A novel hybrid approach for hyperspectral image classification using deep residual networks
DOI:
https://doi.org/10.65746/jbrha136Keywords:
hyperspectral image; classification; deep learning; transfer learning; deep residual network; overall accuracyAbstract
The classification of Hyperspectral images has a lot of improvements through the deep learning approaches. The hybrid deep learning technique (HDL) is proposed in this paper to enhance the classification. The deep residual network is composed of layers with residual blocks that enable the classification of pixels into multiple classes. Transfer learning is used to analyze the basic values in the training state that integrates the classification. The MaxPooling function has non-overlapping windows to produce the output value for every sub-region by reducing the computational complexity to generate the translation invariance. The Convolution operation has the dimensionality reduction while the total operations have the minimized computational cost, the last pooling layer produces the pooling operations to the data as the classifier has the classification procedure. The Experimental results proved that the performance of the proposed technique for Hyperspectral image classification is effectively enhanced using popular datasets of Pavia University dataset, Indian Pines dataset, Salinas scene dataset. Also, the overall accuracy is significantly improved than the related methodologies in various parameters.
References
1. Liu X, Sun Q, Liu B, et al. Hyperspectral image classification based on convolutional neural network and dimension reduction. 2017 Chinese automation congress (CAC). IEEE; 2017. pp. 1686-1690. doi: 10.1109/cac.2017.8243039
2. Jia S, Jiang S, Lin Z, et al. A survey: Deep learning for hyperspectral image classification with few labeled samples. Neurocomputing. 2021; 448: 179–204. doi: 10.1016/j.neucom.2021.03.035
3. Paoletti ME, Haut JM, Plaza J, et al. Deep learning classifiers for hyperspectral imaging: A review. ISPRS Journal of Photogrammetry and Remote Sensing. 2019; 158: 279–317. doi: 10.1016/j.isprsjprs.2019.09.006
4. Lin L, Chen C, Xu T. Spatial-spectral hyperspectral image classification based on information measurement and CNN. EURASIP Journal on Wireless Communications and Networking. 2020; 2020(1): 59. doi: 10.1186/s13638-020-01666-9
5. Yu Y, Ma Y, Mei X, et al. A spatial-spectral feature descriptor for hyperspectral image matching. Remote Sensing. 2021; 13(23): 4912. doi: 10.3390/rs13234912
6. Bidari I, Chickerur S, Ranmale H, et al. Hyperspectral imagery classification using deep learning. 2020 Fourth World Conference on Smart Trends in Systems, Security and Sustainability (WorldS4). IEEE; 2020. pp. 672–676. doi: 10.1109/WorldS450073.2020.9210332
7. Guo Y, Yin X, Zhao X, et al. Hyperspectral image classification with SVM and guided filter. EURASIP Journal on Wireless Communications and Networking. 2019; 2019(1): 56. doi: 10.1186/s13638-019-1346-z
8. Sun L, Zhao G, Zheng Y, et al. Spectral–spatial feature tokenization transformer for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing. 2022; 60: 1–14. doi: 10.1109/TGRS.2022.3144158
9. Dhandhalya JK, Parmar SK. Hyperspectral image classification using spatial spectral features and machine learning approach. 2016 IEEE International Conference on Recent Trends in Electronics, Information & Communication Technology (RTEICT). IEEE; 2016. pp. 1161–1165. doi: 10.1109/rteict.2016.7808014
10. Kong Y, Wang X, Cheng Y. Spectral–spatial feature extraction for HSI classification based on supervised hypergraph and sample expanded CNN. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2018; 11(11): 4128–4140. doi: 10.1109/JSTARS.2018.2869210
11. Luo Y, Zou J, Yao C, et al. HSI-CNN: A novel convolution neural network for hyperspectral image. 2018 International Conference on Audio, Language and Image Processing (ICALIP). IEEE; 2018. pp. 464–469. doi: 10.1109/ICALIP.2018.8455251
12. Li Z, Huang H, Zhang Z, et al. Manifold-based multi-deep belief network for feature extraction of hyperspectral image. Remote Sensing. 2022; 14(6): 1484. doi: 10.3390/rs14061484
13. Liu W, You J, Lee J. Hsigan: A conditional hyperspectral image synthesis method with auxiliary classifier. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing. 2021; 14: 3330–3344. doi: 10.1109/JSTARS.2021.3063911
14. Feng J, Bai G, Gao Z, et al. Automatic design recurrent neural network for hyperspectral image classification. 2021 IEEE International Geoscience and Remote Sensing Symposium IGARSS. IEEE; 2021. pp. 2234–2237. doi: 10.1109/IGARSS47720.2021.9554089
