Computational Vision at CB, CSC, KTH

Image based matching and recognition

We perform basic research in the areas of spatial and spatio-temporal recognition to develop new methods for

• recognizing previously seen objects from novel views,
• classifying previously unseen objects into object categories, and
• recognizing human activities and spatio-temporal events.

The overall methodogy is based on image measurements in terms of receptive fields expressed in terms Gaussian derivatives and differential invariants as obtained from scale-space theory.

Scale-space theory for visual operations

Scale-space theory was originally developed as a principled framework for handling image structures at different scales. Now, it has evolved into a general theory of visual operations. We perform theoretical, algorithmic and experimental work to generalized this theory, in particular concerning new methods for feature detection and image descriptors.

There are close similarities between receptive fields as obtained by necessity from scale-space theory and receptive field profiles registered in biologicial vision. We perform work on relating scale-space theory to biological vision.

Analysis of biomedical image data

Computer vision tools can be used for analysing biomedical image data in 2-D, 3-D as well as time-dependent images in 2+1-D or 3+1-D. In previous work, we have applied scale-space methodologies to tasks such as detecting regions of locally high activity in functional brain activation images, registration of 3-D MR images to standard anatomical format and segmenting the brain from surrounding tissue.