Image classification may be performed using supervised, unsupervised or semi-supervised learning techniques. In supervised learning, the system is presented with numerous examples of images that must be manually processed and labelled. Using this training data, a learned model is then generated and used to predict the features of unknown images.
Using Machine Intelligence (MI) methods and new machine learning algorithms and image classification we aim to extend some of the well-established machine learning techniques and apply them to three-dimensional images of materials such as those obtained by 3D microscopes.
Over the past 15 years, the X-ray CT microscopes at the Department of Applied Mathematics have been busy producing thousands of 3D images. A 3D image may be composed of multiple elements, minerals, alloys, fibres etc. Separating these components can be challenging and is certainly a laborious manual task in 3D.
In this project, the students will be working closely with the researchers to implement machine-learning techniques for material identification in 3D images.
- Mohammad Saadatfar
- Shane Latham