Band Selection Methods for Hyperspectral Imagery Analysis – A Critical Comparison
Keywords:
Dimensionality Reduction, Curse of Dimensionality, Band Selection, Band SubsetAbstract
Dimensionality Reduction (DR) encompasses a multifaceted array of techniques essential for addressing the challenges inherent in high-dimensional data, particularly evident in the analysis of Hyperspectral Images (HSI). The "Curse of Dimensionality" presents a formidable obstacle, rendering the utilization of all spectral bands computationally daunting. DR in HSI endeavors to preserve pertinent information while alleviating computational burdens, often through Band Selection methods. This analysis consolidates the contributions of researchers in the past 10 years, categorizing methodologies into nine distinct categories. Notably, clustering-based and optimization-based techniques emerge as frontrunners, consistently yielding superior accuracy. Experimentation across 19 real-time HSI datasets, including several highly-cited examples, underscores the efficacy of clustering-based methodologies in achieving optimal accuracy. In conclusion, while all DR methods merit appreciation, clustering-based approaches stand out for their demonstrated effectiveness in preserving data fidelity while reducing dimensionality.
Downloads
References
Datta, Aloke, Susmita Ghosh, and Ashish Ghosh. "Combination of clustering and ranking techniques for unsupervised band selection of hyperspectral images." IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Vol 8, no. 6, pp: 2814-2823,May 22, 2015. DOI: 10.1109/JSTARS.2015.2428276.
Wang, Qi, Fahong Zhang, and Xuelong Li. "Optimal clustering framework for hyperspectral band selection." IEEE Transactions on Geoscience and Remote Sensing vol 56, no. 10, pp: 5910-5922.May 9, 2018. DOI: 10.1109/TGRS.2018.2828161
Huang, Shaoguang, Hongyan Zhang, and Aleksandra Pižurica. "A structural subspace clustering approach for hyperspectral band selection." IEEE Transactions on Geoscience and Remote Sensing vol 60, pp: 1-15, Aug 11, 2021.DOI: 10.1109/TGRS.2021.3102422
Motiyani, Hitenkumar, Quazi Sameed, Prashant Kumar Mali, and Anand Mehta. "Clustering of Hyperspectral Images using Entropy based Multiple Features (Bands) Set Selection." In 2023 International Conference on Computational Intelligence and Sustainable Engineering Solutions (CISES), pp. 849-854, Apr 28, 2023. DOI: 10.1109/CISES58720.2023.10183495.
Wang, Jingyu, Hongmei Wang, Zhenyu Ma, Lin Wang, Qi Wang, and Xuelong Li. "Unsupervised hyperspectral band selection based on hypergraph spectral clustering." IEEE Geoscience and Remote Sensing Letters vol 19, pp: 1-5,Oct 5, 2021. DOI: 10.1109/LGRS.2021.3115340.
Wang, Qi, Qiang Li, and Xuelong Li. "A fast neighborhood grouping method for hyperspectral band selection." IEEE Transactions on Geoscience and Remote Sensing vol 59, no. 6, pp: 5028-5039, Jul 31, 2020. DOI: 10.1109/TGRS.2020.3011002.
Karoui, Moussa Sofiane, Khelifa Djerriri, and Issam Boukerch. "Unsupervised hyperspectral band selection by sequentially clustering a mahalanobis-based dissimilarity of spectrally variable endmembers." 2020 Mediterranean and Middle-East Geoscience and Remote Sensing Symposium (M2GARSS). IEEE, 2020. DOI: 10.1109/M2GARSS47143.2020.9105250.
