Sections
You are here: Home Members Köstinger Martin

Martin Köstinger

Martin K�stinger

Short CV

Martin Köstinger recieved his MSc Degree in Software Development and Business Management from the Graz University of Technology in 2009. He is currently a research assistant at the Insitute for Computer Graphics and Vision where he is involved in the Multimedia Documentation Lab (KIRAS - MDL) Project. His research is focused on Object Detection and Recognition, with a special focus on faces.

Research

  • Multi-view Face Detection
  • Face Recognition
  • Visual Speaker Identification
  • Self-supervised Learning
  • Natural image OCR

Videos

Face Recognition

media player

... from Videos only using Weakly Related Information Cues

media player

Visual Speaker Identification

media player

Optical Character Recognition in Videos (VideoOCR) and Natural Images

Source:

OCR

Image with inpainted text:

OCR

Student Projects

How George-Bush(y) is your nose? Project Type Sem./Proj., Bachelors Project
Status Open
Topic Description Expemplar based Face Recognition! Train classifiers to recognize the presence or absence of aspects of visual appearance Attributes like e.g. male/female, hair color, mustache Similarity to prototypes e.g. nose like George Bush.
Requirements MATLAB, C++, Interest in Machine Learning and Computer Vision
Contact koestinger(at)icg.tugraz.at
Information Link to ICG opportunities
Robust Visual Speaker Identification Project Type Sem./Proj., Bachelors Project
Status Open
Topic Description Detect in real-world scenes if a person is speaking or not
Requirements MATLAB, C++, Interest in Machine Learning and Computer Vision
Contact koestinger(at)icg.tugraz.at
Information Link to ICG opportunities
Optical Character Recognition in Videos Project Type Sem./Proj., Bachelors Project
Status Open
Topic Description Optical Character Recognition in Videos. Improve existing video OCR approach with some features. E.g. different character extraction oder segmentation.
Requirements MATLAB, C++, Interest in Machine Learning and Computer Vision
Contact koestinger(at)icg.tugraz.at



Publications

2011

  1. Annotated Facial Landmarks in the Wild: A Large-scale, Real-world Database for Facial Landmark LocalizationMartin Koestinger, Paul Wohlhart, Peter M. Roth, and Horst Bischof In First IEEE International Workshop on Benchmarking Facial Image Analysis Technologies, 2011
  2. Learning to Recognize Faces from Videos and Weakly Related Information CuesMartin Koestinger, Paul Wohlhart, Peter M. Roth, and Horst Bischof In Proc. IEEE Int'l Conf. on Advanced Video and Signal-Based Surveillance, 2011
  3. Multiple Instance Boosting for Face Recognition in VideosPaul Wohlhart, Martin Koestinger, Peter M. Roth, and Horst Bischof In Proc. DAGM Symposium, 2011
  4. Learning Face Recognition in Videos from Associated Information Sources Paul Wohlhart, Martin Koestinger, Peter M. Roth, and Horst Bischof In Proc. Workshop of the Austrian Association for Pattern Recognition, 2011

2010

  1. Video Detection of Dangerous Goods Vehicles in Road Tunnels Josef Birchbauer, Martin Koestinger, Paul Wohlhart, Peter M. Roth, Horst Bischof, and Claudia Windisch In Proc. Tunnel Safety and Ventilation, 2010
  2. Automatic Detection and Reading of Dangerous Goods PlatesPeter M. Roth, Martin Koestinger, Paul Wohlhart, Horst Bischof, and Josef Birchbauer In Proc. IEEE Int'l Conf. on Advanced Video and Signal-Based Surveillance, 2010

2010

  1. Planar Trademark and Logo RetrievalMartin Koestinger, Peter M. Roth, and Horst Bischof Technical Report, Graz University of Technology, Inst. f. Computer Graphics and Vision, ICG-TR-10/01, 2010 (Presented at Computer Vision Winter Workshop 2010)

2009

  1. KIRAS-MDL State-of-the-Art Report Martin Koestinger, Paul Wohlhart, Peter M. Roth, and Horst Bischof Technical Report, Graz University of Technology, Inst. f. Computer Graphics and Vision, ICG-TR-09/09, 2009

2009

  1. An Object Recognition System for planar Trademark and Logo Retrieval Martin Koestinger MSc. Thesis, Graz University of Technology, Faculty of Computer Science, 2009




Document Actions
[Powered by Plone]