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
Optical character recognition is an excellent area for studying and evaluating approaches to these problems, as well as a useful application. We are currently building a system called OCRopus, designed for large scale digital library applications.  A second application is high quality 3D capture of books and art using low-cost digital cameras as part of project DECAPOD.  As part of project PaREn, we are creating datasets and tools intended to improve the evaluation and validation of pattern recognition methods.  The MOVIMOS and Moonvid projects are creating a next-generation content-based image retrieval system, also with applications to forensics and security.

IUPR is funded through industrial contract research and public research grants (EU, federal, state).

Appointments

To make an appointment, please use the link below.  On that form, you should indicate a range of times you are available plus a duration for the meeting.   It is best if you select blocks of time on two or more days.  The blocks you select can (and should) be longer than the meeting you are proposing.

Schedule a Meeting

Contact

Director
Mailing Address
Prof. Dr. Thomas Breuel
Building. 48, Room 459
Technical University of Kaiserslautern
Gottlieb-Daimler-Str., 67663 Kaiserslautern, Germany
Phone
 ++49 (0)631 205-3456
FAX
++49 (0)631 205-3357
Group E-mail
job applicants: jobs@iupr.com
general messages: secretary@iupr.com




 

Projects





OCRopus Book OCR System

High performance document image processing, document analysis, character recognition, and statistical language processing.  OCRopus is made possible by the generous support from Google and the TextGrid project.

DECAPOD

3D Capture, Dewarping, and Archival Conversion of Books and other Historical Objects


Acknowledgements


Some of the organizations that have sponsored our work: