Abstract
Hyperspectral image classification has become an important issue in remote sensing due to the significant amount of spectral information in HSI. The costly and time-consuming annotation task of HSIs makes the number of labeled samples is limited. To address the above problem, we propose an enhanced semi-supervised support vector machine algorithm for spectral-spatial HSI classification. To fully capture the spectral and spatial information of HSI, we use local binary pattern to obtain spatial feature. The captured spatial features are concatenated with the spectral features to yield the hybrid spectral-spatial features. Self-training mechanism is then adopted to gradually select confident unlabeled samples with their pseudo-labels and add them to the labeled set. To further improve the classification performance of the semi-supervised support vector machine, we choose a cuckoo search algorithm based on the chaotic catfish effect to find its optimal combination of parameters. The experimental results on two publicly available HSI datasets show that the proposed model achieves excellent classification accuracy for each category in hyperspectral images, and also has superior overall accuracy compared with other comparative algorithms. Adequate experiments and analysis illustrate the promising potential and prospect of our proposed model for HSI classification.
REFERENCES
K. L.-M. Ang and J. K. Ph. Seng, “Big data and machine learning with hyperspectral information in agriculture,” IEEE Access 9, 36699–36718 (2021). https://doi.org/10.1109/ACCESS.2021.3051196
K. Bennett and A. Demiriz, “Semi-supervised support vector machine,” Adv. Neural Inf. Process. Syst. 11, 368–374 (1999).
O. Chapelle, B. Schölkopf, and A. Zien, “Transductive support vector machines,” in Semi-Supervised Learning (MIT Press, 2006).
O. Chapelle, V. Sindhwani, and S. S. Keerthi, “Branch and bound for semi-supervised support vector machines,” in Advances in Neural Information Processing Systems, Ed. by B. Schölkopf, J. Platt, and T. Hofmann (The MIT Press, 2007), Vol. 19, pp. 217–224. https://doi.org/10.7551/mitpress/7503.003.0032
O. Chapelle, V. Sindhwani, and S. S. Keerthi, “Optimization techniques for semi-supervised support vector machine,” J. Mach. Learn. Res. 9, 203–233 (2008).
H. Chen, Yi. Yu, Yi. Jia, and L. Zhang, “Safe transductive support vector machine,” Connection Sci. 34, 942–959 (2022). https://doi.org/10.1080/09540091.2021.2024511
E. Cheung and Yu. Li, “Self-training with adaptive regularization for S3VM,” in 2017 Int. Joint Conf. on Neural Networks (IJCNN), Anchorage, Alaska, 2017 (IEEE, 2017), pp. 3633–3640. https://doi.org/10.1109/ijcnn.2017.7966313
C. Cortes and V. Vapnik, “Support-vector networks,” Mach. Learn. 20, 273–297 (1995). https://doi.org/10.1007/bf00994018
Q. Du and H. Yang, “Similarity-based unsupervised band selection for hyperspectral image analysis,” IEEE Geosci. Remote Sensing Lett. 5, 564–568 (2008). https://doi.org/10.1109/lgrs.2008.2000619
M. T. Eismann, A. D. Stocker, and N. M. Nasrabadi, “Automated hyperspectral cueing for civilian search and rescue,” Proc. IEEE 97, 1031–1055 (2009). https://doi.org/10.1109/JPROC.2009.2013561
