Optimal superpixel selection for hyperspectral image classification of limited training samples

The hyperspectral image (HSI) classification method based on superpixel segmentation can solve the HSI classification problem of limited training samples. The proposed method improves the classification accuracy of each test sample by selecting the optimal superpixel for it and then extracting classification features. First, an HSI is segmented into superpixels with different scales. Subsequently, we propose an optimal superpixel evaluation method that selects the optimal superpixel for each sample in the HSI to extract classification feature. Lastly, the optimal superpixel is selected for each training sample to augment the training samples and improve the accuracy of the classifier. Experiments on two datasets indicate that the proposed method can effectively improve the classification accuracy of HSIs with limited training samples.