|
|
Pattern Analysis (PA)- Lecturer
- Prof. Dr.-Ing. Joachim Hornegger
- Details
- Vorlesung
3 cred.h, benoteter certificate, ECTS studies, ECTS credits: 5, Sprache Deutsch
Time and place: Mon, Tue 8:15 - 9:45, H16
- Fields of study
- WPF MT-MA-BDV 1-4 (ECTS-Credits: 5)
WPF IuK-MA-MMS-INF 1-4 (ECTS-Credits: 5)
WPF CME-MA 1-4 (ECTS-Credits: 5)
WPF INF-MA 1-4 (ECTS-Credits: 5)
- Prerequisites / Organisational information
- Mustererkennung (früher Mustererkennung 1)
- Contents
- Aufbauend auf der Vorlesung Pattern Recognition führt die Vorlesung in das Design von Musteranalysesystemen sowie die zugrundeliegenden mathematischen Methoden ein. Die Vorlesung umfasst im Einzelnen: Fluch der Dimension, ROC-Kurve, Bias-Varianz Tradeoff, Mean Shift Algorithmus, Random-Walker und Graph Cut Segmentierung, Baumklassifikatoren, konvexe Kostenfunktionen, Chinese Restaurant Problem, Dirichlet Verteilungen, Gauß Prozesse, Haar Merkmale, AdaBoost, Probabilistic Boosting Trees, Marginal Space Learning, Random Forest Klassifikator, Kalman Filter, Partikel Filter, Reinforcement Learning, Markov Zufallsfelder, Bayes Netze.
- Recommended literature
- Christopher Bishop, Pattern Recognition and Machine Learning, Springer Verlag, Heidelberg, 2006
Richard O. Duda, Peter E. Hart und David G. Stork, Pattern Classification, Second Edition, 2004
Trevor Hastie, Robert Tibshirani und Jerome Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Second Edition, Springer Verlag, 2009
- ECTS information:
- Title:
- Pattern Recognition 2
- Credits: 5
- Prerequisites
- Pattern Recognition
- Contents
- This lecture first supplement the methods of preprocessing
presented in Pattern Recognition 1 by some
operations useful for image processing.
In addition several approaches to image segmentation are
shown, like edge detection, recognition of regions and textures and motion
computation in image sequences. In the area of speech processing
approaches to segmentation of speech signals are discussed as well as
vector quantization and the theory of Hidden Markov Models.
Accordingly several methods for object recognition are shown. Above that
different control strategies usable for pattern analysis systems are
presented and therefore also several control algorithms e.g. the
A(star) - algorithm.
Finally some formalisms for knowledge representation
in pattern analysis systems and knowledge-based pattern analysis
are introduced.
In the tutorials the methods and procedures which are presented in this
lecture are illustrated using simple exercises.
- Literature
- lecture notes
Niemann H.: Pattern Analysis and Understanding; Springer, Berlin 1990 Ballard D., Brown C.: Computer Vision; Prentice Hall, New Jersey 1982 Rosenfeld A.: Techniques for 3-D Machine Perception;
Elsevier Science Publ. B.V., Amsterdam 1986 Pratt W.: Digital Image Processing; Wiley-Interscience, New York 1991
- Additional information
- Keywords: Mustererkennung, Musteranalyse
Expected participants: 20, Maximale Teilnehmerzahl: 25
www: http://www5.informatik.uni-erlangen.de/lectures/ss-14/pattern-analysis-pa/
- Assigned lectures
- UE: Pattern Analysis Exercises
-
Lecturer: Thomas Köhler, M. Sc.
www: http://www5.cs.fau.de/lectures/ss-14/pattern-analysis-pa/exercises/
- Verwendung in folgenden UnivIS-Modulen
- Startsemester SS 2014:
- Pattern Analysis (lecture + exercises) (PA-VÜ)
- Pattern Analysis (lecture only) (PA-V)
- Department: Chair of Computer Science 5 (Pattern Recognition)
|
|
|