Dr.-Ing. Thomas Käster, PhD

Data Scientist, Project Manager

Raum 1.018

Institut für Neuro- und Bioinformatik
Ratzeburger Allee 160 (Geb. 64)
23562 Lübeck

Email:
Phone:
+49 451 8836818
Fax:
+49 451 8836819

Curriculum Vitae

Research interests

The research interests of Thomas Kaester lie in the field of computer vision, pattern recognition, machine learning, image processing, and computer graphics. In particular, he is interested in:

  • big data and analysis
  • object detection, tracking and recognition
  • human-machine interaction
  • medical image processing
  • action detection and classification in videos
  • computer animation and visualization
  • the design of intelligent / cgnitive vision systems
  • image and video retrieval (including short-term and long-term learning)
  • industrial image processing

TEACHING

 

SUPERVISION - Theses

Current:

Mathis LichtenbergerBacheloriPhone Foto App Entwicklung

 

Finished:

Florian MarkowskyBachelorKonzeption und Implementierung eines Systems zu Time-of-Flight Kamera basierter Navigation in Videos
Dirk HansenDiplomFast Object Detection

Michael Brehler

MasterTissue Segmentation and Analysis
Tobias MeyerMasterObject Recognition and Retrieval
Kai RöhrBachelorImage Stitching and Mosaicing
Tobias MendeBachelorMerkmalsbasierte Qualitäts- und Ästhetikbewertung von Fotografien
Sebastian FischerBachelorComputergestützte Herstellung von Biochips durch den Einsatz von Bildverarbeitungsmethoden
Frederick KaiserBachelorEinsatz digitaler Bildverarbeitung zur Analyse von Zellkulturen
Thomas KlähnDiplomKonzeption und Implementierung eines Systems zur inhaltsbasierten Bildsuche
Marten Heidemeyer
(Bachelor)		BachelorObject Recognition and Scene Classification
Imre GoretzkiAutobildkollage
Jason KrauseBachelorEntwicklung einer Stereobild-basierten Anwendung auf einer Mobilplattform

 

OPEN Thesis TOPICS

  • Brain Tissue Segmentation and Analysis (Mdical Image processing)
  • Automatic Image Tagging (Computer Vision)
  • Object Detection (Computer Vision)
  • Scene Classification(Computer Vision

 

Internships

  • Christina Kluck, 01.10.2012 bis 28.02.2013: Klassifikation von Zellen mittels Durchlichtaufnahmen.

 

Student Assistants

  • Sebastian Fischer
  • Marvin Töllner
  • Sven Friedrichs

 

Former Student Assistants

  • Folke Will
  • Uinonah Weise

 

Projects

  • Project manager of cooperation with EUROIMMUN AG

Publikationen

2015

  • Lars Hertel and Erhardt Barth and Thomas Käster and Thomas Martinetz: Deep Convolutional Neural Networks as Generic Feature Extractors. in Proc. 2015 IEEE International Joint Conference on Neural Networks (IJCNN), Killarney, Ireland, 2015
    BibTeX Link 
    @inproceedings{HeBaKaMa15,
author = {Lars Hertel and Erhardt Barth and Thomas K{\"a}ster and Thomas Martinetz},
title = {Deep {C}onvolutional {N}eural {N}etworks as {G}eneric {F}eature {E}xtractors},
booktitle = {Proc. 2015 {IEEE} International Joint Conference on Neural Networks (IJCNN)},
address = {Killarney, Ireland},
owner = {Hertel},
year = {2015},
timestamp = {2015.05.13},
url = {http://webmail.inb.uni-luebeck.de/inb-publications/pdfs/HeBaKaMa15.pdf},
}

2014

  • Bogdan Miclut and Thomas Käster and Thomas Martinetz and Erhard Barth: Committees of deep feedforward networks trained with few data. arXiv:1406.5947v1[cs.CV], 2014
    BibTeX Link 
    @article{MiKaMaBa14,
author = {Bogdan Miclut and Thomas K{\"a}ster and Thomas Martinetz and Erhard Barth },
title = {Committees of deep feedforward networks trained with few data},
journal = {arXiv:1406.5947v1[cs.CV]},
year = {2014},
url = {http://webmail.inb.uni-luebeck.de/inb-publications/pdfs/MiKaMaBa14.pdf},
}

2013

  • Mike Wellner and Thomas Käster and Thomas Martinetz and Erhardt Barth: Optimizing depth-of-field based on a range map and a wavelet transform. in Mobile Computational Photography, no. 8667D, Proceedings of SPIE, 2013
    BibTeX Link 
    @inproceedings{WeKaMaBa13,
author = {Mike Wellner and Thomas K{\"a}ster and Thomas Martinetz and Erhardt Barth},
title = {Optimizing depth-of-field based on a range map and a wavelet transform},
booktitle = {Mobile Computational Photography},
publisher = {Proceedings of SPIE},
year = {2013},
volume = {8667D},
url = {http://webmail.inb.uni-luebeck.de/inb-publications/pdfs/WeKaMaBa13.pdf},
}

2012

  • T. Binder and F. Kriener and C. Wichner and M. Wille and M. Wellner and T. Käster and T. Martinetz and E. Barth: How to make a small phone camera shoot like a big DSLR: creating and fusing multi-modal exposure series. in Human Vision and Electronic Imaging XVII, no. 8291, 2012
    BibTeX Link 
    @inproceedings{BiKrWiWiWeKaMaBa12,
author = {T. Binder and F. Kriener and C. Wichner and M. Wille and M. Wellner and T. K{\"a}ster and T. Martinetz and E. Barth},
title = {How to make a small phone camera shoot like a big {DSLR}: creating and fusing multi-modal exposure series},
booktitle = {Human Vision and Electronic Imaging XVII},
series = {Proceedings SPIE},
volume = {8291},
year = {2012},
doi = {10.1117/12.905560},
url = {http://webmail.inb.uni-luebeck.de/inb-publications/pdfs/BiKrWiWiWeKaMaBa12.pdf},
}