Cogprints

Learning viewpoint invariant perceptual representations from cluttered images

Spratling, Dr Michael (2005) Learning viewpoint invariant perceptual representations from cluttered images. [Journal (Paginated)]

Full text available as:

[img]
Preview
PDF
365Kb

Abstract

In order to perform object recognition, it is necessary to form perceptual representations that are sufficiently specific to distinguish between objects, but that are also sufficiently flexible to generalise across changes in location, rotation and scale. A standard method for learning perceptual representations that are invariant to viewpoint is to form temporal associations across image sequences showing object transformations. However, this method requires that individual stimuli are presented in isolation and is therefore unlikely to succeed in real-world applications where multiple objects can co-occur in the visual input. This article proposes a simple modification to the learning method, that can overcome this limitation, and results in more robust learning of invariant representations.

Item Type:Journal (Paginated)
Keywords:Computational models of vision; Neural Nets; invariance; object recognition
Subjects:Neuroscience > Neural Modelling
Computer Science > Machine Vision
Computer Science > Neural Nets
ID Code:4884
Deposited By:Spratling, Dr Michael
Deposited On:25 May 2006
Last Modified:11 Mar 2011 08:56

Metadata

Repository Staff Only: item control page