International Journal of Wireless and Microwave Technologies (IJWMT)
IJWMT Vol. 16, No. 5, 8 Oct. 2026
Cover page and Table of Contents: PDF (size: 1454KB)
SpectroRes-Former: A Spectral–Spatial Residual Transformer with Quantum–Fisher Feature Selection for Hyperspectral Land-Cover Classification
PDF (1454KB), PP.191-218
Views: 0 Downloads: 0
Author(s)
Index Terms
Hyperspectral Image Classification, Indian Pines Dataset, SpectroRes-Former, Quantum–Fisher Feature Selection (QuFiSel), Spectral–Spatial Attention, Transformer Network
Abstract
Proper land-cover and deforestation classification is crucial in environmental protection, sustainable land use, and climate change. Nevertheless, the current deep learning and remote sensing models are usually limited by poor spectral-spatial feature integration, high computational complexity, and poor feature selection, which reduces the classification accuracy. To address these limitations, this paper presents a new model that combines SpectroRes-Former, a SpectralSpatial Residual Transformer Network, and QuFiSel (QuantumFisher Selection), a hybrid feature selection method. The SpectroRes-Former effectively learns both spatial and spectral dependencies with a ResNet encoder, spectral-spatial attention fusion, and Transformer-based contextual learning. At the same time, QuFiSel improves the discrimination of features by integrating Quantum-Inspired Feature Selection (QIFS) and Fisher Score, so that the most informative features are selected to classify. The effectiveness of the approach is tested based on the Indian Pines hyperspectral image, which consists of 220 bands after typical band selection and 16 land cover types. The performance is measured through 5-fold cross-validation and the statistical validation through mean, standard deviation, and paired tests. The obtained average classification accuracy of the proposed method equals 99.21 ± 0.08%, along with the Precision value of 99.08%, Recall 99.16%, F1-score 99.12%, and Matthews Correlation Coefficient 0.991, demonstrating superior results compared to some of the most competitive state-of-the-art techniques. The paired t-test gives p < 0.05, which confirms the statistical significance of the result. It is shown that the introduced SpectroRes-Former framework can be used effectively for hyperspectral land cover classification while providing high generalization. The offered solution can serve as a reliable base for smart environmental monitoring systems.
Cite This Paper
M. H. Vahitha Rahman, M. Vanitha, "SpectroRes-Former: A Spectral–Spatial Residual Transformer with Quantum–Fisher Feature Selection for Hyperspectral Land-Cover Classification", International Journal of Wireless and Microwave Technologies(IJWMT), Vol.16, No.5, pp. 191-218, 2026. DOI:10.5815/ijwmt.2026.05.12
Reference
[1]Yousefi, S., Mirzaee, S., Almohamad, H., Al Dughairi, A. A., Gomez, C., Siamian, N., ... & Abdo, H. G. (2022). Image classification and land cover mapping using Sentinel-2 imagery: Optimization of SVM parameters. Land, 11(7), 993. DOI: https://doi.org/10.3390/land11070993
[2]Sobala, M. (2024). Reconstructing of historical land cover based on contemporary cartographical materials. Journal of Historical Geography, 84, 14–26. DOI: https://doi.org/10.1016/j.jhg.2024.03.011
[3]Long, Y., Jiang, F., Deng, M., Wang, T., & Sun, H. (2023). Spatial-temporal changes and driving factors of eco-environmental quality in the Three-North region of China. Journal of Arid Land, 15(3), 231–252. DOI: https://doi.org/10.1007/s40333-023-0053-0
[4]Chen, S., Woodcock, C. E., Bullock, E. L., Arévalo, P., Torchinava, P., Peng, S., & Olofsson, P. (2021). Monitoring temperate forest degradation on Google Earth Engine using Landsat time series analysis. Remote Sensing of Environment, 265, 112648. DOI: https://doi.org/10.1016/j.rse.2021.112648
[5]Jayanthi, J., & Kumar, K. A. (2024). AI-Driven Restoration: Enhancing Biodiversity Conservation and Ecosystem Resilience. In Explainable AI (XAI) for Sustainable Development (pp. 180–193). Chapman and Hall/CRC. DOI: https://doi.org/10.1201/9781003457176-11
[6]Bhagarathi, L. K., DaSilva, P. N., Maharaj, G., Balkarran, R., Baksh, A., Kalika-Singh, S., ... & Cossiah, C. (2024). The impact of climate change on the reproductive biology and population dynamics of fishes: Implications for fisheries and food security. International Journal of Biological and Pharmaceutical Sciences Archive, 8, 13–34.
