Research Areas
Areas
General Interests
Computer Vision and Graphics, Medical Vision, Neuro Imaging, Differential and Computational Geometry, Computational Topology, Human Computer Interaction
Shape Analysis (Recognition, Matching, Registration)
| |
|
Shape analysis falls under Computer Vision as it tries to extract information from graphical or image data.
Concepts from differential and computational geometry and topology are necessary to model the shape and the
methods for shape processing. Shape analysis is an umbrella term for shape matching and recognition,
shape reconstruction and segmentation, shape parametrization and registration and probably more.
So far, I worked on isometry (pose) invariant shape matching/recognition and on segmentation.
See the following links for more
details and examples of database retrieval applications:
More Details on Isometry Invariant Shape Analysis
Database Retrieval Example I
Database Retrieval Example II
|
|
|
Neuro Imaging and Medical Vision
| |
|
Neuroimaging tries to image
the structure and function of the brain.
Vision is the process of automatically processing images and shapes in order to
extract information. Often a registration and segmentation of the shape is needed so
shape reconstruction and shape analysis are central components of neuro vision
(see for example the image at the left for a cortical segmentation of my brain, left hemisphere).
I have done statistical morphometric studies on populations of subcortical brain structures in
schizotypal personality disorder (see publications).
|
|
|
Geometric Modeling, Computer Aided Design
| |
|
Geometric model(l)ing is the construction or use of geometric models. Geometric models are used in computer graphics, computer-aided design and manufacturing, and many applied fields such as medical image processing.
But not only the models themselves are of interest, but also robust tools to process them (such as intersection, union, continuous attachment ...).
An important sub-field are curves and (subdivision) surfaces (B-Splines, NURBS, ...) that can be employed for modeling the shapes,
as well as for analytic purposes (e.g. the solution of multinomial systems, see my publications).
I also studied the medial axis (a skeletal shape representation) and its usability for shape parametrization (to combine
design, meshing, FEM analysis and possible automatic design optimization).
|
|
|