W. Emara, M. K. M. Karnstedt, K. Sattler, D. Habich, and W. Lehner, “An approach for incremental semi-supervised SVM,” in Seventh IEEE Int. Conf. on Data Mining Workshops (ICDMW 2007), Omaha, Neb., 2007 (IEEE, 2007), pp. 539–544. https://doi.org/10.1109/icdmw.2007.106
J. Feng, Z. Ye, D. Li, Yu. Liang, X. Tang, and X. Zhang, “Hyperspectral image classification based on semi-supervised dual-branch convolutional autoencoder with self-attention,” in IGARSS 2020–2020 IEEE Int. Geoscience and Remote Sensing Symp., Waikoloa, Hawaii, 2020 (IEEE, 2020), pp. 1267–1270. https://doi.org/10.1109/igarss39084.2020.9323656
F. Gao, J. Mei, J. Sun, J. Wang, E. Yang, and A. Hussain, “A novel classification algorithm based on incremental semi-supervised support vector machine,” PLoS One 10, e0135709 (2015). https://doi.org/10.1371/journal.pone.0135709
F. Gao, Q. Wang, J. Dong, and Q. Xu, “Spectral and spatial classification of hyperspectral images based on random multi-graphs,” Remote Sensing 10, 1271 (2018). https://doi.org/10.3390/rs10081271
A. F. H. Goetz, G. Vane, J. E. Solomon, and B. N. Rock, “Imaging spectrometry for earth remote sensing,” Science 228, 1147–1153 (1985). https://doi.org/10.1126/science.228.4704.1147
Z. He, K. Xia, Yu. Hu, Z. Yin, S. Wang, and J. Zhang, “Semi-supervised anchor graph ensemble for large-scale hyperspectral image classification,” Int. J. Remote Sensing 43, 1894–1918 (2022). https://doi.org/10.1080/01431161.2022.2048916
Z. He, K. Xia, T. Li, B. Zu, Z. Yin, and J. Zhang, “A constrained graph-based semi-supervised algorithm combined with particle cooperation and competition for hyperspectral image classification,” Remote Sensing 13, 193 (2021). https://doi.org/10.3390/rs13020193
Z. He, K. Xia, W. Niu, N. Aslam, and J. Hou, “Semisupervised SVM based on cuckoo search algorithm and its application,” Math. Probl. Eng. 2018, 8243764 (2018). https://doi.org/10.1155/2018/8243764
S. Jia, S. Jiang, Z. Lin, N. Li, M. Xu, and S. Yu, “A survey: Deep learning for hyperspectral image classification with few labeled samples,” Neurocomputing 448, 179–204 (2021). https://doi.org/10.1016/j.neucom.2021.03.035
S. Jia, S. Jiang, Z. Lin, M. Xu, W. Sun, Q. Huang, J. Zhu, and X. Jia, “A semisupervised siamese network for hyperspectral image classification,” IEEE Trans. Geosci. Remote Sensing 60, 5516417 (2021). https://doi.org/10.1109/tgrs.2021.3116138
T. Joachims, “Transductive inference for text classification using support vector machines,” in ICML’99: Proc. Sixteenth Int. Conf. on Machine Learning, Ed. by I. Bratko and S. Dzeroski (Morgan Kaufmann, San Francisco, 1999), pp. 200–209.
Yu. Li, C. Guan, H. Li, and Z. Chin, “A self-training semi-supervised SVM algorithm and its application in an EEG-based brain computer interface speller system,” Pattern Recognit. Lett. 29, 1285–1294 (2008). https://doi.org/10.1016/j.patrec.2008.01.030
Yu.-F. Li and Zh.-H. Zhou, “Towards making unlabeled data never hurt,” IEEE Trans. Pattern Anal. Mach. Intell. 37, 175–188 (2014). https://doi.org/10.1109/TPAMI.2014.2299812
W. Liu, J. He, and S. Chang, “Large graph construction for scalable semisupervised learning,” in ICML’10: Proc. 27th Int. Conf. on Machine Learning, Haifa, Israel, 2010, Ed. by J. Fürnkranz and T. Joachims (Omnipress, Madison, Wis., 2010), pp. 679–686.
