BCN Perceptual Computing Lab Repository

Weighted Dissociated Dipoles for Evolutive Learning

Baró, Xavier and Vitrià, Jordi (2007) Weighted Dissociated Dipoles for Evolutive Learning. Artificial Intelligence Resarch and Development, Frontiers in Artificial Intelligence and Applications, 163 . pp. 189-196. ISSN 978-1-58603-798-7

[img]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
185Kb

Abstract

The complexity of any learning task depends as in the learning method as on finding a good representation of the data. In the concrete case of object recognition in computer vision, the representation of the images is one of the most important decisions in the design step. As a starting point, in this work we use the representation based on Haar-like filters, a biological inspired feature based on local intensity differences. From this commonly used representation, we jump to the dissociated dipoles, another biological plausible representation which also includes non-local comparisons. After analyzing the benefits of both representations, we present a more general representation which brings together all the good properties of Haar-like and dissociated dipoles representations. All these feature sets are tested with an evolutionary learning algorithm over different object recognition problems. Besides, an extended statistically study of these results is performed in order to verify the relevance of these huge feature spaces applied to different object recognition problems.

Item Type:Article
Subjects:Q Science > QA Mathematics > QA76 Computer software
ID Code:36
Deposited By:n/d Generic User
Deposited On:03 Aug 2009 22:03
Last Modified:29 Nov 2010 17:52

Repository Staff Only: item control page