We investigate the application of a new category of low-level image descriptors termed interest points to remote sensed image analysis. In particular, we compare how scale and rot...
Abstract. We introduce a new type of local feature basedon the phaseand amplitude responsesof complex-valuedsteerable filters. The designof this local feature is motivated by a des...
Invariant feature descriptors such as SIFT and GLOH have been demonstrated to be very robust for image matching and object recognition. However, such descriptors are typically of ...
Abstract. We propose a new method for face recognition under arbitrary pose and illumination conditions, which requires only one training image per subject. Furthermore, no limitat...
This paper investigates ordinal image description for
invariant feature correspondence. Ordinal description is
a meta-technique which considers image measurements in
terms of th...