T. Ojala, M. Pietikainen, and T. Maenpaa, “Multiresolution gray-scale and rotation invariant texture classification with local binary patterns,” IEEE Trans. Pattern Anal. Mach. Intell. 24, 971–987 (2002). https://doi.org/10.1109/tpami.2002.1017623
U. Patel, H. Dave, and V. Patel, “Hyperspectral image classification using semi-supervised learning with label propagation,” in 2020 IEEE India Geoscience and Remote Sensing Symp. (InGARSS), Ahmedabad, India, 2020 (IEEE, 2020), pp. 205–208. https://doi.org/10.1109/ingarss48198.2020.9358921
S. Peyghambari and Yu. Zhang, “Hyperspectral remote sensing in lithological mapping, mineral exploration, and environmental geology: An updated review,” J. Appl. Remote Sensing 15, 31501 (2021). https://doi.org/10.1117/1.jrs.15.031501
A. Plaza, J. A. Benediktsson, J. W. Boardman, J. Brazile, L. Bruzzone, G. Camps-Valls, J. Chanussot, M. Fauvel, P. Gamba, A. Gualtieri, M. Marconcini, J. C. Tilton, and G. Trianni, “Recent advances in techniques for hyperspectral image processing,” Remote Sensing Environ. 113, S110–S122 (2009). https://doi.org/10.1016/j.rse.2007.07.028
Yi. Qiong and L. Wei, “Geological exploration scheme based on remote sensing image processing technology,” in 2016 Int. Conf. on Smart Grid and Electrical Automation (ICSGEA), Zhangjiajie, China, 2016 (IEEE, 2016), pp. 179–182. https://doi.org/10.1109/icsgea.2016.79
P. Kumar Sethy, C. Pandey, Yo. Kumar Sahu, S. Kumari, and Behera, “Hyperspectral imagery applications for precision agriculture-a systemic survey,” Multimedia Tools Appl. 81, 3005–3038 (2021). https://doi.org/10.1007/s11042-021-11729-8
I. Steinwart, D. Hush, and C. Scovel, “Training SVMs without offset,” J. Mach. Learn. Res. 12, 141–202 (2011).
H. Su, Z. Wu, H. Zhang, and Q. Du, “Hyperspectral anomaly detection: A survey,” IEEE Geosci. Remote Sensing Mag. 10 (1), 64–90 (2021). https://doi.org/10.1109/mgrs.2021.3105440
Yu. Sun, S. Ding, L. Guo, and Z. Zhang, “Hypergraph regularized semi-supervised support vector machine,” Inf. Sci. 591, 400–421 (2022). https://doi.org/10.1016/j.ins.2022.01.038
M. Tanveer, T. Rajani, R. Rastogi, Y. H. Shao, and M. A. Ganaie, “Comprehensive review on twin support vector machines,” Ann. Oper. Res. (2022). https://doi.org/10.1007/s10479-022-04575-w
C. Wang, B. Liu, L. Liu, Ya. Zhu, J. Hou, P. Liu, and X. Li, “A review of deep learning used in the hyperspectral image analysis for agriculture,” Artif. Intell. Rev. 54, 5205–5253 (2021). https://doi.org/10.1007/s10462-021-10018-y
M. Wang, W. Fu, S. Hao, D. Tao, and X. Wu, “Scalable semi-supervised learning by efficient anchor graph regularization,” IEEE Trans. Knowl. Data Eng. 28, 1864–1877 (2016). https://doi.org/10.1109/tkde.2016.2535367
X. Wang and H. Ji, “Semi-supervised hyperspectral image classification based on label propagation via selected path,” IEEE Access 8, 221225–221234 (2020). https://doi.org/10.1109/access.2020.3042885
X. Xie and S. Sun, “General multi-view semi-supervised least squares support vector machines with multi-manifold regularization,” Inf. Fusion 62, 63–72 (2020). https://doi.org/10.1016/j.inffus.2020.04.005
Yu. Xiong, K. Xu, Yo. Dou, Ya. Zhao, and Z. Gao, “WRMatch: Improving FixMatch with weighted nuclear-norm regularization for few-shot remote sensing scene classification,” IEEE Trans. Geosci. Remote Sensing 60, 5612214 (2021). https://doi.org/10.1109/tgrs.2021.3121765
X.-Sh. Yang and Suash Deb, “Cuckoo Search via Lévy flights,” in 2009 World Congress on Nature and Biologically Inspired Computing (NaBIC), Coimbatore, India, 2009 (IEEE, 2009), pp. 210–214. https://doi.org/10.1109/nabic.2009.5393690
X.-Sh. Yang and S. Deb, “Engineering optimisation by cuckoo search,” Int. J. Math. Modell. Numer. Optimisation 1, 330–343 (2010). https://doi.org/10.1504/IJMMNO.2010.03543
