ICCK Journal of Image Analysis and Processing Home About Editors Current Issue
RETRACTED: Adaptive Hyperspectral Direct Classification Method Based on Computational Spectral Imaging
Research Article  ·  Published: 07 May 2026
Issue cover
ICCK Journal of Image Analysis and Processing
Volume 2, Issue 2, 2026: 92-103
Research Article Open Access

RETRACTED: Adaptive Hyperspectral Direct Classification Method Based on Computational Spectral Imaging

by
Dingguo Wang Dingguo Wang 1 * ORCID
Yudi Chen Yudi Chen 1
1 School of Optoelectronic Engineering, Xi'an Technological University, Xi'an 710021, China
* Corresponding Author: Dingguo Wang, [email protected]
Volume 2, Issue 2
Volume 2, Issue 2 2026
Received: 13 April 2026 Accepted: 01 May 2026 Published: 07 May 2026 CrossMark
Download PDF 1.41 MB Cite Metrics
DOI: 10.62762/JIAP.2026.481080
ARK: ark:/57805/jiap.2026.481080
  This article was retracted on  28 May 2026.
Retraction Notice to "Adaptive Hyperspectral Direct Classification Method Based on Computational Spectral Imaging"

Article Information

Published in ICCK Journal of Image Analysis and Processing
Volume/Issue Volume 2, Issue 2, 2026
Pages 92-103

Abstract

Hyperspectral image classification is a central task in remote sensing information extraction. Conventional approaches follow a reconstruct-then-classify paradigm, which entails large data volumes, high computational cost, and poor real-time performance. This paper presents an adaptive hyperspectral direct classification method based on computational spectral imaging. A Digital Micromirror Device (DMD) is used to spectrally encode and modulate the incident light, enabling direct output of two-dimensional spatial classification results without reconstructing the three-dimensional spectral data cube. First, a classification-oriented encoding template is designed via Fisher discriminant analysis to maximize inter-class separability. Second, classification decisions are made in the measurement space using Bayesian posterior probabilities, where the class-conditional probability is modeled as a multivariate Gaussian distribution and the maximum a posteriori (MAP) criterion is adopted. Third, an adaptive encoding template optimization mechanism driven by posterior probability weighting is introduced, which progressively improves classification accuracy through iterative feedback. Experiments on the Indian Pines and Pavia University datasets demonstrate that the proposed method achieves overall accuracies of 66.97% and 72.96%, respectively, using only 15-dimensional measurements (8.4% and 14.6% of the original spectral dimensions), with several individual class accuracies exceeding those of the standard Support Vector Machine (SVM) method, thereby confirming the feasibility and generalizability of the classify without reconstruction paradigm.

Graphical Abstract

RETRACTED: Adaptive Hyperspectral Direct Classification Method Based on Computational Spectral Imaging

Keywords

computational spectral imaging hyperspectral classification digital micromirror device Fisher discriminant analysis adaptive encoding template posterior probability

Data Availability Statement

Data will be made available on request.

Funding

This work was supported without any funding.

Conflicts of Interest

The authors declare no conflicts of interest.

AI Use Statement

The authors declare that no generative AI was used in the preparation of this manuscript.

Ethical Approval and Consent to Participate

Not applicable.