Jia, Sen, et al. "A novel ranking-based clustering approach for hyperspectral band selection." IEEE Transactions on Geoscience and Remote Sensing vol 54,no 1, pp: 88-102.2015. DOI: 10.1109/TGRS.2015.2450759
Baisantry, M., Sao, A. K., Shukla, D. P. "Discriminative spectral–spatial feature extraction-based band selection for hyperspectral image classification". IEEE Transactions on Geoscience and Remote Sensing, vol 60, pp: 1-14. (2021). DOI: 10.1109/TGRS.2021.3129841
Mali, P. K., Motiyani, H., Sameed, Q., Mehta, "A. Hyper Spectral Image Clustering and Local Feature Selection using Gini Impurity". In 2023 7th International Conference on Trends in Electronics and Informatics (ICOEI). pp. 1629-1634. IEEE. (2023, April). DOI: 10.1109/ICOEI56765.2023.10125605
He, C., Zhang, Y., Gong, D., Song, X., Sun, X. "A multitask bee colony band selection algorithm with variable-size clustering for hyperspectral images". IEEE Transactions on Evolutionary Computation, vol 26, no 6, pp: 1566-1580. (2022). DOI: 10.1109/TEVC.2022.3159253
Li, S., Liu, Z., Fang, L., Li, Q." Block diagonal representation learning for hyperspectral band selection". IEEE Transactions on Geoscience and Remote Sensing.(2023). DOI: 10.1109/TGRS.2023.3266811
Tang, C., Wang, J., Zheng, X., Liu, X., Xie, W., Li, X., Zhu, X. . "Spatial and spectral structure preserved self-representation for unsupervised hyperspectral band selection". IEEE Transactions on Geoscience and Remote Sensing, vol 61,pp: 1-13.2023. DOI: 10.1109/TGRS.2023.3331236.
Sun, Weiwei, et al. "Hyperspectral band selection using weighted kernel regularization." IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing vol 12, no 9, pp: 3665-3676,(2019).DOI: 10.1109/JSTARS.2019.2922201.
Kamandar, Mehdi. "Kernel-Based Band Selection for Hyperspectral Image Classification." at 31st International Conference on Electrical Engineering '' ICEE. IEEE, Tehran, Iran May 9-11,2023, pp: 149-153. DOI: 10.1109/ICEE59167.2023.10334890.
Cao, X., Wu, B., Tao, D., and Jiao, L. "Automatic band selection using spatial-structure information and classifier-based clustering", in ''~emph{IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing}, vol. 9, no. 9,(2016). pp: 4352-4360. DOI: 10.1109/JSTARS.2015.2509461.
Dey A, Ghosh S, Ientilucci EJ. "A Combination of Mutual and Neighborhood Information for Band Selection in Hyperspectral Images", ''IEEE International Geoscience and Remote Sensing Symposium pp: 6077-6080, Jul 16, 2023. IEEE. DOI: 10.1109/IGARSS52108.2023.10283374.
Sun W, Peng J, Yang G, Du Q. "Correntropy-based sparse spectral clustering for hyperspectral band selection", IEEE Geoscience and Remote Sensing Letters. vol 17, no 3, pp: 484-488, Jul 15, 2019. DOI: 10.1109/LGRS.2019.2924934
MartÍnez-UsÓMartinez-Uso, Adolfo, et al. "Clustering-based hyperspectral band selection using information measures." IEEE Transactions on Geoscience and Remote Sensing vol 45,no 12, pp: 4158-4171, 2007. DOI: 10.1109/TGRS.2007.904951
Jain, Namita, and Susmita Ghosh. "An unsupervised band selection method for hyperspectral images using mutual information based dependence index." IGARSS 2022-2022 IEEE International Geoscience and Remote Sensing Symposium. IEEE, pp: 783-786,2022. DOI:10.1109/IGARSS46834.2022.9884061
Ali, UA Md Ehsan, and Keisuke Kameyama. "Informative Band Subset Selection for Hyperspectral Image Classification using Joint and Conditional Mutual Information." 2022 IEEE Symposium Series on Computational Intelligence (SSCI). IEEE, ,pp: 573-580,2022. DOI:10.1109/SSCI51031.2022.10022154
Chugh, Rohit, et al. "Spectrally Optimized Feature Identification (SOFI): A Novel Band Selection Method for Hyperspectral Image Analysis." 2023 International Conference on Machine Intelligence for GeoAnalytics and Remote Sensing (MIGARS). Vol. 1. IEEE, pp: 1-3, 2023. DOI: 10.1109/MIGARS57353.2023.10064625.
