Sciweavers

3 search results - page 1 / 1
» Learning High-level Independent Components of Images through...
Sort
View
ICPR
2004
IEEE
14 years 5 months ago
Learning High-level Independent Components of Images through a Spectral Representation
Statistical methods, such as independent component analysis, have been successful in learning local low-level features from natural image data. Here we extend these methods for le...
Aapo Hyvärinen, Jussi T. Lindgren
BMCV
2000
Springer
13 years 8 months ago
The Spectral Independent Components of Natural Scenes
Abstract. We apply independent component analysis (ICA) for learning an efficient color image representation of natural scenes. In the spectra of single pixels, the algorithm was a...
Te-Won Lee, Thomas Wachtler, Terrence J. Sejnowski
IJON
2007
88views more  IJON 2007»
13 years 4 months ago
Information maximization in face processing
This perspective paper explores principles of unsupervised learning and how they relate to face recognition. Dependency coding and information maximization appear to be central pr...
Marian Stewart Bartlett