The essence of the signal-to-symbol problem consists of associating a symbolic description of an object (e.g., a chair) to a signal (e.g., an image) that captures the real object....
Manuela M. Veloso, Paul E. Rybski, Felix von Hunde...
This paper explores how to exploit shape information to perform object class recognition. We use a sparse partbased model to describe object categories defined by shape. The spars...
Josephine Sullivan, Oscar M. Danielsson, Stefan Ca...
This research features a novel approach that efficiently detects depth edges in real world scenes. Depth edges play a very important role in many computer vision problems because t...
Jiyoung Park, Cheolhwon Kim, Juneho Yi, Matthew Tu...
Very early in the object recognition process the human visual system extracts shading information. While shading can enhance the visibility of structures, it can have a negative i...
Text that appears in images contains important and useful information. Detection and extraction of text in images have been used in many applications. In this paper, we propose a ...