Statistical model of the 2001 Czech Census for Interactive Presentation

Presentations:
A Statistical Approach to Local Evaluation of a Single Texture Image: pdf
Distribution mixtures I (in czech): pdf
Distribution mixtures II (in czech): pdf

Head of the Department:
Michal Haindl

Deputy head of the Department:
Jiří Grim

Secretary:
Jana Krejčová

phone: +420 266 052 505
www: http://ro.utia.cas.cz/
staff: people, Ph.D. students
List of publications, courses, projects

The scope of the activities of the Department of Pattern Recognition covers statistical pattern recognition, with emphasis being put on model-based pattern recognition and the application of finite mixtures, modeling of random fields for scene interpretation, probabilistic neural networks, statistical feature selection and applications in economics, the car industry, architecture, medicine, and text-document classification and processing. In all these areas, the group members enjoy an international reputation manifested by scientific awards and memberships in the governing bodies of international organizations.

Recent news:

Konkurz na vývoj a konstrukci jednoúčelového měřicího zařízení

Konkurz na vývoj a konstrukci jednoúčelového měřicího zařízení Konkurz bude uzavřen 5.3. 2010 ve 24 hodin. Měřící zařízení založené na dvou sklopných ramenech v úhlech -90 až 90 stupňů. Jedno rameno navíc rotuje okolo svislé osy v rozmezí -90 až 90 stupňů. Součástí je také otočný stolek otočný v rozmezí -180 až 180 stupňů. Podrobnosti zadání naleznete zde.

Featured article in November issue of IEEE TPAMI

The IEEE TPAMI selected the article:

Filip J., Haindl M.:Bidirectional Texture Function Modeling: A State of the Art Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 31, no. 11, pp. 1921-1940, Oct. 2009

as a featured article of the November issue.

Přednáška Petra Somola

Konání: 18.ledna (pátek) v 10:00 bude v rámci semináře ZOI pořádaná přednáška Petra Somola

Are Better Feature Selection Methods Actually Better?

One of hot topics discussed recently in relation to pattern recognition techniques is the question of actual performance of modern feature selection methods.

• 1
• 2
• 3
• next ›
• last »