Exploring Oblique Rotation Factor to Restructure Deep Hyperspectral Image Classification.

Factor analysis (FA) is commonly used in fields such as economics and is now being introduced as a new tool on dimensionality reduction (DR) for hyperspectral image classification (HSIC), but FA usually employed orthogonal rotation to directly maximize the separation among factors, which would oversimplify the relationships between variables and factors, worse still, the orthogonal rotation often distorts the true relationships between underlying traits in real life and can not always accurately represent these relationships. To this end, this letter proposes a DR algorithm about FA based on oblique rotation Oblimax to improve HSIC. First, the common factors are extracted from the hyperspectral data to form a factor loading matrix which will be obliquely rotated, then its factor score is estimated to obtain the eigen dimensions for the hyperspectral data, thus realizing DR. On the basis of the successful DR, a deep classifier is constructed, especially, a double-branch structure about 3-D-convolutional neural networks (3-D-CNN) with different sizes is restructured to extract multi-scale spatial-spectral features, and early fusion is performed on the features, then 2-D-convolutional neural networks (2-D-CNN) is restructured to reduce the computational complexity and learns more spatial features. Finally, the accuracy of the proposed algorithm on the datasets Indian Pines (IP), Kennedy Space Center (KSC), and Muufl Gulfport (MUUFL), respectively achieves 99.78%, 99.95%, and 95.57%. It shows that the proposed algorithm in this letter has advantages in improving classification accuracy and reducing the complexity of computation.