TY - GEN
T1 - A soft classification algorithm based on spectral-spatial kernels in hyperspectral images
AU - Gu, Yanfeng
AU - Liu, Ying
AU - Zhang, Ye
PY - 2007
Y1 - 2007
N2 - In this paper, a soft classification algorithm based on composite kernels, which incorporate both spectral and spatial information, is proposed for hyperspectral image. Compared with hard classification, soft classification provides more information about the probabilities one pixel belongs to each class. To calculate these probabilities, the proposed algorithm uses Support Vector Machine (SVM), and it successfully converts SVM output values into probabilities, while at the same time integrates spatial and spectral information by composite kernels. To validate the proposed algorithm, experiments are conducted on hyperspectral images with 126 and 186 bands, and experimental results show that soft classification using SVM can yield better results compared with Maximum Likelihood Classifier (MLC),and the introduction of spectral-spatial kernels can greatly improve classification accuracies.
AB - In this paper, a soft classification algorithm based on composite kernels, which incorporate both spectral and spatial information, is proposed for hyperspectral image. Compared with hard classification, soft classification provides more information about the probabilities one pixel belongs to each class. To calculate these probabilities, the proposed algorithm uses Support Vector Machine (SVM), and it successfully converts SVM output values into probabilities, while at the same time integrates spatial and spectral information by composite kernels. To validate the proposed algorithm, experiments are conducted on hyperspectral images with 126 and 186 bands, and experimental results show that soft classification using SVM can yield better results compared with Maximum Likelihood Classifier (MLC),and the introduction of spectral-spatial kernels can greatly improve classification accuracies.
UR - https://www.scopus.com/pages/publications/39049137436
U2 - 10.1109/ICICIC.2007.90
DO - 10.1109/ICICIC.2007.90
M3 - 会议稿件
AN - SCOPUS:39049137436
SN - 0769528821
SN - 9780769528823
T3 - Second International Conference on Innovative Computing, Information and Control, ICICIC 2007
BT - Second International Conference on Innovative Computing, Information and Control, ICICIC 2007
PB - IEEE Computer Society
T2 - 2nd International Conference on Innovative Computing, Information and Control, ICICIC 2007
Y2 - 5 September 2007 through 7 September 2007
ER -