Abstract—In this paper, we present a novel languageindependent algorithm for extracting text-lines from handwritten document images. Our algorithm is based on the seam carving ap...
This paper describes a new algorithm for recovering the
3D shape and motion of deformable and articulated objects
purely from uncalibrated 2D image measurements using an
iterati...
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...
We present an algorithm for finding a meaningful vertexto-vertex correspondence between two 3D shapes given as triangle meshes. Our algorithm operates on embeddings of the two sh...
This paper addresses the fundamental problem of computing stable medial representations of 3D shapes. We propose a spatially adaptive classification of geometric features that yi...