References

  1. Bioucas-Dias, J. M., Plaza, A., Dobigeon, N., Parente, M., Du, Q., Gader, P., & Chanussot, J. (2012). Hyperspectral unmixing overview: Geometrical, statistical, and sparse regression-based approaches. IEEE journal of selected topics in applied earth observations and remote sensing, 5(2), 354-379.
    [CrossRef] [Google Scholar]
  2. Melgani, F., & Bruzzone, L. (2004). Classification of hyperspectral remote sensing images with support vector machines. IEEE Transactions on geoscience and remote sensing, 42(8), 1778-1790.
    [CrossRef] [Google Scholar]
  3. Yuan, X., Brady, D. J., & Katsaggelos, A. K. (2021). Snapshot compressive imaging: Theory, algorithms, and applications. IEEE Signal Processing Magazine, 38(2), 65-88.
    [CrossRef] [Google Scholar]
  4. Hagen, N., & Kudenov, M. W. (2013). Review of snapshot spectral imaging technologies. Optical Engineering, 52(9), 090901-090901.
    [CrossRef] [Google Scholar]
  5. Arce, G. R., Brady, D. J., Carin, L., Arguello, H., & Kittle, D. S. (2013). Compressive coded aperture spectral imaging: An introduction. IEEE Signal Processing Magazine, 31(1), 105-115.
    [CrossRef] [Google Scholar]
  6. Candès, E. J., & Wakin, M. B. (2008). An introduction to compressive sampling. IEEE signal processing magazine, 25(2), 21-30.
    [CrossRef] [Google Scholar]
  7. Wagadarikar, A., John, R., Willett, R., & Brady, D. (2008). Single disperser design for coded aperture snapshot spectral imaging. Applied optics, 47(10), B44-B51.
    [CrossRef] [Google Scholar]
  8. Zhang, X., Chen, B., Zou, W., Liu, S., Zhang, Y., Xiong, R., & Zhang, J. (2024). Progressive content-aware coded hyperspectral snapshot compressive imaging. IEEE Transactions on Circuits and Systems for Video Technology, 34(11), 10817-10830.
    [CrossRef] [Google Scholar]
  9. Wu, Z., Lu, R., Fu, Y., & Yuan, X. (2024, September). Latent diffusion prior enhanced deep unfolding for snapshot spectral compressive imaging. In European Conference on Computer Vision (pp. 164-181). Cham: Springer Nature Switzerland.
    [CrossRef] [Google Scholar]
  10. Si, Y., Lin, Z., Wang, X., & He, S. (2025). A new hyperspectral reconstruction method with conditional diffusion model for snapshot spectral compressive imaging. IEEE Transactions on Instrumentation and Measurement, 74, 1–14.
    [CrossRef] [Google Scholar]
  11. Cao, X., Yue, T., Lin, X., Lin, S., Yuan, X., Dai, Q., ... & Brady, D. J. (2016). Computational snapshot multispectral cameras: Toward dynamic capture of the spectral world. IEEE Signal Processing Magazine, 33(5), 95-108.
    [CrossRef] [Google Scholar]
  12. Kaarna, A., Toivanen, P., & Keränen, P. (2006). Compression and classification methods for hyperspectral images. Pattern Recognition and Image Analysis, 16(3), 413-424.
    [CrossRef] [Google Scholar]
  13. Zhang, H., Ma, X., Zhao, X., & Arce, G. R. (2021). Compressive hyperspectral image classification using a 3D coded convolutional neural network. Optics Express, 29(21), 32875-32891.
    [CrossRef] [Google Scholar]
  14. Bacca, J., Galvis, L., & Arguello, H. (2020). Coupled deep learning coded aperture design for compressive image classification. Optics express, 28(6), 8528-8540.
    [CrossRef] [Google Scholar]
  15. Yang, Q., Wang, X., Wang, D., Yu, B., Zhou, Y., & Qiao, S. (2024). Compressive hyperspectral target detection with restricted distribution property. IEEE Transactions on Geoscience and Remote Sensing, 62, 1-15.
    [CrossRef] [Google Scholar]
  16. Yang, Q., Wang, X., Chen, L., Zhou, Y., & Qiao, S. (2024). CS-TTD: Triplet transformer for compressive hyperspectral target detection. IEEE Transactions on Geoscience and Remote Sensing, 62, 1-15.
    [CrossRef] [Google Scholar]
  17. Chen, Y., Jiang, H., Li, C., Jia, X., & Ghamisi, P. (2016). Deep feature extraction and classification of hyperspectral images based on convolutional neural networks. IEEE transactions on geoscience and remote sensing, 54(10), 6232-6251.
    [CrossRef] [Google Scholar]
  18. Hong, D., Han, Z., Yao, J., Gao, L., Zhang, B., Plaza, A., & Chanussot, J. (2021). SpectralFormer: Rethinking hyperspectral image classification with transformers. IEEE Transactions on Geoscience and Remote Sensing, 60, 1-15.
    [CrossRef] [Google Scholar]
  19. Zhao, X., Ma, J., Wang, L., Zhang, Z., Ding, Y., & Xiao, X. (2025). A review of hyperspectral image classification based on graph neural networks. Artificial Intelligence Review, 58(6), 172.
    [CrossRef] [Google Scholar]
