|
The unsupervised algorithm extracts hyperspectral image features, focusing on one aspect and often ignoring some other information. To guarantee the effective extraction of information before image analysis, an unsupervised feature extraction technique with hyperspectral imaging data based on multidimensional feature fusion is proposed. First, we use principal component analysis (PCA) to map the high-dimensional data to a simpler space and extract the spectral features based on the elimination of redundant relationships. Then, the multi-directional spatial feature extraction algorithm of Gabor texture and morphology is utilized to extract each primary component's spatial properties. Finally, the spectral features, morphological features, and Gabor texture features are fused together by the vector stacking fusion. In this paper, the HSI information is extracted unsupervised using the previous technique, and HSI classification experiments using support vector machines are carried out to validate the efficacy of the information. The experiments demonstrate that the proposed method improves the Kappa coefficient by at least 14% in the MUUFL dataset and by 30% in the Trento dataset compared with the traditional spectral feature extraction, which significantly improves the classification accuracy.
|
