2013
DOI: 10.1155/2013/847062
|View full text |Cite
|
Sign up to set email alerts
|

Optimizing Kernel PCA Using Sparse Representation-Based Classifier for MSTAR SAR Image Target Recognition

Abstract: Different kernels cause various class discriminations owing to their different geometrical structures of the data in the feature space. In this paper, a method of kernel optimization by maximizing a measure of class separability in the empirical feature space with sparse representation-based classifier (SRC) is proposed to solve the problem of automatically choosing kernel functions and their parameters in kernel learning. The proposed method first adopts a so-called data-dependent kernel to generate an effici… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
5

Citation Types

0
7
0

Year Published

2013
2013
2018
2018

Publication Types

Select...
6
1

Relationship

1
6

Authors

Journals

citations
Cited by 10 publications
(7 citation statements)
references
References 21 publications
0
7
0
Order By: Relevance
“…SAR-ATR systems generally consist of three stages: detection [1,2], recognition, and classification. At present, common methods of SAR-ATR include template matching [3], support vector machine (SVM) [4], Linear interpolation [5] Principal Component Analysis [6,7], multi-modal dictionary learning and sparse representation combined [8,9], etc. These methods have been successful in some way, but they rely heavily on experience of experts.…”
Section: Introductionmentioning
confidence: 99%
“…SAR-ATR systems generally consist of three stages: detection [1,2], recognition, and classification. At present, common methods of SAR-ATR include template matching [3], support vector machine (SVM) [4], Linear interpolation [5] Principal Component Analysis [6,7], multi-modal dictionary learning and sparse representation combined [8,9], etc. These methods have been successful in some way, but they rely heavily on experience of experts.…”
Section: Introductionmentioning
confidence: 99%
“…The ROIs are sent to the classifier to decide the target class [ 10 , 11 ]. In the literature, the automatic SAR target recognition technology generally includes the traditional template matching method, the model-based algorithm, and the methods based on features such as principal component analysis (PCA) [ 12 , 13 ], wavelet transform [ 14 , 15 ], radon transform [ 16 ]. In addition, considering the scattering characteristics of SAR images, there are two typical models: conditionally Gaussian model [ 11 ] and scattering centers model [ 17 ].…”
Section: Introductionmentioning
confidence: 99%
“…Pang and Yuan [12] proposed to substitute L2-norm with L1-norm to improve the robustness of LPP against outliers. Although SKLPP showed good performance in [7], the selection of kernel function has a significant influence on the kernel feature extraction and the problem was widely studied in the previous works [7,[13][14][15]. In [15], we proposed a Kernel Optimized PCA (KOPCA) with sparse representation-based classifier (SRC).…”
Section: Introductionmentioning
confidence: 99%