15. Zhang X, Guo Y, Zhang X. Hyperspectral image classification based on optimized convolutional neural networks with 3D stacked blocks. Earth Science Informatics. 2022; 15(1): 383–395. doi: 10.1007/s12145-021-00731-1
16. Wang ZY, Xia QM, Yan JW, et al. Hyperspectral image classification based on spectral and spatial information using multi-scale ResNet. Applied Sciences. 2019; 9(22): 4890. doi: 10.3390/app9224890
17. Fabiyi SD, Vu H, Tachtatzis C, et al. Comparative study of PCA and LDA for rice seeds quality inspection. 2019 IEEE AFRICON. IEEE; 2019. pp. 1–4. doi: 10.1109/AFRICON46755.2019.9134059
18. Sun Q, Liu X, Fu M. Classification of hyperspectral image based on principal component analysis and deep learning. 2017 7th IEEE international conference on electronics information and emergency communication (ICEIEC). IEEE; 2017. pp. 356–359. doi: 10.1109/iceiec.2017.8076581
19. Geng F, Shi Z, Jiang Z, et al. Independent innovation analysis for hyperspectral imagery unmixing. 2008 Fourth International Conference on Natural Computation. IEEE. 2008; 3: 226–230. doi: 10.1109/ICNC.2008.652
20. Venkatesan R, Prabu S. Hyperspectral image features classification using deep learning recurrent neural networks. Journal of Medical Systems. 2019; 43(7): 216. doi: 10.1007/s10916-019-1347-9
21. Leng J, Li T, Bai G, et al. Cube-CNN-SVM: A novel hyperspectral image classification method. 2016 IEEE 28th International conference on tools with artificial intelligence (ICTAI). IEEE; 2016. pp. 1027–1034. doi: 10.1109/ICTAI.2016.0158
22. Li Y, Zhang H, Shen Q. Spectral–spatial classification of hyperspectral imagery with 3D convolutional neural network. Remote Sensing, 2017; 9(1): 67. doi: 10.3390/rs9010067
23. Zhu L, Chen Y, Ghamisi P, et al. Generative adversarial networks for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing. 2018; 56(9): 5046–5063. doi: 10.1109/TGRS.2018.2805286
24. Song W, Li S, Fang L, et al. Hyperspectral image classification with deep feature fusion network. IEEE Transactions on Geoscience and Remote Sensing. 2018; 56(6): 3173–3184. doi: 10.1109/TGRS.2018.2794326
25. Zhong Z, Li J, Luo Z, et al. Spectral–spatial residual network for hyperspectral image classification: A 3-D deep learning framework. IEEE Transactions on Geoscience and Remote Sensing. 2017; 56(2): 847–858. doi: 10.1109/TGRS.2017.2755542
26. Kakarla S. A hyperspectral image data for geo-spatial analysis. Pavia University. 2021. Available online: https://www.kaggle.com/datasets/syamkakarla/pavia-university-hsi (accessed on 5 May 2026).
27. Gokar A. Indian Pines Hyperspectral Dataset. Kaggle; 2018. Available online: https://www.kaggle.com/datasets/abhijeetgo/indian-pines-hyperspectral-dataset (accessed on 05 may 2026).
28. Wang S. Hyperspectral dataset. IEEE Dataport; 2020. doi: 10.21227/eqk7-wa46
29. Yang H, Yu H, Zheng K, et al. Hyperspectral image classification based on interactive transformer and CNN with multilevel feature fusion network. IEEE Geoscience and Remote Sensing Letters. 2023; 20: 1–5. doi: 10.1109/LGRS.2023.3303008
30. Hameed AA. Enhancing hyperspectral remote sensing image classification using robust learning technique. Journal of King Saud University-Science. 2024; 36(1): 102981. doi: 10.1016/j.jksus.2023.102981
31. Ranjan P, Girdhar A. A comprehensive systematic review of deep learning methods for hyperspectral images classification. International Journal of Remote Sensing. 2022; 43(17): 6221–6306. doi: 10.1080/01431161.2022.2133579
32. Ranjan P, Girdhar A. Deep siamese network with handcrafted feature extraction for hyperspectral image classification. Multimedia Tools and Applications. 2024; 83(1): 2501-2526. doi: 10.1007/s11042-023-15444-4
33. Ranjan P, Girdhar A. Xcep-Dense: A novel lightweight extreme inception model for hyperspectral image classification. International Journal of Remote Sensing. 2022; 43(14): 5204–5230. doi: 10.1080/01431161.2022.2130727
34. Ranjan P, Gupta G. A cross-domain semi-supervised zero-shot learning model for the classification of hyperspectral images. Journal of the Indian Society of Remote Sensing. 2023; 51(10): 1991–2005. doi: 10.1007/s12524-023-01734-9
35. Ranjan P, Kumar R, Girdhar A. Unlocking the potential of unlabeled data: Semi-supervised learning for stratification of hyperspectral image. 2023 OITS International Conference on Information Technology (OCIT). IEEE; 2023. pp. 938–943. doi: 10.1109/OCIT59427.2023.10430513
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Jafny Benshia Benjamin, Harold Robinson Yesudhas
This work is licensed under a Creative Commons Attribution 4.0 International License.
