TY - JOUR
T1 - Combining t-Distributed Stochastic Neighbor Embedding with Convolutional Neural Networks for Hyperspectral Image Classification
AU - Gao, Lianru
AU - Gu, Daixin
AU - Zhuang, Lina
AU - Ren, Jinchang
AU - Yang, Dong
AU - Zhang, Bing
N1 - Funding Information:
This work was supported by the National Natural Science Foundation of China under Grant 41722108 and Grant 91638201. (Corresponding author: Bing Zhang.) L. Gao is with the Key Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100094, China (e-mail: [email protected]).
Publisher Copyright:
© 2019 IEEE
PY - 2020/8
Y1 - 2020/8
N2 - Hyperspectral images (HSIs), featured by high spectral resolution over a wide range of electromagnetic spectra, have been widely used to characterize materials with subtle differences in the spectral domain. However, a large number of bands and an insufficient number of sample pixels for each class are challenging for traditional machine learning-based classifiers. As alternative tools for feature extraction, neural networks have received extensive attention. This letter proposes to combine t-distributed stochastic neighbor embedding (t-SNE) with a convolutional neural network (CNN) for HSI classification. Our framework is designed to automatically capture the potential assembly features, which are extracted from both the dimension-reduced CNN (DR-CNN) and the multiscale-CNN. Experimental results show that the proposed classification framework outperforms several state-of-the-art techniques for three real data sets.
AB - Hyperspectral images (HSIs), featured by high spectral resolution over a wide range of electromagnetic spectra, have been widely used to characterize materials with subtle differences in the spectral domain. However, a large number of bands and an insufficient number of sample pixels for each class are challenging for traditional machine learning-based classifiers. As alternative tools for feature extraction, neural networks have received extensive attention. This letter proposes to combine t-distributed stochastic neighbor embedding (t-SNE) with a convolutional neural network (CNN) for HSI classification. Our framework is designed to automatically capture the potential assembly features, which are extracted from both the dimension-reduced CNN (DR-CNN) and the multiscale-CNN. Experimental results show that the proposed classification framework outperforms several state-of-the-art techniques for three real data sets.
KW - Assembly fusion
KW - convolutional neural network (CNN)
KW - dimensionality reduction
KW - hyperspectral image (HSI) classification
KW - t-distributed stochastic neighbor embedding (t-SNE)
UR - http://www.scopus.com/inward/record.url?scp=85082307350&partnerID=8YFLogxK
U2 - 10.1109/LGRS.2019.2945122
DO - 10.1109/LGRS.2019.2945122
M3 - Journal article
AN - SCOPUS:85082307350
SN - 1545-598X
VL - 17
SP - 1368
EP - 1372
JO - IEEE Geoscience and Remote Sensing Letters
JF - IEEE Geoscience and Remote Sensing Letters
IS - 8
M1 - 8876672
ER -