Statistische Modellierung für die Objekterkennung in Bildern

• Applicant: Professor Dr.-Ing. Hermann Ney
• Subject Area: Image and Language Processing, Computer Graphics and Visualisation, Human Computer Interaction, Ubiquitous and Wearable Computing
• Term: from 2003 to 2009
• Project identifier: Deutsche Forschungsgemeinschaft (DFG) - Project number 5412085

• Final Report Year: 2008

Final Report Abstract

No abstract available

Publications

• Maximum Entropy and Gaussian Models for Image Object Recognition DAGM 2002, pages 498-506, Zürich, Switzerland, September 2002
  Daniel Keysers, Franz-Josef Och, and Hermann Ney
  
• Tangent Distance Kernels for Support Vector Machines International Conference on Pattern Recognition, pages 864-868, Quebec City, Canada, September 2002
  Bernard Haasdonk and Daniel Keysers
  
• Clustering visually similar images to improve image search engines. In Informatiktage der Gesellschaft für Informatik, page 302, Bad Schussenried, Germany, November 2003
  Thomas Deselaers, Daniel Keysers, and Hermann Ney
  
• Comparison of log-linear models and weighted dissimilarity measures. In Iberian Conference on Pattern Recognition and Image Analysis, pages 370-377, Puerto de Andratx, Spain, June 2003. Springer Verlag
  Daniel Keysers, Roberto Paredes, Enrique Vidal, and Hermann Ney
  
• Elastic image matching is np-complete. Pattern Recognition Letters, 24:445-453, January 2003
  Daniel Keysers and Walter Unger
  
• Local representations for multi-object recognition. In Deutsche Arbeitsgemeinschaft für Mustererkennung Symposium, volume 2781 of Lecture Notes in Computer Science, pages 305-312, Magdeburg, Germany, September 2003. Springer Verlag
  Thomas Deselaers, Daniel Keysers, Roberot Paredes, Enrique Vidal, and Hermann Ney
  
• Statistical framework for model-based image retrieval in medical applications. Journal of Electronic Imaging, 12(1):59-68, January 2003
  Daniel Keysers, Jörg Dahmen, Hermann Ney, Berthold Wein, and Thomas M. Lehmann
  
• Training and recognition of complex scenes using a holistic statistical model. In Deutsche Arbeitsgemeinschaft für Mustererkennung Symposium, volume 2781 of Lecture Notes in Computer Science, pages 52-59, Magdeburg, Germany, September 2003. Springer Verlag
  Daniel Keysers, Michael Motter, Thomas Deselaers, and Hermann Ney
  
• Adaptation in statistical pattern recognition using tangent vectors. IEEE Transactions on Pattern Analysis and Machine Intelligence, 26(2):269-274, February 2004
  Daniel Keysers, Wolfgang Macherey, Hermann Ney, and Jörg Dahmen
  
• Classification error rate for quantitative evaluation of content-based image retrieval systems. In International Conference on Pattern Recognition, volume 2, pages 505-508, Cambridge, UK, August 2004
  Thomas Deselaers, Daniel Keysers, and Hermann Ney
  
• Classification of medical images using non-linear distortion models. In Bildverarbeitung für die Medizin, pages 366-370, Berlin, Germany, March 2004
  Daniel Keysers, Christian Gollan, and Hermann Ney
  
• Enhancements for local feature based image classification. In International Conference on Pattern Recognition, pages 248-251, Cambridge, UK, August 2004
  Tobias Kölsch, Daniel Keysers, Hermann Ney, and Roberto Paredes
  
• Features for image retrieval: A quantitative comparison. In Deutsche Arbeitsgemeinschaft für Mustererkennung Symposium, volume 3175 of Lecture Notes in Computer Science, pages 228-236, Tübingen, Germany, September 2004
  Thomas Deselaers, Daniel Keysers, and Hermann Ney
  
• Linear discriminant analysis and discriminative log-linear modeling. In International Conference on Pattern Recognition, pages 156-159, Cambridge, UK, August 2004
  Daniel Keysers and Hermann Ney
  
• Local context in non-linear deformation models for handwritten character recognition. In International Conference on Pattern Recognition, pages 511-514, Cambridge, UK, August 2004
  Daniel Keysers, Christian Gollan, and Hermann Ney
  
• Pixel-to-pixel matching for image recognition using hungarian graph matching. In Deutsche Arbeitsgemeinschaft für Mustererkennung Symposium, volume 3175 of Lecture Notes in Computer Science, pages 154-162, Tübingen, Germany, September 2004
  Daniel Keysers, Thomas Deselaers, and Hermann Ney
  
