A New Convolutional Kernel Classifier for Hyperspectral Image Classification

• Published in: IEEE journal of selected topics in applied earth observations and remote sensing Vol. 14; pp. 11240 - 11256
• Main Authors: Ansari, Mohsen, Homayouni, Saeid, Safari, Abdolreza, Niazmardi, Saeid
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 2021; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Approximation; Approximation method; Artificial neural networks; Benchmarks; Classification; Classification algorithms; Classifiers; Computer applications; Computer architecture; Convolutional neural network (CNN); Datasets; deep kernel; Deep learning; Feature extraction; hyperspectral classification; Hyperspectral imaging; Image analysis; Image classification; Image processing; Kernel; Kernels; Machine learning; Mathematical analysis; multiple kernel learning (MKL); Neural networks; Nonhomogeneous media; Optimization; Recurrent neural networks; Remote sensing; Task analysis
• ISSN: 1939-1404; 2151-1535; 2151-1535
• DOI: 10.1109/JSTARS.2021.3123087

Multiplekernel learning (MKL) algorithms are among the most successful classification methods for hyperspectral data. Nevertheless, these algorithms suffer from two main drawbacks of computational complexity and debility to admit to the end-to-end learning paradigm. This article proposed a convolutional kernel classifier (CKC) for hyperspectral remote sensing images to address these issues. The CKC uses the Nyström approximation method to estimate a low-rank approximation of the basis kernels, thus solves the issues associated with the high dimensionality of the basis kernels. The CKC uses deep architecture to learn the optimal combination of the basis kernels and the classification task to enable end-to-end learning. The proposed CKC's architecture is based on a one-dimensional-convolutional neural network (CNN-1-D), and it uses kernel dropout to prevent overfitting. It is the first instance of deep-kernel algorithms in the field of remote sensing. The proposed method was compared with several well-known hyperspectral image analysis MKL algorithms, including a multi-kernel variant of the deep kernel machine optimization, MKL-average, Simple-MKL, and generalize MKL, and state-of-the-art deep learning models, including Vanilla recurrent neural network (VanillaRNN) and CNN-1-D in classifying four benchmark hyperspectral datasets. The experimental results show that the CKC consistently outperforms all the competitor methods, and its runtime is lower than its MKL algorithm counterparts on four benchmark hyperspectral datasets. Moreover, the Nyström approximation solves the high dimensionality of the basis kernels and boosts classification accuracy. The source codes of CKC are available from: https://github.com/MohsenAnsari1373/A-New-Convolutional-Kernel-Classifier-for-Hyperspectral-Image-Classification .