TY - GEN
T1 - Kernel weighted joint collaborative representation for hyperspectral image classification
AU - Du, Qian
AU - Li, Wei
N1 - Publisher Copyright:
© 2015 SPIE.
PY - 2015
Y1 - 2015
N2 - Collaborative representation classifier (CRC) has been applied to hyperspectral image classification, which intends to use all the atoms in a dictionary to represent a testing pixel for label assignment. However, some atoms that are very dissimilar to the testing pixel should not participate in the representation, or their contribution should be very little. The regularized version of CRC imposes strong penalty to prevent dissimilar atoms with having large representation coefficients. To utilize spatial information, the weighted sum of local spatial neighbors is considered as a joint spatial-spectral feature, which is actually for regularized CRC-based classification. This paper proposes its kernel version to further improve classification accuracy, which can be higher than those from the traditional support vector machine with composite kernel and the kernel version of sparse representation classifier.
AB - Collaborative representation classifier (CRC) has been applied to hyperspectral image classification, which intends to use all the atoms in a dictionary to represent a testing pixel for label assignment. However, some atoms that are very dissimilar to the testing pixel should not participate in the representation, or their contribution should be very little. The regularized version of CRC imposes strong penalty to prevent dissimilar atoms with having large representation coefficients. To utilize spatial information, the weighted sum of local spatial neighbors is considered as a joint spatial-spectral feature, which is actually for regularized CRC-based classification. This paper proposes its kernel version to further improve classification accuracy, which can be higher than those from the traditional support vector machine with composite kernel and the kernel version of sparse representation classifier.
KW - Classification
KW - Collaborative Representation
KW - Hyperspectral Imagery
KW - Sparse Representation
KW - Spectral-Spatial Classifier
KW - Support Vector Machine
KW - Support Vector Machine with Composite Kernel
UR - http://www.scopus.com/inward/record.url?scp=84938900886&partnerID=8YFLogxK
U2 - 10.1117/12.2179914
DO - 10.1117/12.2179914
M3 - Conference contribution
AN - SCOPUS:84938900886
T3 - Proceedings of SPIE - The International Society for Optical Engineering
BT - Satellite Data Compression, Communications, and Processing XI
A2 - Li, Yunsong
A2 - Chang, Chein-I
A2 - Huang, Bormin
A2 - Du, Qian
A2 - Lee, Chulhee
PB - SPIE
T2 - Satellite Data Compression, Communications, and Processing XI
Y2 - 23 April 2015 through 24 April 2015
ER -