Eventi | Seminari e Convegni

Home Eventi | Seminari e Convegni


Darshan Batavia

TU Wien
Institute of Visual Computing & HC Technology
Pattern Recognition and Image Processing Group


A digital image can be perceived as a 2.5D surface consisting
of pixel coordinates and the intensity of pixel as height of the point in the
surface. Such surfaces can be efficiently represented by the pair of dual
plane graphs: neighborhood (primal) graph and its dual. By defining ori-
entation of edges in the primal graph and use of Local Binary Patters
(LBPs), we can categorize the vertices corresponding to the pixel into
critical (maximum, minimum, saddle) or slope points. Basic operation of
contraction and removal of edges in primal graph result in configuration
of graphs with different combinations of critical and non-critical points.

The face of the graph or the space between the critical points is defined as
slope region. The talk will be focused on the difference between a slope region
and a slope district which are traditionally formed by the watershed and image
morphology. Also we can observe the advantages of irregular pyramid over regular
pyramid, especially in application of image segmentation. Lastly we will focus on
merging of segments such that the resulting segments follow the topological
definition of the slope region.

il seminario si terrà nell'aula dei consigli del DIEM.