A Novel Semi-Supervised Dynamic Classifier Selection Method for HSI Classification Based on SP Segmentation

Abstract

This paper proposes a novel hyperspectral image classification method that combines dynamic semi-supervised multiple-kernel collaborative representation ensemble selection with superpixel (SP) consistency constraints. The method is based on the consistency principle of labels within SP blocks, where the hyperspectral image is divided into different SP blocks, and each block is treated as an independent classification task. It applies a dynamic ensemble selection strategy to select high-confidence samples from the unlabeled data and assigns pseudo-labels to expand the available training sample set. Additionally, it employs a multiple-kernel collaborative representation classifier as the base classifier to better capture sample similarities and correlations, thereby improving the classification performance. Experimental results demonstrate that the proposed method achieves superior classification accuracy on various datasets such as Indian Pines, Purdue, and KSC, outperforming the traditional Meta-DES method significantly.

Keywords

• Hyperspectral image classification
• superpixel segmentation
• semi-supervised
• dynamic classifier selection
• ensemble learning