scholarly journals Weighted Generalized Nearest Neighbor for Hyperspectral Image Classification

IEEE Access ◽  
2017 ◽  
Vol 5 ◽  
pp. 1496-1509 ◽  
Author(s):  
Chunjuan Bo ◽  
Huchuan Lu ◽  
Dong Wang
Keyword(s):  
Image Classification ◽  
Nearest Neighbor ◽  
Hyperspectral Image ◽  
Hyperspectral Image Classification

Hyperspectral Image Classification Algorithm Based on Space-Spectral Weighted Nearest Neighbor

2020 ◽  
Vol 57 (6) ◽  
pp. 061013
Author(s):  
纪磊 Ji Lei ◽  
张欣 Zhang Xin ◽  
张丽梅 Zhang Limei ◽  
文章 Wen Zhang
Keyword(s):  
Image Classification ◽  
Nearest Neighbor ◽  
Hyperspectral Image ◽  
Classification Algorithm ◽  
Hyperspectral Image Classification

scholarly journals Deep Quadruplet Network for Hyperspectral Image Classification with a Small Number of Samples

2020 ◽  
Vol 12 (4) ◽  
pp. 647 ◽  
Author(s):  
Chengye Zhang ◽  
Jun Yue ◽  
Qiming Qin
Keyword(s):  
Image Classification ◽  
Nearest Neighbor ◽  
Hyperspectral Image ◽  
State Of The Art ◽  
Feature Space ◽  
Hyperspectral Image Classification ◽  
Time Analysis ◽  
Time Consumption ◽  
Ablation Study ◽  
Improving Accuracy

This study proposes a deep quadruplet network (DQN) for hyperspectral image classification given the limitation of having a small number of samples. A quadruplet network is designed, which makes use of a new quadruplet loss function in order to learn a feature space where the distances between samples from the same class are shortened, while those from a different class are enlarged. A deep 3-D convolutional neural network (CNN) with characteristics of both dense convolution and dilated convolution is then employed and embedded in the quadruplet network to extract spatial-spectral features. Finally, the nearest neighbor (NN) classifier is used to accomplish the classification in the learned feature space. The results show that the proposed network can learn a feature space and is able to undertake hyperspectral image classification using only a limited number of samples. The main highlights of the study include: (1) The proposed approach was found to have high overall accuracy and can be classified as state-of-the-art; (2) Results of the ablation study suggest that all the modules of the proposed approach are effective in improving accuracy and that the proposed quadruplet loss contributes the most; (3) Time-analysis shows the proposed methodology has a similar level of time consumption as compared with existing methods.

Sign in / Sign up

Export Citation Format

Share Document