Image Segmentation and Mathematical Modeling
  • FENS
  • Image Segmentation and Mathematical Modeling

You are here

Image Segmentation and Mathematical Modeling of Automatic Local
Selective Segmentation

Lavdie Rada
Centre for Mathematical Imaging Techniques and
Department of Mathematical Sciences,
University of Liverpool, United Kingdom

Tuesday, January 3rd, 13:40-14:30, FENS G029

Variational level-set based segmentation methods distinguish all
objects in an image foreground from its background. Such tasks, still
remaining challenging for multiphases, have been deeply investigated
by many researchers. In operational applications requiring selection
such as medical imaging of a particular organ or CCTV monitoring of a
subject, the commonly known models are not capable of doing such a
selection task. The main challenge in a selective image segmentation
problem is how to differentiate one feature from another similar (or nearby) feature or to avoid selecting spurious features. In this talk I will first present a general overview of segmentation, as an image processing which refers to the process of locating objects and boundaries in images, and in the second part of the talk I will introduce a dual level-set selective segmentation (DLSS) model with a combination of the edge detection and geometric distance functions, which can differentiate two objects having similar or identical intensities. The DLSS model uses a combination of two level-sets: a global level-set which segments all boundaries, and a local level-set which evolves and finds the boundary of the object closest to the geometric constraints (markers). Numerical tests show that the proposed model is robust in locally segmenting complex image structures.

Lavdie Rada who was born on May the 17th of 1979 in Diber / Albania,
obtained her first degree in Natural Sciences Faculty in Tirana from a
5 year honor degree program. After completion of the program she
received a lectureship position in Polytechnic University of Tirana
and started the master degree in Applied Mathematics while teaching in
the same institute. She received a scholarship from University of
Liverpool's Mathematical Sciences Department on October 2009 and
started as a PhD student and a Teaching Assistant which still
continues up to now. She is involved in research fields of Applied
Mathematics, Numerical Analysis, Partial Differential Equations,
Denoising and Segmentation in Images, Statistics, Optimization,
Computational Finance until choosing her current main research field
of "Fast Iterative Methods for Variational Models of Image
Segmentation" under the supervision of Prof. Ke Chen.