J. Yuan, S. Wang, C. Wu, and Yo. Xu, “Fine-grained classification of urban functional zones and landscape pattern analysis using hyperspectral satellite imagery: A case study of Wuhan,” IEEE J. Sel. Top. Appl. Earth Obs. Remote Sensing 15, 3972–3991 (2022). https://doi.org/10.1109/jstars.2022.3174412
J. Yue, L. Fang, H. Rahmani, and P. Ghamisi, “Self-supervised learning with adaptive distillation for hyperspectral image classification,” IEEE Trans. Geosci. Remote Sensing 60, 5501813 (2021). https://doi.org/10.1109/tgrs.2021.3057768
B. Zoph, G. Ghiasi, T. Lin, Yi. Cui, H. Liu, E. D. Cubuk, and Q. Le, “Rethinking pre-training and self-training,” Adv. Neural Inf. Process. Syst. 33, 3833–3845 (2020).
Funding
This research was funded by the National Natural Science Foundation of China (nos. U1813222, 42075129); Hebei Province Natural Science Foundation (no. E2021202179), Key Research and Development Project from Hebei Province (nos. 19210404D, 20351802D, 21351803D).
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
The authors of this work declare that they have no conflicts of interest.
Additional information
Ziping He received a PhD degree from the School of Electronics and Information Engineering at Hebei University of Technology, Tianjin, China in 2023. She is currently a lecturer at School of Computer and Communication Engineering in Changsha University of Science and Technology. From October 2021 to November 2022, she is a visiting PhD student with the machine learning group at Helmholtz–Zentrum and Dresden–Rossendorf (HZDR), Germany, supported by the China Scholarship Council. Her research interests include semi-supervised learning, machine learning, deep learning, and hyperspectral image processing.
Kewen Xia received the PhD degree in Electronics from Xi’an Jiaotong University (XJTU), China in 2003. His postdoctoral research was finished in Computer Department of XJTU in 2006. From 2010 to 2011, he worked as a research scholar of Electronics in University of Illinois at Urbana-Champaign, United States Now he is a professor and PhD candidate supervisor with the School of Electronics and Information Engineering, Hebei University of Technology, China. His research interests cover computational intelligence and wireless communication technology.
Jiangnan Zhang received BEng degree in College of Information Science and Engineering from Shanxi Agricultural University, Shanxi, China in 2017. She is now a Doctoral student in Hebei University of Technology, Tianjin, China. Her research interests are image processing, data mining, and communication technology.
Sijie Wang received BSc degree in school of electronic and information engineering from city collage of Hebei University of Technology, Tianjin, China in 2016. Now she is a doctoral student in Hebei University of Technology, Tianjin, China. Her research interests include image processing and data mining.
Zhixian Yin received his BSc degree in Tangshan University, Tangshan, China in 2012. He received MSc Degree in School of Information Science and Technology from Shijiazhuang Tiedao University, Shijiazhuang, China in 2018. He is now a Doctoral student in Hebei University of Technology, Tianjin, China. His research includes image processing and intelligent information processing.
Publisher’s Note.
Pleiades Publishing remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Ziping He, Xia, K., Zhang, J. et al. An Enhanced Semi-Supervised Support Vector Machine Algorithm for Spectral-Spatial Hyperspectral Image Classification. Pattern Recognit. Image Anal. 34, 199–211 (2024). https://doi.org/10.1134/S1054661824010085
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1054661824010085