Dr. Lokesh Setia
	Chair of Pattern Recognition and Image Processing Institute for Computer Science Albert-Ludwigs-University Freiburg Georges-Koehler-Allee 052, Room 01-021 D-79110 Freiburg i.Br., Germany
	Tel. :	+49-(0)761-203-8266
	Fax :	+49-(0)761-203-8262
	Email :

Scientific Interests

• Content-based Image Retrieval [try out a demo of an Image Search Engine]
• Image Processing
• Cognition and Machine Learning

Projects

• I-Search
• Muscle Network of Excellence

Publications (Reverse chronological order)

• Machine Learning Strategies for Content Based Image Retrieval
  Lokesh Setia
  PhD Thesis, 2008 [URL]

• Grayscale Medical Image Annotation using Local Relational Features
  Lokesh Setia, Alexandra Teynor, Alaa Halawani and Hans Burkhardt
  In Pattern Recognition Letters, Special Issue on Medical Image Annotation in ImageCLEF, 2008 [URL]

• Learning Taxonomies in Large Image Databases
  Lokesh Setia and Hans Burkhardt
  In Proceedings of the ACM SIGIR 2007 Workshop on Multimedia Information Retrieval, Amsterdam, Holland
  © ACM, 2007 [pdf]

• Block DCT Vectors Construction for Face Retrieval Based on Genetic Algorithm
  Yonghua Xie, Lokesh Setia and Hans Burkhardt
  In The 3rd International Conference on Natural Computation (ICNC'07)
  

• Object-based Color Image Retrieval Using Concentric Circular Invariant Features
  Yonghua Xie, Lokesh Setia and Hans Burkhardt
  In International Journal of Computer Sciences and Engineering Systems (to appear)
  

• Image Classification using Cluster-Cooccurrence Matrices of Local Relational Features
  Lokesh Setia, Alexandra Teynor, Alaa Halawani, Hans Burkhardt
  In Proceedings of the 8th ACM International Workshop on Multimedia Information Retrieval (MIR 2006), Santa Barbara, CA, USA, October 26-27, 2006.
  © ACM, 2006 [pdf]

• Radiograph Annotation using Local Relational Features
  Lokesh Setia, Alexandra Teynor, Alaa Halawani, Hans Burkhardt
  In Workshop on Cross Language Evaluation Forum (CLEF), Alicante, Spain, September 19-23, 2006
  [pdf] [talk]

• Feature Selection for Automatic Image Annotation
  Lokesh Setia and Hans Burkhardt
  In Proceedings of the 28th DAGM Symposium, Berlin, Germany, September 12-14, 2006
  © Springer-Verlag, 2006 [pdf]

• Properties of Patch Based Approaches for the Recognition of Visual Object Classes
  Alexandra Teynor, Esa Rahtu, Lokesh Setia and Hans Burkhardt
  In Proceedings of the 28th DAGM Symposium, Berlin, Germany, September 12-14, 2006
  © Springer-Verlag, 2006 [pdf]

• Fundamentals and Applications of Image Retrieval: An Overview
  Alaa Halawani, Alexandra Teynor, Lokesh Setia, Gerd Brunner, Hans Burkhardt
  In Datenbank-Spektrum, Heft 18, August 2006.

• Kernel Biased Discriminant Analysis using Histogram Intersection Kernel for Content-Based Image Retrieval.
  Lin Mei, Gerd Brunner, Lokesh Setia, and Hans Burkhardt
  In Proceedings of the Sixth International Conference on Intelligent Data Engineering and Automated Learning (IDEAL'05), Australia, 6th - 8th July, 2005.
  © Springer-Verlag, 2005 [pdf]
  

• SVM-based Relevance Feedback in Image Retrieval using Invariant Feature Histograms.
  Lokesh Setia, Julia Ick and Hans Burkhardt
  In Proceedings of the IAPR Workshop on Machine Vision Applications (MVA2005), Tsukuba Science City, Japan, 16-18 May 2005.
  [pdf]

• Rats are able to navigate in virtual enviroments,
  Hölscher C, Schnee A, Dahmen H, Setia L., Mallot HA
  In Journal of Experimental Biology, 208: 561-569 (2005) [abstract]

• A panoramic virtual reality interface for studying spatial cognition in rodents and man, at the Cognitive Neuroscience Group, University of Tübingen, Germany (Nov'02-April'03)

• Design and implementation of a wideband speech codec at 16-32 kbps using CELP based techniques, Indian Institute of Technology, Delhi, India (July'98-May'99)

Teaching

• Julia Ick, Comparision of content based Image Retrieval using one-class and two-class SVM, August 2004 [pdf]

• Julia Eckert, Watermark Retrieval Enhancement using Relevance Feedback, December 2005 [pdf]

• Margret Keuper, Object classification using Local Relational Features, June 2006 [pdf]

das Feuer, das mich quält, aber zugleich erhöht ist unsichtbar ist unsichtbar	ignis, quo crucior immo quo glorior ignis est invisibilis est invisibilis	the fire, that torments me, but at the same time exalts me as well is invisible is invisible