Qi, Jianwen, et al. "Tensor Decomposition Based Latent Feature Clustering for Hyperspectral Band Selection." ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE,pp: 1-5, 2023. DOI: 10.1109/ICASSP49357.2023.10096731.
Dou, Zeyang, et al. "Band selection of hyperspectral images using attention-based autoencoders." IEEE Geoscience and Remote Sensing Letters vol 18,no 1, pp: 147-151.(2020). DOI:10.1109/LGRS.2020.2967815.
Bao, Dong, Gervase Tuxworth, and Jun Zhou. "Similarity-Based Hyperspectral Band Selection Using Deep Reinforcement Learning." 2022 12th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS). IEEE, pp: 1-5,2022. DOI:10.1109/WHISPERS56178.2022.9955115.
Liu, Yufei, et al. "BSFormer: Transformer-Based Reconstruction Network for Hyperspectral Band Selection." IEEE Geoscience and Remote Sensing Letters JUl, 2023. DOI:10.1109/LGRS.2023.3297746.
Zhou, Yuan, et al. "Hyperspectral Band Selection with Iterative Graph Auto-encoder." IEEE Transactions on Geoscience and Remote Sensing May 9, 2023. DOI: 10.1109/TGRS.2023.3273776.
Francis, Jobin, et al. "A Tensor Non-Convex Low Rank And Sparse Constrained Band Selection Scheme For Clustering Of Hyperspectral Paper Data." 2022 12th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS). IEEE, pp: 1-5, 2022. DOI: 10.1109/WHISPERS56178.2022.9955084.
Das, Samiran, et al. "Sparsity regularized deep subspace clustering for multicriterion-based hyperspectral band selection." IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing vol 15, pp: 4264-4278, 2022. DOI: 10.1109/JSTARS.2022.3172112.
Zhang, Mingyang, Jingjing Ma, and Maoguo Gong. "Unsupervised hyperspectral band selection by fuzzy clustering with particle swarm optimization." IEEE Geoscience and Remote Sensing Letters vol 14, no 5, pp: 773-777, 2017. DOI:10.1109/LGRS.2017.2681118.
Wan, Yuting, Chao Chen, Ailong Ma, Liangpei Zhang, Xunqiang Gong, and Yanfei Zhong. "Adaptive Multi-Strategy Particle Swarm Optimization for Hyperspectral Remote Sensing Image Band Selection." IEEE Transactions on Geoscience and Remote Sensing vol 61,(2023). DOI: 10.1109/TGRS.2023.3305545.
Paul, A., S. Bhattacharya, D. Dutta, J. R. Sharma, and V. K. Dadhwal. "Band selection in hyperspectral imagery using spatial cluster mean and genetic algorithms". GISci Remote Sens vol 52,no 6,pp: 644–661. (2015). DOI: 10.1080/15481603.2015.1075180.
Tong, Xiaoyi, and Xuchuan Zhou. "Hyperspectral band selection algorithm based on artificial bee colony fusion genetic idea." 2023 3rd International Symposium on Computer Technology and Information Science (ISCTIS). IEEE, pp: 323-329, 2023. DOI: 10.1109/ISCTIS58954.2023.10213204.
Yin, Jihao, Yifei Wang, and Jiankun Hu. "A new dimensionality reduction algorithm for hyperspectral image using evolutionary strategy." IEEE Transactions on Industrial Informatics vol 8, no 4, pp:: 935-943,2012. DOI:10.1109/TII.2012.2205397.
Alkhatib, Mohammed Q., and Miguel Velez-Reyes. "Using band subset selection for dimensionality reduction in superpixel segmentation of hyperspectral imagery." 2020 IEEE International Conference on Image Processing (ICIP). IEEE, pp: 26-30, OCT 25,2020. DOI: 10.1109/ICIP40778.2020.9190710.
Wang, Yulei, et al. "A hybrid gray wolf optimizer for hyperspectral image band selection." IEEE Transactions on Geoscience and Remote Sensing vol 60, pp: 1-13, Apr 18,2022. DOI: 10.1109/TGRS.2022.3167888.
