"Bag of words" models have enjoyed much attention and achieved good performances in recent studies of object categorization. In most of these works, local patches are mo...
Non-rigid object alignment is especially challenging when only a single appearance template is available and target and template images fail to match. Two sources of discrepancy b...
An approach is suggested for arguing that a system is dependable. The key idea is to structure the system so that critical requirements are localized in small, reliable subsets of ...
A measure of stability for a wide class of pattern recognition algorithms is introduced to cope with overfitting in classification problems. Based on this concept, constructive me...
Local feature approaches to vision geometry and object recognition are based on selecting and matching sparse sets of visually salient image points, known as `keypoints' or `p...