IEICE TRANSACTIONS on Information
Complex Cell Descriptor Learning for Robust Object Recognition
Summary :
An unsupervised algorithm is proposed for learning overcomplete topographic representations of nature image. Our method is based on Independent Component Analysis (ICA) model due to its superiority on feature extraction, and overcomes the weakness of traditional method in fast overcomplete learning. Besides, the learnt topographic representation, resembling receptive fields of complex cells, can be used as descriptors to extract invariant features. Recognition experiments on Caltech-101 dataset confirm that these complex cell descriptors are not only efficient in feature extraction but achieve comparable performances to traditional descriptors.
- Publication
- IEICE TRANSACTIONS on Information Vol.E94-D No.7 pp.1502-1505
- Publication Date
- 2011/07/01
- Publicized
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.E94.D.1502
- Type of Manuscript
- LETTER
- Category
- Pattern Recognition
Authors
Keyword
Latest Issue
Copyrights notice of machine-translated contents
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Cite this
Copy
Zhe WANG, Yaping HUANG, Siwei LUO, Liang WANG, "Complex Cell Descriptor Learning for Robust Object Recognition" in IEICE TRANSACTIONS on Information,
vol. E94-D, no. 7, pp. 1502-1505, July 2011, doi: 10.1587/transinf.E94.D.1502.
Abstract: An unsupervised algorithm is proposed for learning overcomplete topographic representations of nature image. Our method is based on Independent Component Analysis (ICA) model due to its superiority on feature extraction, and overcomes the weakness of traditional method in fast overcomplete learning. Besides, the learnt topographic representation, resembling receptive fields of complex cells, can be used as descriptors to extract invariant features. Recognition experiments on Caltech-101 dataset confirm that these complex cell descriptors are not only efficient in feature extraction but achieve comparable performances to traditional descriptors.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E94.D.1502/_p
Copy
@ARTICLE{e94-d_7_1502,
author={Zhe WANG, Yaping HUANG, Siwei LUO, Liang WANG, },
journal={IEICE TRANSACTIONS on Information},
title={Complex Cell Descriptor Learning for Robust Object Recognition},
year={2011},
volume={E94-D},
number={7},
pages={1502-1505},
abstract={An unsupervised algorithm is proposed for learning overcomplete topographic representations of nature image. Our method is based on Independent Component Analysis (ICA) model due to its superiority on feature extraction, and overcomes the weakness of traditional method in fast overcomplete learning. Besides, the learnt topographic representation, resembling receptive fields of complex cells, can be used as descriptors to extract invariant features. Recognition experiments on Caltech-101 dataset confirm that these complex cell descriptors are not only efficient in feature extraction but achieve comparable performances to traditional descriptors.},
keywords={},
doi={10.1587/transinf.E94.D.1502},
ISSN={1745-1361},
month={July},}
Copy
TY - JOUR
TI - Complex Cell Descriptor Learning for Robust Object Recognition
T2 - IEICE TRANSACTIONS on Information
SP - 1502
EP - 1505
AU - Zhe WANG
AU - Yaping HUANG
AU - Siwei LUO
AU - Liang WANG
PY - 2011
DO - 10.1587/transinf.E94.D.1502
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E94-D
IS - 7
JA - IEICE TRANSACTIONS on Information
Y1 - July 2011
AB - An unsupervised algorithm is proposed for learning overcomplete topographic representations of nature image. Our method is based on Independent Component Analysis (ICA) model due to its superiority on feature extraction, and overcomes the weakness of traditional method in fast overcomplete learning. Besides, the learnt topographic representation, resembling receptive fields of complex cells, can be used as descriptors to extract invariant features. Recognition experiments on Caltech-101 dataset confirm that these complex cell descriptors are not only efficient in feature extraction but achieve comparable performances to traditional descriptors.
ER -
English
