Analysis of schist thin section images with image processing

OData support
Dr. Csorba Kristóf
Department of Automation and Applied Informatics

The goal of my work was to create a software to half-automatically analyse schist thin-section images. The first step to do that is identifying grains on the image, also called segmentation. The main problem with that is that this isn’t an easy task even for the human eye. As I’ll show in this document, those images show a great variety of colour, size and shape of grains.

At the beginning of this document I’ll start with the introduction of the required knowledge of physics and geology to understand my work. In the following I’ll describe some different approach of this problem, such as the measuring method of the colour distance and the using of the Michel-Lévy chart.

Finally, I’ll present the accomplished results, the ways of using the program, the things I learnt during the developing and ways to further develope the software. The whole topic is based on the birefringence which has a lot possible usage in industry, so the software can be easily develop in new ways based on my work.


Please sign in to download the files of this thesis.