This paper proposes an image segmentation model based on the active contour model, the Mumford-Shah functional and the image decomposition process. Generally speaking, the active ...
We present a novel categorical object detection scheme that uses only local contour-based features. A two-stage, partially supervised learning architecture is proposed: a rudiment...
Abstract. Detecting contour closure, i.e., finding a cycle of disconnected contour fragments that separates an object from its background, is an important problem in perceptual gro...
Algorithms that detect silhouettes, creases, and other edge based features often perform per-edge and per-face mesh computations using global adjacency information. These are unsu...
Grouping and Abstraction Using Simple Part Models Pablo Sala and Sven Dickinson Department of Computer Science, University of Toronto, Toronto ON, Canada We address the problem of ...