Pixel-Wise Classification of Hyperspectral Images With 1D Convolutional SVM Networks
Mayar A. Shafey; Farid Melgani; Mohammed A.-M. Salem; Maryam Nabil Zakaria Al-Berry; Hala M. Ebied; El-Sayed A. El-Dahshan; Mohamed F. Tolba;
Abstract
Nowadays, remote sensing image analysis is needed in various important tasks such as city
planning, land-use classification, agriculture monitoring, military surveillance, and many other applications.
In this context, hyperspectral images can play a useful role, but require specific handling. This paper presents
a convolutional neural network based on one-dimensional support vector machine (SVM) convolution
operations (1D-CSVM) for the analysis of hyperspectral images. SVM-based CNN (CSVM) was introduced
first for the classification of high spatial resolution RGB images. It relies on linear SVMs to create filter banks
in the convolution layers. In this work, the network is modified to cope with one-dimensional hyperspectral
signatures and perform pixel-based classification. It thus analyzes each pixel spectrum independently from
the pixel spatial neighborhood. Experiments were carried out on four benchmark hyperspectral datasets,
Salinas-A, Kennedy Space Center (KSC), Indian Pines (IP) and Pavia University (Pavia-U). Compared to
state-of-the-art models, the proposed network produces promising results for all tested datasets, with an
accuracy up to 99.76%.
planning, land-use classification, agriculture monitoring, military surveillance, and many other applications.
In this context, hyperspectral images can play a useful role, but require specific handling. This paper presents
a convolutional neural network based on one-dimensional support vector machine (SVM) convolution
operations (1D-CSVM) for the analysis of hyperspectral images. SVM-based CNN (CSVM) was introduced
first for the classification of high spatial resolution RGB images. It relies on linear SVMs to create filter banks
in the convolution layers. In this work, the network is modified to cope with one-dimensional hyperspectral
signatures and perform pixel-based classification. It thus analyzes each pixel spectrum independently from
the pixel spatial neighborhood. Experiments were carried out on four benchmark hyperspectral datasets,
Salinas-A, Kennedy Space Center (KSC), Indian Pines (IP) and Pavia University (Pavia-U). Compared to
state-of-the-art models, the proposed network produces promising results for all tested datasets, with an
accuracy up to 99.76%.
Other data
Title | Pixel-Wise Classification of Hyperspectral Images With 1D Convolutional SVM Networks | Authors | Mayar A. Shafey; Farid Melgani; Mohammed A.-M. Salem; Maryam Nabil Zakaria Al-Berry ; Hala M. Ebied; El-Sayed A. El-Dahshan; Mohamed F. Tolba | Keywords | Convolutional neural network, feedforward learning, hyperspectral signature, machine learning, pixel-based classification, support vector machine. | Issue Date | 21-Dec-2022 | Publisher | IEEE | Journal | IEEE Access | Volume | 10 | Start page | 133174 | End page | 133185 | DOI | 10.1109/ACCESS.2022.3231579 |
Recommend this item
Similar Items from Core Recommender Database
Items in Ain Shams Scholar are protected by copyright, with all rights reserved, unless otherwise indicated.