In hyperspectral image classification, small number of labeled samples versus high dimensional data is one of majorchallenges. Semi-supervised learning has shown potential to relief the dilemma. Compared with its supervised learningcounterpart, semi-supervised learning exploits both intrinsic structure of labeled and unlabeled samples. In this work, weproposed a graph fusion based semi-supervised learning method for hyperspectral image classification. More specially,two graphs are constructed from spectral-spatial Gabor features and original spectral signatures, respectively, and then areintegrated using an affine combination. Experimental results from an AVIRIS hyperspectral dataset verify the excellentclassification performance of our method.
展开▼