Joint spatial-spectral hyperspectral image classification based on convolutional neural network
Joint spatial-spectral hyperspectral image classification based on convolutional neural network is a scholarly work, published in 2020 in ''Pattern Recognition Letters''. The main subjects of the publication include spatial analysis, convolutional neural network, artificial intelligence, feature extraction, softmax function, computer science, computer vision, remote sensing, feature, pixel, pattern recognition, and hyperspectral imaging. Experimental results on two datasets demonstrate that the proposed method outperforms other state-of-the-art methods qualitatively and quantitatively.