|
|
|
|
Filip Malmberg | Research | Publications | Teaching
This page contains brief descriptions of the research projects I am involved with. For more details, please see the publications page.
Image segmentation, the process of identifying and separating relevant objects and structures in an image, is a fundamental probelm in image analysis. Accurate segmentation is often required for further processing and analysis of the image can be applied. Despite years of active research, general image segmentation remains an unsolved problem. Semi-automatic, interactive segmentation methods use human expert knowledge as additional input, thereby making the segmentation problem more tractable. A successful semi-automatic method minimizes the required user interaction time, while maintaining tight user control to guarantee the correctness of the result.
In this project, we are developing methods for interactive segmentation of 2- and 3-dimensional images, with focus on graph-based methods.
The manual step in semi-automatic segmentation of medical volume images typically involves initialization procedures such as placement of seed-points or positioning of surface models inside the object to be segmented. The initialization is then used as input to an automatic algorithm. In this project, we investigate how such interaction tasks can be facilitated by using a combined stereoscopic and haptic display.
A software package for interactive visualization and segmentation developed within this project has been released under an open-source license. The package is available for download from the project webpage.
In this project we develop image analysis tools for studying the 3-dimensional microstructure of paper and other fibrous materials. On a microscopic scale, paper consists of wood fibres that bind together in a complex network. The properties of this network are related to the macroscopic properties of the material, so measurements of the microstructure can be used to increase our understanding of the material and how it can be improved. The data used in this project is 3D images of different types of paper and composite materials, produced using micro-CT.
