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.
IOS Press, Inc.
6751 Tepper Drive
Clifton, VA 20124
Tel.: +1 703 830 6300
Fax: +1 703 830 2300 firstname.lastname@example.org
(Corporate matters and books only) IOS Press c/o Accucoms US, Inc.
For North America Sales and Customer Service
West Point Commons
Lansdale PA 19446
Tel.: +1 866 855 8967
Fax: +1 215 660 5042 email@example.com