Wu, Meng, et al. "Heterogeneous Cuckoo Search-Based Unsupervised Band Selection for Hyperspectral Image Classification." IEEE Transactions on Geoscience and Remote Sensing, Dec 5, 2023. DOI: 10.1109/TGRS.2023.3339828.
Xu, ShaoJuan, et al. "Hyperspectral Band Selection Based on Fuzzy C-means and Dingo Optimization Algorithm." 2023 IEEE 13th International Conference on Electronics Information and Emergency Communication (ICEIEC). IEEE, pp. 251-254, Jul 14, 2023. DOI: 10.1109/ICEIEC58029.2023.10199397.
Ou, Xianfeng, et al. "Multi-objective unsupervised band selection method for hyperspectral images classification." IEEE Transactions on Image Processing vol 32, pp: 1952-1965,Mar 22,2023. DOI: 10.1109/TIP.2023.3258739.
Yang, Hong, et al. "Multitask Multiobjective Optimization Method for Adaptive Band Selection." 2023 International Conference on Cyber-Physical Social Intelligence (ICCSI). IEEE, pp:291-296, OCT 20,2023. DOI: 10.1109/ICCSI58851.2023.10304044.
Ma, Mingyang, et al. "Spectral correlation-based diverse band selection for hyperspectral image classification." IEEE Transactions on Geoscience and Remote Sensing vol 61, pp: 1-13, Mar 31, 2023. DOI: 10.1109/TGRS.2023.3263580.
Wang, Qijun, et al. "Unsupervised Hyperspectral Band Selection via Structure-Conserved and Neighborhood-Grouped Evolutionary Algorithm." IEEE Transactions on Geoscience and Remote Sensing Aug 21, 2023. DOI: 10.1109/TGRS.2023.3309830.
Hu, Hai-Miao, et al. "One-shot neural band selection for spectral recovery." ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp: 1-5, June 4, 2023. DOI: 10.1109/ICASSP49357.2023.10096000.
Yang, Rongchao, and Jiangming Kan. "An unsupervised hyperspectral band selection method based on shared nearest neighbor and correlation analysis." IEEE Access vol 7,pp: 185532-185542, Dec 20, 2019. DOI: 10.1109/ACCESS.2019.2961256.
Li, Qiang, Qi Wang, and Xuelong Li. "An efficient clustering method for hyperspectral optimal band selection via shared nearest neighbor." Remote Sensing vol 11, no 3, pp: 350,Feb 10,2019. DOI: https://doi.org/10.3390/rs11030350.
Llaveria, David, et al. "Ranking Methodology for Sequential Band Selection Combining Data Dispersion and Spectral Band Correlation." IGARSS 2022-2022 IEEE International Geoscience and Remote Sensing Symposium. IEEE,pp:775-778, July 17, 2022. DOI: 10.1109/IGARSS46834.2022.9884380.
Sun, Weiwei, et al. "Fast and latent low-rank subspace clustering for hyperspectral band selection." IEEE Transactions on Geoscience and Remote Sensing vol 58, no 6, pp: 3906-3915,Jan 3, 2020. DOI:10.1109/TGRS.2019.2959342.
Xu, Buyun, et al. "A similarity-based ranking method for hyperspectral band selection." IEEE Transactions on Geoscience and Remote Sensing vol 59, no 11, pp: 9585-9599, Jan 14, 2021. DOI: 10.1109/TGRS.2020.3048138.
Li, Shuying, et al. "Hyperspectral band selection via difference between intergroups." IEEE Transactions on Geoscience and Remote Sensing vol 61, pp:1-10, Feb 3, 2023. DOI: 10.1109/TGRS.2023.3242239.
Datta, Aloke, Susmita Ghosh, and Ashish Ghosh. "Clustering based band selection for hyperspectral images." 2012 international conference on communications, devices and intelligent systems (CODIS). IEEE, pp: 101-104, Dec 28, 2012. DOI: 10.1109/CODIS.2012.6422146.
