Version 1
: Received: 3 February 2024 / Approved: 5 February 2024 / Online: 5 February 2024 (08:03:38 CET)
How to cite:
Chen, L.; Wei, Z.; Xu, Y.; Shuai, H. LLFWCNN: A Light-Weighted Low Frequency Wave-Based Network for Hyperspectral Image Classification. Preprints2024, 2024020243. https://doi.org/10.20944/preprints202402.0243.v1
Chen, L.; Wei, Z.; Xu, Y.; Shuai, H. LLFWCNN: A Light-Weighted Low Frequency Wave-Based Network for Hyperspectral Image Classification. Preprints 2024, 2024020243. https://doi.org/10.20944/preprints202402.0243.v1
Chen, L.; Wei, Z.; Xu, Y.; Shuai, H. LLFWCNN: A Light-Weighted Low Frequency Wave-Based Network for Hyperspectral Image Classification. Preprints2024, 2024020243. https://doi.org/10.20944/preprints202402.0243.v1
APA Style
Chen, L., Wei, Z., Xu, Y., & Shuai, H. (2024). LLFWCNN: A Light-Weighted Low Frequency Wave-Based Network for Hyperspectral Image Classification. Preprints. https://doi.org/10.20944/preprints202402.0243.v1
Chicago/Turabian Style
Chen, L., Yang Xu and Huiming Shuai. 2024 "LLFWCNN: A Light-Weighted Low Frequency Wave-Based Network for Hyperspectral Image Classification" Preprints. https://doi.org/10.20944/preprints202402.0243.v1
Abstract
In recent years, researches on combining wavelet decomposition and convolutional neural network (CNN) together to classify hyperspectral images (HSI) have emerged, and some effective classification models have been proposed and achieved good classification results. However, there are two problems for most of the proposed models. One is the heavy training parameters and the other is that there is no distinction between the classification effectiveness of low frequency and high frequency features after wavelet decomposition. In this paper, a new light-weighted HSI classification model (LLFWCNN) is proposed, which performs multi-layer wavelet decomposition for HSI after dimensionality reduction, and only arranges the low frequency features in a specific stack mode, then classifies them through a well-designed convolutional neural network. Compared with other classification models, the number of parameters is only 2.5% of that of other models. And only the low frequency features after wavelet decomposition are used, while the high frequency features are abandoned. The results showed that compared with the state-of-the-art classification models, LLFWCNN could obtain the same or even better classification results with fewer network parameters and proved that the low frequency features after wavelet decomposition provide LLFWCNN with more favorable information for HSI classification as well.
Computer Science and Mathematics, Computer Vision and Graphics
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
