The research of the Computer Vision group is focused on the development of machine learning techniques for solving image recognition tasks.
An important problem when dealing with computer vision is the semantic gap between the high level perception of persons and the low level understanding of computers. While persons are able to immediately capture the content of an image and understand its context, computers use basic features of the image, such as edges or color to identify the image content. This group tries to bridge this gap by integrating human and machine knowledge.

Main research areas of this group include:

• Visual Analytics for video data: Human-Computer-Interaction and Visualization as a link between human and machine processing
• Semi-automatic learning for reducing the manual effort in creating data sets for training recognition systems
• Vision 2.0: efficient development of specific image recognition systems for large scale extraction of context from images

Contact