scholarly journals Recursive Autoencoders-Based Unsupervised Feature Learning for Hyperspectral Image Classification

2017 ◽  
Vol 14 (11) ◽  
pp. 1928-1932 ◽  
Author(s):  
Xiangrong Zhang ◽  
Yanjie Liang ◽  
Chen Li ◽  
Ning Huyan ◽  
Licheng Jiao ◽  
...  
2020 ◽  
Vol 10 (9) ◽  
pp. 2027-2031
Author(s):  
Xu Yifang

Hyperspectral image classification refers to a key difficulty on the domain of remote sensing image processing. Feature learning is the basis of hyperspectral image classification problems. In addition, how to jointly use the space spectrum information is Also an important issue in hyperspectral image classification. Recent ages have seen that as further exploration is developing, the method of hyperspectral image cauterization according to deep learning has been rapidly developed. However, existing deep networks often only consider reconstruction performance while ignoring the task itself. In addition, for improving preciseness of classification, most categorization methods use the fixed-size neighborhood of per hyperspectral pixel as the object of feature extraction, ignoring the identification and difference between the neighborhood pixel and the current pixel. On the basis of exploration above, our research group put forward with an image classification algorithm based on principal component texture feature deep learning, and achieved good results.


2015 ◽  
Vol 53 (3) ◽  
pp. 1592-1606 ◽  
Author(s):  
Jun Li ◽  
Xin Huang ◽  
Paolo Gamba ◽  
Jose M. Bioucas Bioucas-Dias ◽  
Liangpei Zhang ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document