• Appearance-based recognition of words in american sign language. In Iberian Conference on Pattern Recognition and Image Analysis, pages 513-520, Estoril, Portugal, June 2005
  Morteza Zahedi, Daniel Keysers, and Hermann Ney
  
• Combination of tangent distance and an image distortion model for appearance-based sign language recognition. In Deutsche Arbeitsgemeinschaft für Mustererkennung Symposium, volume 3663 of Lecture Notes in Computer Science, pages 401-408, Vienna, Austria, August 2005
  Morteza Zahedi, Daniel Keysers, Thomas Deselaers, and Hermann Ney
  
• Discriminative training for object recognition using image patches. In IEEE Conference on Computer Vision and Pattern Recognition, volume 2, pages 157-162, San Diego, CA, June 2005
  Thomas Deselaers, Daniel Keysers, and Hermann Ney
  
• Fire - flexible image retrieval engine: ImageCLEF 2004 evaluation. In Multilingual Information Access for Text, Speech and Images - Fifth Workshop of the Cross-Language Evaluation Forum, CLEF 2004, volume 3491 of LNCS, pages 688-698, Bath, UK, 2005. Springer
  Thomas Deselaers, Daniel Keysers, and Hermann Ney
  
• Gesture recognition using image comparison methods. In S. Gibet, N. Courty, and J.-F. Kamp, editors, International Gesture Workshop, volume 3881 of Lecture Notes in Computer Science, pages 124-128, Ile-de-Berder, France, May 2005
  Philippe Dreuw, Daniel Keysers, Thomas Deselaers, and Hermann Ney
  
• Improving a discriminative approach to object recognition using image patches. In Deutsche Arbeitsgemeinschaft für Mustererkennung Symposium, volume 3663 of Lecture Notes in Computer Science, pages 326-333, Vienna, Austria, August 2005
  Thomas Deselaers, Daniel Keysers, and Hermann Ney
  
• Pronunciation clustering and modeling of variability for appearance-based sign language recognition. In International Gesture Workshop, volume 3881, pages 68-79, Ile-de-Berder, France, May 2005
  Morteza Zahedi, Daniel Keysers, and Hermann Ney
  
• 32] Thomas Deselaers, Andre Hegerath, Daniel Keysers, and Hermann Ney. Sparse patchhistograms for object classification in cluttered images. In Deutsche Arbeitsgemeinschaft für Mustererkennung Symposium, volume 4174 of Lecture, Notes in Computer Science, pages 202-211, Berlin, Germany, September 2006
  Thomas Deselaers, Andre Hegerath, Daniel Keysers, and Hermann Ney
  
• Continuous sign language recognition - approaches from speech recognition and available data resources. In LREC Workshop on the Representation and Processing of Sign Languages: Lexicographic Matters and Didactic Scenarios, pages 21-24, Genoa, Italy, May 2006
  Morteza Zahedi, Philippe Dreuw, David Rybach, Thomas Deselaers, and Hermann Ney
  
• FIRE in ImageCLEF 2005: Combining content-based image retrieval with textual information retrieval. In Accessing Multilingual Information Repositories, 6th Workshop of the Cross- Language Evaluation Forum, CLEF 2005, volume 4022 of Lecture Notes in Computer Science, pages 652-661, Vienna, Austria, 2006
  Thomas Deselaers, Tobias Weyand, Daniel Keysers, Wolfgang Macherey, and H. Ney
  
• Patch-based object recognition using discriminatively trained gaussian mixtures. In British Maschine Vision Conference, volume 2, pages 519-528, Edinburgh, UK, September 2006
  Andre Hegerath, Thomas Deselaers, and Hermann Ney
  
• Shared-memory parallelization for content-based image retrieval. In ECCV Workshop on Computation Intensive Methods for Computer Vision, Graz, Austria, May 2006
  Christian Terboven, Thomas Deselaers, Christian Bischof, and Hermann Ney
  
• The 2005 pascal visual object classes challenge. In Pascal Challenges Workshop, number 3944 in Lecture Notes in Artificial Intelligence, pages 117-176, Southampton, UK, 2006
  Mark Everingham, Andrew Zisserman, Christopher K. I. Williams, Luc van Gool, Moray Allan, Christopher M. Bishop, Olivier Chapelle, Navneet Dalai, Thomas Deselaers, Gyuri Dorko, Stefan Duffner, Jan Eichhorn, Jason D. R. Farquhar, Mario Fritz, Christophe Garcia, Tom Griffiths, Frederic Jurie, Daniel Keysers, Markus Koskela, Jorma Laaksonen, Diane Larlus, Bastian Leibe, Hongying Meng, Hermann Ney, Bernt Schiele, Cordelia Schmid, Edgar Seemann, John Shawe-Taylor, Amos Storkey, Sandor Szedmak, Bill Triggs, Ilkay Ulusoy, Ville Viitaniemi, and Jianguo Zhang
  
