We present a method to automatically learn object categories from unlabeled images. Each image is represented by an unordered set of local features, and all sets are embedded into...
: Fast and accurate 3D object reconstruction and partial 3D component retrieval from 2D image slices represent a difficult and challenging problem. To group related objects on diff...
Edit distance matching has been used in literature for word spotting with characters taken as primitives. The recognition rate however, is limited by the segmentation inconsistenci...
In this paper, we propose a morphing method by which face color images can be freely transformed. The main focus of this work is the transformation of one face image to another. Th...
Abstract. Inter-subjectnon-rigid registration of cortical anatomical structures as seen in MR is a challenging problem. The variability of the sulcal and gyral patterns across pati...
Haili Chui, James Rambo, James S. Duncan, Robert T...