DocumentCode
594857
Title
Learning a selectivity-invariance-selectivity feature extraction architecture for images
Author
Gutmann, M.U. ; Hyvarinen, Aapo
Author_Institution
Dept. Comput. Sci., Univ. of Helsinki, Helsinki, Finland
fYear
2012
fDate
11-15 Nov. 2012
Firstpage
918
Lastpage
921
Abstract
Selectivity and invariance are thought to be important ingredients in biological or artificial visual systems. A fundamental problem is, however, to know what the visual system should be selective to and what to be invariant to. Building a statistical model of images, we learn here a three-layer feature extraction system where the selectivity and invariance emerges from the properties of the images.
Keywords
feature extraction; image processing; statistical analysis; artificial visual system; feature extraction; image processing; invariance; learning; selectivity; statistical model; Biology; Computational modeling; Computer architecture; Estimation; Feature extraction; Vectors; Visualization;
fLanguage
English
Publisher
ieee
Conference_Titel
Pattern Recognition (ICPR), 2012 21st International Conference on
Conference_Location
Tsukuba
ISSN
1051-4651
Print_ISBN
978-1-4673-2216-4
Type
conf
Filename
6460284
Link To Document