This section provides an overview of the research activities of the CVL. The research in the group is guided by two principles:

• Develop sound theories that allow to predict results of methods without the need for trial and error
• Experience shows that expert knowledge from different disciplines is important in many applications, but very difficult to asses

Hence our goal is to acquire such know-how; avoid as much as possible the need for verbal definitions and use instead interactive, graphical, iconic communications.

• Object Recognition
  • Content-Based Image and Video Tagging
  • Robust Local Video and Image Features
  • Large Scale Object Recognition
  • Efficient Replica Detection
• Document Analysis
  • Text Classification and Writer Identification
  • Segmentation
  • Layout Analysis
  • Multispectral Imaging
• Video Analysis
  • Motion detection
  • Object tracking
  • Scene Analysis
• 3D Vision
  • Calibration
  • Stereo Vision
  • Structured Light