Detta är ett uppsatsförslag hämtat från Nationella Exjobb-poolen. Klicka här för att komma tillbaka till samtliga exjobbsförslag.
Test of image analysis parameters
This masters thesis project deals with image analysis and statistics. Two different aims are defined. It would be suitable to have two students working on the two different parts of the project.
The aim of this part of the project is to study the accuracy of the image analysis methods used. Image analysis parameters can be measured in different ways. Several different parameters have been developed for the project. We need to determine the variability of results associated with the different parameters. Particles are randomly placed on a surface; about 100 are imaged at one time. The position of the particles and the distance between the particles and the camera can influence the results. We suggest that a reference sample of particles is imaged 10 times, removing and replacing the particles for each image. Plus images are to be taken at different distances between the object and camera for each of the 10 images. In this way we can determine the standard deviation in the results for the different parameters.
The aim of this part of the project is to study how different aspects of the particles are measured with respect to the different parameters. For example: the length of a particle can be represented by many different parameters, the length of a superscribed rectangle, the length of a superscribed ellipse, the longest ferret diameter and more. The superscribed rectangle can be determined in different ways with image analysis. The aim is to evaluate the differences in parameters and how they influence results.
The advisor of the project is Docent Joanne Fernlund. You will also work in close cooperation with other master students working on associated projects and well as doctorate student Mimmi Arvidsson responsible for the geophysical studies.
Informationen om uppsatsförslag är hämtad från Nationella Exjobb-poolen.