Abstract
Hyperspectral Image (HSI) has many narrow and continuous spectral bands. There are many problems with the original HSI. For example, the classification accuracy of the test data is affected by the curse of dimensionality problem because the image bands are highly correlated in both space and time. So, dimensionality reduction is done and improved the classification result. In this paper, a deep convolutional network is suggested to reduce the dimensionality of HSI classification by considering both spectral and spatial features. When combined factor analysis and mRMR are used, spectral features are reduced, while 2D wavelet CNN reduces spatial features. A wavelet CNN is an extension of a 2D CNN that can be used to classify high-resolution images. Wavelet CNNs also use layered wavelet transformations to pull out spectral features. A wavelet CNN is easier to calculate than a 3D CNN or a 2D-3D CNN. In the next step, the spectral features are connected to the two-dimensional CNN to get the spatial features, creating a spatial-spectral feature vector. It makes a model that can accurately classify HSI data at multiple resolutions. As part of the HSI classification, we used data sets from the Pavia University and Salinas Scene dataset to see how well the two methods work together. In two datasets, the proposed Expanded 2DNET did better than the handcrafted methods, according to the experiment.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Chen, Z., Jiang, J., Jiang, X., Fang, X., Cai, Z.: Spectral-spatial feature extraction of hyperspectral images based on propagation filter. Sensors 18, 1978 (2018). https://doi.org/10.3390/s18061978
Kong, Y., Wang, X., Cheng, Y.: Spectral–spatial feature extraction for HSI classification based on supervised hypergraph and sample expanded CNN. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 11, 4128–4140 (2018). https://doi.org/10.1109/JSTARS.2018.2869210
Zhao, W., Du, S.: Spectral-spatial feature extraction for hyperspectral image classification: a dimension reduction and deep learning approach. IEEE Trans. Geosci. Remote Sens. 54, 4544–4554 (2016). https://doi.org/10.1109/TGRS.2016.2543748
Ali, M.U., Ahmed, S., Ferzund, J., Mehmood, A., Rehman, A.: Using PCA and factor analysis for dimensionality reduction of bio-informatics data. Int. J. Adv. Comput. Sci. Appl. (2017). https://doi.org/10.48550/arXiv.1707.07189
Islam, R., Ahmed, B., Hossain, M.A.: Feature reduction based on segmented principal component analysis for hyperspectral images classification (2019). https://doi.org/10.1109/ECACE.2019.8679394
Salas-Gonzalez, D., et al.: Feature selection using factor analysis for Alzheimer’s diagnosis using 18F-FDG PET images. Med. Phys. 37, 6084–6095 (2010)
Islam, R., Ahmed, B., Hossain, M.A.: Feature reduction of hyperspectral image for classification. Spatial Science (2020). https://doi.org/10.1080/14498596.2020.1770137
Xu, Y., Jones, G., Li, J., Wang, B., Sun, C.: A study on mutual information-based feature selection for text categorization. J. Comput. Inf. Syst. 3, 1007–1012 (2007)
Diakite, A., Gui, J., Xiaping, F.: Hyperspectral image classification using 3D 2D CNN. IET Image Proc. 15 (2021). https://doi.org/10.1049/ipr2.12087
Roy, S., Krishna, G., Dubey, S.R., Chaudhuri, B.: HybridSN: exploring 3-D-2-D CNN feature hierarchy for hyperspectral image classification. IEEE Geosci. Remote Sens. Lett. 17, 277–281 (2019). https://doi.org/10.1109/LGRS.2019.2918719
Chakraborty, T., Trehan, U.: SpectralNET: exploring spatial-spectral waveletCNN for hyperspectral image classification (2021). Arxiv preprint Arxiv:2104.00341
Khosla, N.: Dimensionality reduction using factor analysis. Griffith University, Australia (2004)
Shrestha, N.: Factor analysis as a tool for survey analysis. Am. J. Appl. Math. Stat. 9(1), 4–11 (2021). https://doi.org/10.12691/ajams-9-1-2
Shu, W., Qian, W.: Mutual information-based feature selection from set-valued data, pp. 733–739 (2014). https://doi.org/10.1109/ICTAI.2014.114
Zhou, H., Wang, X., Zhu, R.: Feature selection based on mutual information with correlation coefficient. Appl. Intell. 52(5), 5457–5474 (2021). https://doi.org/10.1007/s10489-021-02524-x
Vergara, J.R., Estévez, P.A.: A review of feature selection methods based on mutual information. Neural Comput. Appl. 24(1), 175–186 (2013). https://doi.org/10.1007/s00521-013-1368-0
