The Department is involved in basic research in image processing and pictorial pattern recognition. Major application areas are biomedicine, remote sensing, astronomy, and art conservation.
Main scientific areas
Recognition of distorted images and patterns by invariant descriptors regardless of their actual position in the scene
Registration and fusion of several images of the same scene taken at different times, by different sensors and/or from different viewpoints in order to obtain information of higher quality
Theory of moment invariants, namely of rotation invariants, affine invariants and invariants to convolution
Restoration of degraded images, namely multichannel blind deconvolution, edgepreserving denoising, local contrast enhancement, and color transformations
Image forensics - detection of image forgeries
Cultural heritage applications - cooperation with art conservators in order to facilitate the conservation and material analysis work
The aim of the VKG 3.0 project is a new system for the diagnosis of vocal disorders, consisting of a new type of multi-line video camera and data processing software.
Bilateral cooperation with University of Antwerp: Separating the invisible from the visible: mixture analysis of macroscopic elemental maps of valuable paintings
PROVENANCE is an intermediary-free solution that gives greater control to users of social media and underpins the dynamics of social sharing in values of trust, openness, and fair participation. PROVENANCE will use blockchain to record multimedia content that is uploaded and registered by content creators or identified for registration by the PROVENANCE Social Network Monitor.
Objects moving fast with respect to the camera appear blurred when observed. Surprisingly this common phenomenon has not yet been considered and analyzed by the computer vision
community. It is the blur that encodes information about the object motion properties. Instead of considering blur as a nuisance, the project proposes to take it as a cue for detection and tracking of fast moving objects.
The proposal falls into the area of computer image analysis and pattern recognition. It is focused on special type of data - multidimensional vector and tensor fields. Vector fields may describe particle velocity, optical/motion flow, image gradient, deformation/condutivity/diffusion tensors,
and other phenomena.