This paper presents an approach for creating realistic shadows of objects composited into a novel background. Existing techniques either do not deal with the shadows or require th...
Long-duration tracking of general targets is quite challenging for computer vision, because in practice target may undergo large uncertainties in its visual appearance and the unc...
This paper investigates the digital reconstruction of destroyed buildings from small sets of old, uncalibrated photographs. The application domain is the heritage preservation of ...
Christopher de Kadt, James E. Gain, Patrick Marais
— Orthogonal Neighborhood Preserving Projections (ONPP) is a linear dimensionality reduction technique which attempts to preserve both the intrinsic neighborhood geometry of the ...
Segmentation of medical images is challenging due to poor image contrast and artifacts that result in missing or diffuse organ/tissue boundaries. Consequently, this task involves ...