Multi-Scale Image Analysis Inspired by Biological Vision

Notion of scale in physics and mathematics
Physics of observation, apertures
Axiomatic derivation of filters
Differentiation, scale and regularization
History of scale-space theory
The human visual pathway, receptive field structure
Retinal distribution of receptive fields, feedback in the visual system
Information processing in the visual cortex
Multi-scale (Gaussian) derivatives, their properties and the diffusion equation
Some differential geometry on images in 2D, 3D, 2D-time for robust feature detection and shape analysis
Geometric invariants, landmarks
Derivation of formulas for isophote curvature in 2D and 3D, high order differential features (a.o. corners, T-junctions)
Applications in medical imaging: computer-aided detection (CAD)
Mathematical morphology, multi-scale erosion and dilation
Nonlinear, geometry-driven diffusion (evolution of images by partial differential equations), edge preserving smoothing
Deep structure of images, edge focusing, multi-scale watershed segmentation
Top-points, winding numbers and SIFT features, content based image retrieval
Multi-orientation analysis, enhancing lines (even when crossing)

Type of event: 
course (spread out over multiple weeks)
Organizing university/company: 
Eindhoven University of Technology and University of Maastricht
Organizing institute/department: 
Department of Biomedical Engineering
Location (city, country): 
Eindhoven
URL that links to schedule & location: 
http://bmia.bmt.tue.nl/Education/Courses/FEV/course/index2012-BME.html
URL that links to detailed description: 
http://bmia.bmt.tue.nl/Education/Courses/FEV/course/index2012-BME.html
Contact person (email): 
prof.dr.ir. Bart M. ter Haar Romeny <B.M.terHaarRomeny@tue.nl>
Target audience (level): 
PhD students and Postdocs