Conference Paper Semi-supervised hyperspectral manifold learning for regression

宇都, 有昭  ,  Uto, Kuniaki  ,  小杉, 幸夫  ,  KOSUGI, YUKIO  ,  齋藤, 元也  ,  Saito, Genya

pp.9 - 12 , 2015-07
Regression based on hyperspectral remote sensing data con- tains two-fold complications, i.e., lack of labeled data and dif- ficulty in collecting quantitative ground-truth. In this paper, we propose semi-supervised subspace learning methods for regression based on a generalized eigenvalue problem. The methods exploit abundant unlabeled data for low-dimensional subspace learning. Quantitative target values are replaced by ordinal values that can be easily acquired in comparison with accurate quantitative ground-truth. The subspace learning methods are further expanded into nonlinear manifold learn- ing methods by the kernel trick. The methods are applied to estimation problems of growth-state-related properties of rice based on hyprspectral remote sensing data of rice paddies.

Number of accesses :  

Other information