1. PolSAR image classification via a novel semi-supervised recurrent complex-valued convolution neural network.
- Author
-
Xie, Wen, Ma, Gaini, Zhao, Feng, Liu, Hanqiang, and Zhang, Lu
- Subjects
- *
SYNTHETIC aperture radar , *POLARIMETRY , *SYNTHETIC apertures , *MATHEMATICAL convolutions , *CLASSIFICATION - Abstract
• For the reason that Polarimetric synthetic aperture radar (PolSAR) data is complex-valued, we use a complex-valued classification network in this paper. • PolSAR data has the problem of lacking labeled samples, so we make full use of a small number of labeled samples to propose a novel semi-supervised recurrent classification method. • The problem of network overfitting could be solved to some extent by our methods, especially for very small training samples and large testing samples. • The classification accuracy of three datasets are improved only by using very small number of labeled training samples. Due to that polarimetric synthetic aperture radar (PolSAR) data suffers from missing labeled samples and complex-valued data, this article presents a novel semi-supervised PolSAR terrain classification method named recurrent complex-valued convolution neural network (RCV-CNN) which combines semi-supervised learning and complex-valued convolution neural network (CV-CNN). The proposed method only needs a small number of labeled samples to achieve good classification results. First, a Wishart classifier is used to select some reliable PolSAR samples. Then, two new semi-supervised deep classification model RCV-CNN1 and RCV-CNN2 have been proposed to improve PolSAR image classification accuracy. Moreover, our proposed methods could solve the problem of network overfitting phenomenon to some extend when the number of training samples is too small. Finally, three real PolSAR dataset are applied to verify the effectiveness of our algorithms. Compared with the other five state-of-the-art methods, the proposed RCV-CNN1 and RCV-CNN2 classification models show good performance in accuracy and generalization. [ABSTRACT FROM AUTHOR]
- Published
- 2020
- Full Text
- View/download PDF