• Tracking using dynamic programming for appearance-based sign language recognition. In IEEE International Conference Automatic Face and Gesture Recognition, IEEE, pages 293-298, Southampton, UK, April 2006
  Philippe Dreuw, Thomas Deselaers, David Rybach, Daniel Keysers, and Hermann Ney
  
• Using geometric features to improve continuous appearance-based sign language recognition. In British Maschine Vision Conference, volume 3, pages 1019-1028, Edinburgh, UK, September 2006
  Morteza Zahedi, Philippe Dreuw, David Rybach, Thomas Deselaers, and Hermann Ney
  
• Deformation models for image recognition. IEEE Transactions on Pattern Analysis and Machine Intelligence, 29(8):1422-1435, August 2007
  Daniel Keysers, Thomas Deselaers, Christian Gollan, and Hermann Ney
  
• Image retrieval and annotation using maximum entropy. In C. Peters, P. Clough, F. Gey, J. Karlgren, B. Magnini, D.W. Oard, M. de Rijke, and M. Stempfhuber, editors, Evaluation of Multilingual and Multi-modal Information Retrieval - Seventh Workshop of the Cross-Language Evaluation Forum, CLEF 2006, volume 4730 of LNCS, pages 725-734, Alicante, Spain, 2007
  Thomas Deselaers, Tobias Weyand, and Hermann Ney
  
• Incorporating ondemand stereo for real time recognition. In IEEE Conference on Computer Vision and Pattern Recognition, Minneapolis, MN, USA, June 2007
  Thomas Deselaers, Antonio Criminisi, John Winn, and Ankur Agarwal
  
• Management und Verarbeitung medizinischer multimedialer Daten. In Achim Jöckel, editor, Telemedizinführer, pages 228-235. Medzin Forum AG, 1 edition, June 2007
  Henning Müller, Thomas Deselaers, Thomas M. Lehmann, and Antoine Geissbuhler
  
• Optimal geometric matching for patch-based object detection. Electronic Letters on Computer Vision and Image Analysis, 6(1):44-54, June 2007
  Daniel Keysers, Thomas Deselaers, and Thomas M Breuel
  
• Reducing time and RAM requirements in content-based image retrieval using retrieval filtering. In Informatiktage der Gesellschaft fur Informatik, Lecture Notes in Informatics, pages 143-146, Bonn, Germany, March 2007
  Jens Forster and Thomas Deselaers
  
• Robust Appearance-based Sign Language Recognition. PhD thesis, RWTH Aachen University, Aachen, Germany, September 2007
  Morteza Zahedi
  
• Speech recognition techniques for a sign language recognition system. In Interspeech, pages 2513-2516, Antwerp, Belgium, August 2007
  Philippe Dreuw, David Rybach, Thomas Deselaers, Morteza Zahedi, and Hermann Ney
  
• The CLEF 2005 automatic medical image annotation task. International Journal of Computer Vision, 74(1):51-58, August 2007
  Thomas Deselaers, Henning Müller, Paul Clough, Hermann Ney, and Thomas M Lehmann
  
• Efficient approximations to model-based joint tracking and recognition of continuous sign language. In IEEE International Conference Automatic Face and Gesture Recognition, Amsterdam, The Netherlands, September 2008
  Philippe Dreuw, Jens Forster, Thomas Deselaers, and Hermann Ney
  
• Exploring the relationship between feature and perceptual visual spaces. Journal of the American Society for Information Science and Technology, 59(5):770-784, March 2008
  Abebe Rorissa, Paul D Clough, and Thomas Deselaers
  
• Features for image retrieval: An experimental comparison. Information Retrieval, 11(2):77-107, 2008
  Thomas Deselaers, Daniel Keysers, and Hermann Ney
  
• GIS-like Estimation of Log-Linear Models with Hidden Variables IEEE International Conference on Acoustics, Speech, and Signal Processing, pages 4045-4048, Las Vegas, NV, USA, April 2008
  Georg Heigold, Thomas Deselaers, Ralf Schlüter, and Hermann Ney