.3, 2.1)
- Develop a process to capture an image and enhance it for further processing (PO 4) (EA 2.1, 2.2)
- Analyse a procedure to segment an image to differentiate the objects of interest from the back ground and recognise/interpret them in an image (PO 1, 4) (EA 1.3, 2.1, 2.2 )
- Compare machine learning methods and evaluate/apply an appropriate one for a given application in a group (PO 1, 4, 8) (EA 1.3, 2.1, 2.2, 3.6)