Local Image Descriptors Using Supervised Kernel ICA
Summary :
PCA-SIFT is an extension to SIFT which aims to reduce SIFT's high dimensionality (128 dimensions) by applying PCA to the gradient image patches. However PCA is not a discriminative representation for recognition due to its global feature nature and unsupervised algorithm. In addition, linear methods such as PCA and ICA can fail in the case of non-linearity. In this paper, we propose a new discriminative method called Supervised Kernel ICA (SKICA) that uses a non-linear kernel approach combined with Supervised ICA-based local image descriptors. Our approach blends the advantages of supervised learning with nonlinear properties of kernels. Using five different test data sets we show that the SKICA descriptors produce better object recognition performance than other related approaches with the same dimensionality. The SKICA-based representation has local sensitivity, non-linear independence and high class separability providing an effective method for local image descriptors.
- Publication
- IEICE TRANSACTIONS on Information Vol.E92-D No.9 pp.1745-1751
- Publication Date
- 2009/09/01
- Publicized
- Online ISSN
- 1745-1361
- DOI
- 10.1587/transinf.E92.D.1745
- Type of Manuscript
- PAPER
- Category
- Image Recognition, Computer Vision
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
Masaki YAMAZAKI, Sidney FELS, "Local Image Descriptors Using Supervised Kernel ICA" in IEICE TRANSACTIONS on Information,
vol. E92-D, no. 9, pp. 1745-1751, September 2009, doi: 10.1587/transinf.E92.D.1745.
Abstract: PCA-SIFT is an extension to SIFT which aims to reduce SIFT's high dimensionality (128 dimensions) by applying PCA to the gradient image patches. However PCA is not a discriminative representation for recognition due to its global feature nature and unsupervised algorithm. In addition, linear methods such as PCA and ICA can fail in the case of non-linearity. In this paper, we propose a new discriminative method called Supervised Kernel ICA (SKICA) that uses a non-linear kernel approach combined with Supervised ICA-based local image descriptors. Our approach blends the advantages of supervised learning with nonlinear properties of kernels. Using five different test data sets we show that the SKICA descriptors produce better object recognition performance than other related approaches with the same dimensionality. The SKICA-based representation has local sensitivity, non-linear independence and high class separability providing an effective method for local image descriptors.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.E92.D.1745/_p
Copy
@ARTICLE{e92-d_9_1745,
author={Masaki YAMAZAKI, Sidney FELS, },
journal={IEICE TRANSACTIONS on Information},
title={Local Image Descriptors Using Supervised Kernel ICA},
year={2009},
volume={E92-D},
number={9},
pages={1745-1751},
abstract={PCA-SIFT is an extension to SIFT which aims to reduce SIFT's high dimensionality (128 dimensions) by applying PCA to the gradient image patches. However PCA is not a discriminative representation for recognition due to its global feature nature and unsupervised algorithm. In addition, linear methods such as PCA and ICA can fail in the case of non-linearity. In this paper, we propose a new discriminative method called Supervised Kernel ICA (SKICA) that uses a non-linear kernel approach combined with Supervised ICA-based local image descriptors. Our approach blends the advantages of supervised learning with nonlinear properties of kernels. Using five different test data sets we show that the SKICA descriptors produce better object recognition performance than other related approaches with the same dimensionality. The SKICA-based representation has local sensitivity, non-linear independence and high class separability providing an effective method for local image descriptors.},
keywords={},
doi={10.1587/transinf.E92.D.1745},
ISSN={1745-1361},
month={September},}
Copy
TY - JOUR
TI - Local Image Descriptors Using Supervised Kernel ICA
T2 - IEICE TRANSACTIONS on Information
SP - 1745
EP - 1751
AU - Masaki YAMAZAKI
AU - Sidney FELS
PY - 2009
DO - 10.1587/transinf.E92.D.1745
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E92-D
IS - 9
JA - IEICE TRANSACTIONS on Information
Y1 - September 2009
AB - PCA-SIFT is an extension to SIFT which aims to reduce SIFT's high dimensionality (128 dimensions) by applying PCA to the gradient image patches. However PCA is not a discriminative representation for recognition due to its global feature nature and unsupervised algorithm. In addition, linear methods such as PCA and ICA can fail in the case of non-linearity. In this paper, we propose a new discriminative method called Supervised Kernel ICA (SKICA) that uses a non-linear kernel approach combined with Supervised ICA-based local image descriptors. Our approach blends the advantages of supervised learning with nonlinear properties of kernels. Using five different test data sets we show that the SKICA descriptors produce better object recognition performance than other related approaches with the same dimensionality. The SKICA-based representation has local sensitivity, non-linear independence and high class separability providing an effective method for local image descriptors.
ER -
English
