Research Interests

Computational Vision: My long-term goal is to model an image-understanding system mimicking human categorization and search performance. The overall approach is motivated by a number of perceptual and cognitive studies and is summarized in a monograph I have written a few years ago. In the mean time, I developed an elaborate decomposition process, whose output can be used to classify (categorize) and search images to some degree. The decomposition also bears the potential for improving other applications, such as image retrieval and object detection algorithms. To work towards a perfectly categorizing system, the next hurdle is to develop grouping and learning methodology, which automatically acquires category representations. To move toward a complete image-understanding system, a framework needs to be invented, which efficiently represents and accesses scene knowledge.

 

[link to image classification]          shows results from image classification (categorization), searches and sorting.

[link to COREL category labels]    contains info about the labeling of the COREL image classes.

[link to visual search]                    discusses search aspects (e.g., regions of interest).

 

Applied Visual Perception: Human-computer interaction at visual interfaces, such as the PC monitor, is still relatively awkward. The interaction could be easily improved if human gaze position were tracked and guided toward task-relevant locations (Barth et al 2006). To realize that in practice, it requires a good concept of how to read the user’s attention and how to generate the appropriate process of gaze guidance. I have assembled a list of aspects, which allows me to systematically approach this issue, and I have carried out basic eye-movement research to investigate some of these aspects in detail. Some of my applied ideas are presently implemented in collaboration with Michael Dorr at the University of Lübeck. To gain a more detailed understanding of saccadic target selection, I have started to analyse fixation locations made in real scenes, a project done in collaboration with Ben Tatler at the University of Dundee.

 

[link to gaze guidance]                      surveys my part of the research collaboration.

[link to applied project]                     a gaze-recapturing editor cursor (GREC) to improve text-editing on a PC monitor.

[link to saccadic target selection]    an analysis of saccadic target selection.

[link to project website]                     5 different European labs are involved.

 

 


Christoph Rasche