About

IUPR research focuses on large scale, practical applications of pattern recognition, image understanding, machine learning, and statistical language modeling.  The fundamental techniques we are developing are: 
  • practical learning algorithms that scale to very large problem sizes
  • automatic parameter selection and validation for pattern recognition systems
  • problem instance-specific adaptation
  • validation and benchmarking of systems
  • massively parallel methods
  • statistical analysis of text and images


Mailing Address
Prof. Dr. Thomas Breuel
Building. 48, Room 459
University of Kaiserslautern
Gottlieb-Daimler-Str.
67663 Kaiserslautern
Germany 
Phone
 ++49 (0)631 205-3456

FAX
++49 (0)631 205-3357

E-mail

Secretary: 
Ingrid Romani
Room 48-458
Phone ++49(0)631-205-3358

opening hours for students 
Monday-Friday 1:30 - 4:30 pm

Jobs
There are no job openings in IUPR.

Exam Dates / Prüfungen     

  Next timeslot for oral exams will be in July 2014 before the semester ends.

        For scheduling exam dates (Prüfungen), please contact secretary@iupr.com.

        Remember to register with the "Prüfungsamt" lastest 14 working days in advance!



Appointments
Please send mail to secretary@iupr.com

Acknowledgements
Some of the organizations that have sponsored our work:

      




Lectures / Projects WiSe 2013/14

89-7256 Multimedia Information Retrieval

Lernziele/Goals

Multimedia information retrieval is increasingly used in online services, such as Picasa, Google Books and Google Scholar, YouTube, and Facebook. Students have an understanding of information retrieval systems for text, images, videos, and audio, and the underlying statistical and algorithmic methods.

Inhalte/Contents

  • models of information retrieval
  • nearest neighbors, range queries, hash algorithms
  • PLSA and topic models vector space models
  • text categorization, analysis, tagging, parsing
  • content based image and video retrieval
  • image retrieval based on color, texture, and shape
  • visual bag of words model
  • grouping, static and motion segmentation, scene cuts
  • geometric indexing, verification, and object recognition
  • automatic annotation and categorization
  • HMM-based methods (audio, video, music, document retrieval)
  • generative and discriminative methods
  • selected special purpose applications, such as face detection, x-ray image analysis
  • performance evaluation and competitions
  • applications in consumer imaging, security, forensics, and copyright and plagiarism detection

Thursdays, 13:45 - 15:15h in 48-462

89-7258 Self-Organization and Simulation

Lernziele/Goals

An understanding of the mathematical principles and models of self-organization and their computational realization and simulation. Applications in biology, economics, social sciences, and physics.

Inhalte/Contents

  • mathematical models of competition, evolution, and economic activities
  • Ontogeny and phylogeny
  • Pattern formation and communication in biological systems.
  • Multi-agent and intelligent agent modeling and analysis.
  • Techniques for large-scale simulation.
  • Applications of self-organization to the creation of structures.
  • Applications of computational science to testing biological, social, and economic theories.
  • Organic computing.

Wednesdays, 13:45 - 15:15 in 48-462

89-7245 und 89-1381 Project Bachelor und Master:

Pattern Recognition, Machine Learning, Image Understanding

The goal of this semester's master project (advanced bachelor students welcome) is to work on making better and more intelligent 3D printers. This includes adding computer vision and image analysis to existing printers for failure detection, computing and learning control programs for printing, coming up with better mechanical designs, and creating a nearly fully printed 3D printer.

Technologies / skills:

  • 3D printing
  • computer vision
  • embedded controllers / stepper motors
  • minimal mechanical construction
  • 3D modeling (Blender, etc.)
  • a sense of fun and interest in cutting edge, open source technologies
  • Home page: http://project13.iupr.com/

Einführung/Introduction Monday, November 4, 13:30 h in 48-459

89-7271 und 89-7211 Seminar: Topics in Pattern Recognition (Bachelor und Master)

This semester's seminar topics are on papers related to 3D printing:
  • techniques for 3D printing
  • printable electronics
  • food printing
  • 3D design and printing software
  • relationships between robotics and 3D printing

Einführung/Intnroduction Monday, October 28, 16:15h in 48-459