We develop a novel method for class-based feature matching across large changes in viewing conditions. The method (called MBE) is based on the property that when objects share a si...
In this paper we revisit local feature detectors/descriptors developed for 2D images and extend them to the more general framework of scalar fields defined on 2D manifolds. We pro...
Andrei Zaharescu (INRIA Grenoble), Edmond Boyer (L...
With the success of local features in object recognition, feature-set representations are widely used in computer vision and related domains. Pyramid match kernel (PMK) is an effi...
W e introduce a novel view-based object representation, called the saliency map graph (SMG), which captures the salient regions of an object view at multiple scales using a wavele...
For non-rigid registration, the objects in medical images are usually treated as a single deformable body with homogeneous stiffness distribution. However, this assumption is inval...