Chang, Chein-I., Yi-Mei Kuo, and Peter Fuming Hu. "Unsupervised rate distortion function-based band subset selection for hyperspectral image classification." IEEE Transactions on Geoscience and Remote Sensing Jul 19,2023. DOI: 10.1109/TGRS.2023.3296728.
Zhu, Qingyu, et al. "Hyperspectral band selection based on improved affinity propagation." 2021 11th Workshop on Hyperspectral Imaging and Signal Processing: Evolution in Remote Sensing (WHISPERS). IEEE, pp:1-4, Mar 24 ,2021. DOI: 10.1109/WHISPERS52202.2021.9484004.
Jampana, Meenakshi, et al. "Wavelet Entropy based Band Selection for Hyperspectral Images." 2023 Second International Conference on Electronics and Renewable Systems (ICEARS). IEEE, pp: 444-448, Mar 2, 2023. DOI: 10.1109/ICEARS56392.2023.10085053.
Henneberger, Katherine, Longxiu Huang, and Jing Qin. "Hyperspectral Band Selection Based on Matrix CUR Decomposition." IGARSS 2023-2023 IEEE International Geoscience and Remote Sensing Symposium. IEEE, pp: 7380-7383,Jul 16, 2023. DOI: 10.1109/IGARSS52108.2023.10282944.
Qi, Jianwen, et al. "Tensor Decomposition Based Latent Feature Clustering for Hyperspectral Band Selection." ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, pp: 1-5,Jun 4, 2023. DOI: 10.1109/ICASSP49357.2023.10096731.
Zhang, Wenxian, et al. "Sparse Principal Component Analysis and Adaptive Multigraph Learning for Hyperspectral Band Selection." IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Nov 21, 2023. DOI: 10.1109/JSTARS.2023.3335286.
Zhou, Hui, Zhaoxin Yue, and Dan Yao. "Band Selection Method Based on Orthogonal Projection and Cross Entropy." 2022 15th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics (CISP-BMEI). IEEE, pp: 1-6, Nov 5, 2022. DOI: 10.1109/CISP-BMEI56279.2022.9979889.
You, Mengbo, et al. "Robust Unsupervised Hyperspectral Band Selection via Global Affinity Matrix Reconstruction." IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing July 28, 2023. DOI: 10.1109/JSTARS.2023.3299731.
Shang, Xiaodi, Chuanyu Cui, and Xudong Sun. "Spectral-spatial hypergraph-regularized self-representation for hyperspectral band selection." IEEE Geoscience and Remote Sensing Letters May 15, 2023. DOI: 10.1109/LGRS.2023.3276055.
Shafana, N. Jeenath, K. T. Jayan, and R. Divagar Iyyappan. "Optimal Band Selection and Scale based Feature Selection for Hyper Spectral Image Classification using Hybrid Neural Network." 2022 3rd International Conference on Smart Electronics and Communication (ICOSEC). IEEE, pp: 1515-1519, OCT 19, 2022. DOI: 10.1109/ICOSEC54921.2022.9952114.
Race, Benjamin, and Todd Wittman. "On Dimension Reduction of Hyperspectral Images." IGARSS 2023-2023 IEEE International Geoscience and Remote Sensing Symposium. IEEE, pp: 7396-7399,July 16, 2023. DOI: 10.1109/IGARSS52108.2023.10281535.
Downloads
Published
How to Cite
Issue
Section
License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
All papers should be submitted electronically. All submitted manuscripts must be original work that is not under submission at another journal or under consideration for publication in another form, such as a monograph or chapter of a book. Authors of submitted papers are obligated not to submit their paper for publication elsewhere until an editorial decision is rendered on their submission. Further, authors of accepted papers are prohibited from publishing the results in other publications that appear before the paper is published in the Journal unless they receive approval for doing so from the Editor-In-Chief.
IJISAE open access articles are licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. This license lets the audience to give appropriate credit, provide a link to the license, and indicate if changes were made and if they remix, transform, or build upon the material, they must distribute contributions under the same license as the original.
