DocumentCode :
3645048
Title :
Learning invariant color features with sparse topographic restricted Boltzmann machines
Author :
Hanlin Goh;Łukasz Kuśmierz;Joo-Hwee Lim;Nicolas Thome;Matthieu Cord
Author_Institution :
Institute for Infocomm Research A∗
fYear :
2011
Firstpage :
1241
Lastpage :
1244
Abstract :
Our objective is to learn invariant color features directly from data via unsupervised learning. In this paper, we introduce a method to regularize restricted Boltzmann machines during training to obtain features that are sparse and topographically organized. Upon analysis, the features learned are Gabor-like and demonstrate a coding of orientation, spatial position, frequency and color that vary smoothly with the topography of the feature map. There is also differentiation between monochrome and color filters, with some exhibiting color-opponent properties. We also found that the learned representation is more invariant to affine image transformations and changes in illumination color.
Keywords :
"Image color analysis","Lighting","Learning systems","Conferences","Encoding","Image coding"
Publisher :
ieee
Conference_Titel :
Image Processing (ICIP), 2011 18th IEEE International Conference on
ISSN :
1522-4880
Print_ISBN :
978-1-4577-1304-0
Type :
conf
DOI :
10.1109/ICIP.2011.6115657
Filename :
6115657
Link To Document :
بازگشت