Semi-supervised rotation forest based on ensemble margin theory for the classification of hyperspectral image with limited training data

• Published in: Information sciences Vol. 575; pp. 611 - 638
• Main Authors: Feng, Wei, Quan, Yinghui, Dauphin, Gabriel, Li, Qiang, Gao, Lianru, Huang, Wenjiang, Xia, Junshi, Zhu, Wentao, Xing, Mengdao
• Format: Journal Article
• Language: English
• Published: Elsevier Inc 01.10.2021; Elsevier
• Subjects: Classification; Engineering Sciences; Ensemble margin; Environmental Sciences; Global Changes; Hyperspectral image; Rotation forest; Semi-supervised learning; Signal and Image processing; Rotation forest; Hyperspectral image; Ensemble margin; Semi-supervised learning; Classification
• ISSN: 0020-0255; 1872-6291
• DOI: 10.1016/j.ins.2021.06.059

In this paper, an adaptive semi-supervised rotation forest (SSRoF) algorithm is proposed for the classification of hyperspectral images with limited training data. Our proposition is based on Rotation Forest (RoF), a classifying technique that has proved to be remarkably accurate in the context of high-dimensional data. It is adapted to the semi-supervised context, by increasing the number of training instances in the learning stage, with high-quality unlabeled samples mined using ensemble margin. SMOTE is adopted to overcome the class imbalance problem. Out-Of-Bag (OOB) instances are used in a second phase to figure out the optimal number of samples to be added to the training set. Five ensemble methods and five semi-supervised methods are employed as comparisons. The results on three real hyperspectral remote sensing datasets demonstrate the effectiveness of the proposed method.