De Jay, N., Papillon-Cavanagh, S., Olsen, C., El-Hachem, N., Bontempi, G., Haibe-Kains, B.: mRMRe: an R package for parallelized mRMR ensemble feature selection. Bioinformatics 29(18), 2365–2368 (2013)
Kursun, O., Sakar, C.O., Favorov, O., Aydin, N., Gurgen, F.: Using covariates for improving the minimum redundancy maximum relevance feature selection method. Turk. J. Electr. Eng. Comput. Sci. 18, 975–987 (2010). https://doi.org/10.3906/elk-0906-75
Aghaeipoor, F., Javidi, M.M.: A hybrid fuzzy feature selection algorithm for high-dimensional regression problems: an mRMR-based framework. Expert Syst. Appl. 162, 113859 (2020). https://doi.org/10.1016/j.eswa.2020.113859
Billah, M., Waheed, S.: Minimum redundancy maximum relevance (mRMR) based feature selection from endoscopic images for automatic gastrointestinal polyp detection. Multimedia Tools and Applications 79(33–34), 23633–23643 (2020). https://doi.org/10.1007/s11042-020-09151-7
Vaddi, R., Manoharan, P.: Probabilistic PCA based hyper spectral image classification for remote sensing applications. In: Abraham, A., Cherukuri, A.K., Melin, P., Gandhi, N. (eds.) ISDA 2018 2018. AISC, vol. 941, pp. 863–869. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-16660-1_84
Vaddi, R., Prabukumar, M.: Hyperspectral image classification using CNN with spectral and spatial features integration. Infrared Phys. Technol. 107, 103296 (2020). https://doi.org/10.1016/j.infrared.2020.103296
Wang, K., Cheng, L., Yong, B.: Spectral-similarity-based kernel of SVM for hyperspectral image classification. Remote Sens. 12, 2154 (2020). https://doi.org/10.3390/rs12132154
Aparna, G., Rachana, K., Rikhita, K., Phaneendra Kumar, B.L.N.: Comparison of feature reduction techniques for change detection in remote sensing. In: Chowdary, P.S.R., Anguera, J., Satapathy, S.C., Bhateja, V. (eds.) Evolution in Signal Processing and Telecommunication Networks. LNEE, vol. 839, pp. 325–333. Springer, Singapore (2022). https://doi.org/10.1007/978-981-16-8554-5_30
Kong, F., Hu, K., Li, Y., Li, D., Zhao, S.: Spectral-spatial feature partitioned extraction based on CNN for multispectral image compression. Remote Sens. 13, 9 (2020). https://doi.org/10.3390/rs13010009
Fujieda, S., Takayama, K., Hachisuka, T.: Wavelet convolutional neural networks (2018). arXiv preprint arXiv:1805.08620
Ghaderizadeh, S., Abbasi-Moghadam, D., Sharifi, A., Zhao, Na., Tariq, A.: Hyperspectral image classification using a hybrid 3D-2D convolutional neural networks. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 14, 7570–7588 (2021). https://doi.org/10.1109/JSTARS.2021.3099118
Wang, C., Ma, N., Ming, Y., Wang, Q., Xia, J.: Classification of hyperspectral imagery with a 3D convolutional neural network and J-M distance. Adv. Space Res. 64, 886–899 (2019). https://doi.org/10.1016/j.asr.2019.05.005
Li, X., et al.: A wavelet transform-assisted convolutional neural network multi-model framework for monitoring large-scale fluorochemical engineering processes. Processes 8(11), 1480 (2020). https://doi.org/10.3390/pr8111480
Uddin, M.P., Mamun, M.A., Afjal, M.I., Hossain, M.A.: Information-theoretic feature selection with segmentation-based folded principal component analysis (PCA) for hyperspectral image classification. Int. J. Remote Sens. 42, 286–321 (2020). https://doi.org/10.1080/01431161.2020.1807650
Fu, H., Sun, G., Jaime, Z., Aizhu, Z., Ren, J., Jia, X.: A novel spectral-spatial singular spectrum analysis technique for near real-time in situ feature extraction in hyperspectral imaging. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sens. 13, 2214–2225 (2020). https://doi.org/10.1109/JSTARS.2020.2992230
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering
About this paper
Cite this paper
Islam, M.T., Kumar, M., Islam, M.R. (2023). Spectral–Spatial Feature Reduction for Hyperspectral Image Classification. In: Satu, M.S., Moni, M.A., Kaiser, M.S., Arefin, M.S. (eds) Machine Intelligence and Emerging Technologies. MIET 2022. Lecture Notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering, vol 491. Springer, Cham. https://doi.org/10.1007/978-3-031-34622-4_45
Download citation
DOI: https://doi.org/10.1007/978-3-031-34622-4_45
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-34621-7
Online ISBN: 978-3-031-34622-4
eBook Packages: Computer ScienceComputer Science (R0)