Kernel Hebbian Algorithm for single-frame super-resolution
PDF Web
This paper presents a method for single-frame image super-resolution using an unsupervised learning technique. The required prior knowledge about the high-resolution images is obtained from Kernel Principal Component Analysis (KPCA). The original form of KPCA, however, can be only applied to strongly restricted image classes due to the limited number of training examples that can be processed. We therefore propose a new iterative method for performing KPCA, the {em Kernel Hebbian Algorithm}. By kernelizing the Generalized Hebbian Algorithm, one can iteratively estimate the Kernel Principal Components with only linear order memory complexity. The resulting super-resolution algorithm shows a comparable performance to the existing supervised methods on images containing faces and natural scenes.
| Author(s): | Kim, KI. and Franz, M. and Schölkopf, B. |
| Links: | |
| Book Title: | Computer Vision - ECCV 2004, LNCS vol. 3024 |
| Journal: | Statistical Learning in Computer Vision (SLCV 2004) |
| Pages: | 135-149 |
| Year: | 2004 |
| Month: | May |
| Day: | 0 |
| Editors: | A Leonardis and H Bischof |
| Publisher: | Springer |
| BibTeX Type: | Conference Paper (inproceedings) |
| Address: | Berlin, Germany |
| Event Name: | 8th European Conference on Computer Vision (ECCV 2004) |
| Event Place: | Praha, Czech Republic |
| Digital: | 0 |
| Electronic Archiving: | grant_archive |
| Language: | en |
| Organization: | Max-Planck-Gesellschaft |
| School: | Biologische Kybernetik |
BibTeX
@inproceedings{2645,
title = {Kernel Hebbian Algorithm for single-frame super-resolution},
journal = {Statistical Learning in Computer Vision (SLCV 2004)},
booktitle = {Computer Vision - ECCV 2004, LNCS vol. 3024},
abstract = {This paper presents a method for single-frame image super-resolution
using an unsupervised learning technique. The required prior
knowledge about the high-resolution images is obtained from
Kernel Principal Component Analysis (KPCA). The original form of
KPCA, however, can be only applied to strongly restricted image
classes due to the limited number of training examples that can be
processed. We therefore propose a new iterative method for performing
KPCA, the {em Kernel Hebbian Algorithm}. By kernelizing the
Generalized Hebbian Algorithm, one can iteratively estimate the Kernel
Principal Components with only linear order memory complexity. The
resulting super-resolution algorithm shows a comparable performance to
the existing supervised methods on images containing faces and natural
scenes.},
pages = {135-149},
editors = {A Leonardis and H Bischof},
publisher = {Springer},
organization = {Max-Planck-Gesellschaft},
school = {Biologische Kybernetik},
address = {Berlin, Germany},
month = may,
year = {2004},
author = {Kim, KI. and Franz, M. and Sch{\"o}lkopf, B.},
month_numeric = {5}
}