Image Processing and Pattern Recognition 2

Course guarantor:

Lecturer:

Tutor:

Supervisor:

Department of Mathematics

Synopsis:

The course is a continuation of ROZ1. Major attention is paid to features for shape description and recognition, and to general pattern recognition techniques. Numerous applications and experimental results are presented in addition to the theory.

Requirements:

passing of ROZ1

Syllabus of lectures:

features for description and recognition of 2-D shapes

invariant features, Fourier descriptors, moment invariants, differential invariants

statistical pattern recognition, supervised and nonsupervised classification, NN- classifier, linear classifier, Bayessian classifier

clustering in a feature space, iterative and hierarchical methods

dimensionality reduction of a feature space

Syllabus of tutorials:

simple 2D visual features

Fourier descriptors

basic classification algorithms

cluster analysis - simple examples

Study Objective:

to teach students the basics of object recognition

Study materials:

Duda R.O. et al., Pattern Classification, (2nd ed.), John Wiley, New York, 2001

Media and tools: a complete set of lecture slides and excersises are available at http://zoi.utia.cas.cz/ROZ2

Note:

Further information:

No time-table has been prepared for this course

The course is a part of the following study plans:

• Jaderná a částicová fyzika (elective course)
• Nuclear and Particle Physics (elective course)