This paper develops a weakly supervised algorithm that learns to segment rigid multi-colored objects from a set of training images and key points. The approach uses congealing to ...
Douglas Moore, John Stevens, Scott Lundberg, Bruce...
Abstract In the analysis of any unconstrained document image it is necessary to first decide what the main area of interest is. Previous work has been done on simply removing the ...
John Bunch, Dean Curtis, Christopher Jones, Jia Ts...
Abstract. We describe a new approach for learning to perform classbased segmentation using only unsegmented training examples. As in previous methods, we first use training images ...
Using existing programming tools, writing high-performance image processing code requires sacrificing readability, portability, and modularity. We argue that this is a consequenc...
Jonathan Ragan-Kelley, Andrew Adams, Sylvain Paris...
This paper addresses the segmentation from an image of entities that have the form of a ‘network’, i.e. the region in the image corresponding to the entity is composed of bran...