TY - GEN
T1 - Classification of hyperspectral image using multiscale spatial texture features
AU - Sidike, Paheding
AU - Chen, Chen
AU - Asari, Vijayan
AU - Xu, Yan
AU - Li, Wei
N1 - Publisher Copyright:
© 2016 IEEE.
PY - 2016/6/28
Y1 - 2016/6/28
N2 - Spatial information has shown significant contribution for hyperspectral image classification. Local Binary Pattern (LBP) can be used for extracting spatial texture features, however it is incapable of capturing textural and structural features of images at various resolution. Hence, we present a multiscale scheme on Complete LBP (CLBP) as well as on LBP to obtain better spatial features from hyperspectral imagery (HSI). Experiments conducted on two standard HSI datasets proved that the proposed multiscale scheme can improve the classification accuracy of both LBP and CLBP, and Multiscale CLBP provides better accuracy compared to the state-of-the-art spatial feature extraction methods for HSI classification.
AB - Spatial information has shown significant contribution for hyperspectral image classification. Local Binary Pattern (LBP) can be used for extracting spatial texture features, however it is incapable of capturing textural and structural features of images at various resolution. Hence, we present a multiscale scheme on Complete LBP (CLBP) as well as on LBP to obtain better spatial features from hyperspectral imagery (HSI). Experiments conducted on two standard HSI datasets proved that the proposed multiscale scheme can improve the classification accuracy of both LBP and CLBP, and Multiscale CLBP provides better accuracy compared to the state-of-the-art spatial feature extraction methods for HSI classification.
KW - Completed local binary pattern (CLBP)
KW - Extreme learning machine (ELM)
KW - Hyperspectral imagery (HSI)
KW - Image classification
KW - Local binary pattern (LBP)
UR - http://www.scopus.com/inward/record.url?scp=85022137837&partnerID=8YFLogxK
U2 - 10.1109/WHISPERS.2016.8071767
DO - 10.1109/WHISPERS.2016.8071767
M3 - Conference contribution
AN - SCOPUS:85022137837
T3 - Workshop on Hyperspectral Image and Signal Processing, Evolution in Remote Sensing
BT - 2016 8th Workshop on Hyperspectral Image and Signal Processing
PB - IEEE Computer Society
T2 - 8th Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS 2016
Y2 - 21 August 2016 through 24 August 2016
ER -