Hyperspectral Image Classification Based on Class Confusion Merging and Soft Band Selection

In hyperspectral image (HSI) classification, the distinction of similar classes has always been a focus of research. In this paper, a new classification module named class confusion merging (CCM) is proposed to improve the classification accuracy, especially for classes with the similar spectral feature. In CCM processing, the merging matrix is firstly constructed based on the confusion matrix to measure the similarity between different classes. Then similar classes are merged as big categories. Finally, for each big category, soft band selection is implemented based on the spectral difference of contained classes for reclassification. To evaluate the performance of CCM, real image experiments are conducted in comparison with no CCM module hyperspectral classification methods. The experiment results demonstrate that the CCM module can improve the classifier performance by providing higher classification accuracy.