photo of Arjan Kuijper

VO : Signal- und Bildverarbeitung, 323.014

Teaching language will be English. The course is now named: "Image analysis and processing"
Registration in KUSSS is not possible anymore, but you're welcome to attend the lectures. :)
(You'll be able to register for my summer semester course on Level Set Methods and Dynamic Impicit Surfaces in Computer Vision and Computational Physics in Februari 2007.)

Day & Time: Thursday 10:15 – 11:45
Weeks: 40-42, 45-50 (2006), 2-4 (2007)
Location: KEP 1
NOTE: This is room KH 004 at the Kepler Heim, Altenbergerstrasse 74 - not on the campus!!

Flyer

Contents:

Image analysis & processing deals with the investigation of images and the application of specific tasks on them, like enhancement, denoising, deblurring, and segmentation. In this course, mathematical methods that are commonly used are presented and discussed. The focus will be on the axiomatic choice for the models, their mathematical properties, and their practical use.

Course slides

Some key words:

Filtering (Edge detection, enhancement, Wiener, Fourier, Sobel, Canny, ...)
Images & Observations: Scale space, regularisation, distributions.
Objects: Differential structure, invariants, feature detection
Deep structure: Catastrophes & Multi-scale Hierarchy
Variational Methods & Partial Differential Methods: Perona Malik, Anisotropic Diffusion, Total Variation, Mumford-Shah.
Curve Evolution: Normal Motion, Mean Curvature Motion, Euclidian Shortening Flow.

Audience:

As image analysis and processing is a mixture of several disciplines, like physics, mathematics, vision, computer science, and engineering, this course is aimed at a broad audience. Therefore, only basic knowledge of analysis is assumed and necessary mathematical tools will be outlined during the meetings.

Examination material:

Course material exists of a collection of papers, covering the presented themes. For the Gaussian scale space part: For the non-linear part:

Other on-line available material worth reading:

References & further reading:

Examination:

Investigation and public presentation of recent work in image analysis (e.g. book chapter) provided at the course, and an oral exam on contents of the course (material & slides). Topics (preliminary timetable!): 1,2,3: 11.01.07, 4,5,6: 18.01.07, 7,8: 25.01.07.

1 Colour images and scale space Anyeva
2 Optic Flow, temporal scale space Kumar & Kho
3 Steerable kernels He & Zhou
4 PDE diffusion vs. Wavelets Muresan
5 nonlinear audio diffusion Feurer
6 Bregman distance & Total Variation Cao
7 Indexing & Reconstruction using deep structureKasumba & Ssemaganda
8 Multiscale Watershed segmentation & singularitiesLu
......
As mentioned, by answering at forehand questions out of this preliminary list, you can steer the discussion during the exam.

NEW:

For those interested in the topic: in the summer semester I'll give a course on Level Set Methods and Dynamic Impicit Surfaces in Computer Vision and Computational Physics, course ID 323022.
Home Research Teaching CV Publications Links


Arjan Kuijper / arjan.kuijper@oeaw.ac.at / updated September 4, 2006