[7]Shen, Y., Zhang, F., Liu, D., Pu, W., & Zhang, Q. (2022). Manhattan-distance IOU loss for fast and accurate bounding box regression and object detection. Neurocomputing, 500, 99–114. DOI: https://doi.org/10.1016/j.neucom.2022.05.052
[8]Lv, Z., Wang, F., Cui, G., Benediktsson, J. A., Lei, T., & Sun, W. (2022). Spatial–spectral attention network guided with change magnitude image for land cover change detection using remote sensing images. IEEE Transactions on Geoscience and Remote Sensing, 60, 1–12. DOI: https://doi.org/10.1109/TGRS.2022.3197901
[9]Hong, D., Han, Z., Yao, J., Gao, L., Zhang, B., Plaza, A., & Chanussot, J. (2022). SpectralFormer: Rethinking hyperspectral image classification with transformers. IEEE Transactions on Geoscience and Remote Sensing, 60, 1–15. DOI: https://doi.org/10.1109/TGRS.2021.3130716
[10]Zhang, H., Zang, N., Cao, Y., Wang, Y., Zhang, L., Huang, B., & Mathiopoulos, P. T. (2022). DGCC-EB: Deep global context construction with an enabled boundary for land use mapping of CSMA. IEEE Transactions on Geoscience and Remote Sensing, 60, 1–15. DOI: https://doi.org/10.1109/TGRS.2022.3224733
[11]Yang, G., Yu, W., Yao, X., Zheng, H., Cao, Q., Zhu, Y., ... & Cheng, T. (2021). AGTOC: A novel approach to winter wheat mapping by automatic generation of training samples and one-class classification on Google Earth Engine. International Journal of Applied Earth Observation and Geoinformation, 102, 102446. DOI: https://doi.org/10.1016/j.jag.2021.102446
[12]Zhang, X., Shang, S., Tang, X., Feng, J., & Jiao, L. (2022). Spectral partitioning residual network with spatial attention mechanism for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 60, 1–14. DOI: https://doi.org/10.1109/TGRS.2021.3074196
[13]Zhang, H., Liu, H., Yang, R., Wang, W., Luo, Q., & Tu, C. (2024). Hyperspectral image classification based on double-branch multi-scale dual-attention network. Remote Sensing, 16(12), 2051. DOI: https://doi.org/10.3390/rs16122051
[14]Du, Z., Liu, S., Liao, Y., Tang, Y., Liu, Y., Xing, H., ... & Zhang, D. (2025). UniHSFormer X for hyperspectral crop classification with prototype-routed semantic structuring. Agriculture, 15(13), 1427. DOI: https://doi.org/10.3390/agriculture15131427
[15]Li, Y., Zhou, Y., Zhang, Y., Zhong, L., Wang, J., & Chen, J. (2022). DKDFN: Domain knowledge-guided deep collaborative fusion network for multimodal unitemporal remote sensing land cover classification. ISPRS Journal of Photogrammetry and Remote Sensing, 186, 170–189. DOI: https://doi.org/10.1016/j.isprsjprs.2022.02.013
[16]Zhang, J., Meng, Z., Zhao, F., Liu, H., & Chang, Z. (2022). Convolution transformer mixer for hyperspectral image classification. IEEE Geoscience and Remote Sensing Letters, 19, 1–5. DOI: https://doi.org/10.1109/LGRS.2022.3208935
[17]Yu, H., Xu, Z., Zheng, K., Hong, D., Yang, H., & Song, M. (2022). MSTNet: A multilevel spectral–spatial transformer network for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 60, 1–13. DOI: https://doi.org/10.1109/TGRS.2022.3186400
[18]Dutta, T., Bhattacharyya, S., Panigrahi, B. K., Zelinka, I., & Mrsic, L. (2023). Multi-level quantum inspired metaheuristics for automatic clustering of hyperspectral images. Quantum Machine Intelligence, 5(1), 22. DOI: https://doi.org/10.1007/s42484-023-00110-7
[19]Fei, X., Wu, S., Miao, J., Wang, G., & Sun, L. (2024). Lightweight-VGG: A fast deep learning architecture based on dimensionality reduction and nonlinear enhancement for hyperspectral image classification. Remote Sensing, 16(2), 259. DOI: https://doi.org/10.3390/rs16020259
[20]Feng, Y., Zhu, J., Song, R., & Wang, X. (2024). S2EFT: Spectral-spatial-elevation fusion transformer for hyperspectral image and LiDAR classification. Knowledge-Based Systems, 283, 111190. DOI: https://doi.org/10.1016/j.knosys.2023.111190
[21]Xue, F., Tan, F., Ye, Z., Chen, J., & Wei, Y. (2022). Spectral-spatial classification of hyperspectral image using improved functional principal component analysis. IEEE Geoscience and Remote Sensing Letters, 19, 1–5. DOI: https://doi.org/10.1109/LGRS.2021.3089278
[22]Wan, X., Chen, F., Liu, W., & He, Y. (2024). Artificial gorilla troops optimizer enfolded broad learning system for spatial-spectral hyperspectral image classification. Infrared Physics & Technology, 138, 105220. DOI: https://doi.org/10.1016/j.infrared.2024.105220
[23]Hafeez, M. A., Munir, A., & Ullah, H. (2024). H-QNN: A hybrid quantum–classical neural network for improved binary image classification. AI, 5(3), 1462–1481. DOI: https://doi.org/10.3390/ai5030070
[24]Chen, N., Yue, J., Fang, L., & Xia, S. (2023). SpectralDiff: A generative framework for hyperspectral image classification with diffusion models. IEEE Transactions on Geoscience and Remote Sensing, 61, 1–16. DOI: https://doi.org/10.1109/TGRS.2023.3310023
[25]Song, R., Feng, Y., Cheng, W., Mu, Z., & Wang, X. (2022). BS2T: Bottleneck spatial–spectral transformer for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 60, 1–17. DOI: https://doi.org/10.1109/TGRS.2022.3185640