Some Measures for Shape Analysis

Paul Rosin

(Cardiff University)

Shape is an important aspect of biological vision and computer
vision. In particular, global shape measures are a convenient way to describe regions. They are generally simple and efficient to extract, easily interpreted by humans, and provide an easy means for high level tasks such as classification as well as helping direct low-level computer vision processes such as segmentation.
This talk discusses a variety of global shape measures recently developed for computer vision, and also mentions in passing some related perceptual aspects of shape.
Tuesday 27th November 2007, 14:00
Robert Recorde Room
Department of Computer Science