BCN Perceptual Computing Lab Repository

Weighted Dissociated Dipoles: An Extended Visual Feature Set

Baró, Xavier and Vitrià, Jordi (2008) Weighted Dissociated Dipoles: An Extended Visual Feature Set. Lecture Notes in Computer Science, 5008 . pp. 281-290. ISSN 0302-9743

[img]
Preview
PDF - Requires a PDF viewer such as GSview, Xpdf or Adobe Acrobat Reader
1914Kb

Abstract

The complexity of any learning task depends on the learning method as on finding a good data representation. 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 set based on local intensity differences, which has been successfully applied to different object recognition tasks, such as pedestrian or face recognition problems. 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. Since these feature sets cannot be used with the classical Adaboost approach due computational limitations, an evolutionary learning algorithm is used to test them over different state of the art object recognition problems. Besides, an extended statistically study of these results is performed in order to verify the relevance of these huge feature spaces.

Item Type:Article
Subjects:Q Science > QA Mathematics > QA75 Electronic computers. Computer science
ID Code:16
Deposited By:Xavier Baró
Deposited On:12 Jun 2009 17:38
Last Modified:29 Nov 2010 17:52

Repository Staff Only: item control page