  20. Meng, Z., Yan, Q., Zhao, F., Chen, G., Hua, W., & Liang, M. (2024). Global–Local multigranularity transformer for hyperspectral image classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 18, 112-131.
    [CrossRef] [Google Scholar]
  21. Wan, X., Chen, F., Gao, W., He, Y., Liu, H., & Li, Z. (2024). Efficient spectral-spatial fusion with multiscale and adaptive attention for hyperspectral image classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 18, 1196-1211.
    [CrossRef] [Google Scholar]
  22. Zhang, Z., Jiang, L., Tang, B. H., Liu, J., Wang, Q., Hu, Y., ... & Fu, Z. (2025). Attention residual hybrid network for unmanned aerial vehicles hyperspectral image classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.
    [CrossRef] [Google Scholar]
  23. CAI, Y., TAN, M., PAN, J., & HE, K. (2024). Hyperspectral image classification based on multi-scale asymmetric dense network. Journal of Electronics & Information Technology, 46(4), 1448–1457. http://dx.doi.org/10.11999/JEIT230651
    [Google Scholar]
  24. Sun, J., Zhang, H., Wang, J., Sima, H., & Jin, S. (2025). Hyperspectral Image Classification With Re-Attention Agent Transformer and Multiscale Partial Convolution. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.
    [CrossRef] [Google Scholar]
  25. Correa, C. V., Arguello, H., & Arce, G. R. (2016). Spatiotemporal blue noise coded aperture design for multi-shot compressive spectral imaging. Journal of the Optical Society of America A, 33(12), 2312-2322.
    [CrossRef] [Google Scholar]
  26. Rueda-Chacon, H., Florez-Ospina, J. F., Lau, D. L., & Arce, G. R. (2019). Snapshot compressive tof+ spectral imaging via optimized color-coded apertures. IEEE transactions on pattern analysis and machine intelligence, 42(10), 2346-2360.
    [CrossRef] [Google Scholar]
  27. Bacca, J., Gelvez-Barrera, T., & Arguello, H. (2021). Deep Coded Aperture Design: An End-to-End Approach for Computational Imaging Tasks. IEEE Transactions on Computational Imaging, 7, 1148-1160.
    [CrossRef] [Google Scholar]
  28. Arguello, H., Bacca, J., Kariyawasam, H., Vargas, E., Marquez, M., Hettiarachchi, R., ... & Edussooriya, C. U. (2022). Deep optical coding design in computational imaging. arXiv preprint arXiv:2207.00164.
    [CrossRef] [Google Scholar]
  29. Li, W., Prasad, S., & Fowler, J. E. (2013). Hyperspectral image classification using Gaussian mixture models and Markov random fields. IEEE Geoscience and Remote Sensing Letters, 11(1), 153-157.
    [CrossRef] [Google Scholar]
  30. He, X., Chen, Y., & Huang, L. (2023). Bayesian deep learning for hyperspectral image classification with low uncertainty. IEEE Transactions on Geoscience and Remote Sensing, 61, 1-16.
    [CrossRef] [Google Scholar]
  31. Tarabalka, Y., Benediktsson, J. A., & Chanussot, J. (2009). Spectral–spatial classification of hyperspectral imagery based on partitional clustering techniques. IEEE transactions on geoscience and remote sensing, 47(8), 2973-2987.
    [CrossRef] [Google Scholar]
  32. Gehm, M. E., John, R., Brady, D. J., Willett, R. M., & Schulz, T. J. (2007). Single-shot compressive spectral imaging with a dual-disperser architecture. Optics express, 15(21), 14013-14027.
    [CrossRef] [Google Scholar]
  33. Lee, J., Son, D., Kim, H., Lee, S., Roh, J., & Yoon, J. (2025). Development of a digital micromirror device-based hyperspectral imaging system with dynamically adjustable measurement regions. Scientific Reports, 15(1), 26587.
    [CrossRef] [Google Scholar]
  34. Kittle, D., Choi, K., Wagadarikar, A., & Brady, D. J. (2010). Multiframe image estimation for coded aperture snapshot spectral imagers. Applied optics, 49(36), 6824-6833.
    [CrossRef] [Google Scholar]
  35. Dunlop-Gray, M., Poon, P. K., Golish, D., Vera, E., & Gehm, M. E. (2016). Experimental demonstration of an adaptive architecture for direct spectral imaging classification. Optics express, 24(16), 18307-18321.
    [CrossRef] [Google Scholar]
  36. Bacca, J., Martinez, E., & Arguello, H. (2023). Computational spectral imaging: a contemporary overview. Journal of the Optical Society of America A, 40(4), C115-C125.
    [CrossRef] [Google Scholar]
  37. Sun, L., Zhao, G., Zheng, Y., & Wu, Z. (2022). Spectral–spatial feature tokenization transformer for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 60, 1-14.
    [CrossRef] [Google Scholar]
  38. Li, Y., Fu, X., Liu, J., & Ma, W. K. (2024). Hyperspectral Unmixing Under Endmember Variability: A Variational Inference Framework. arXiv preprint arXiv:2407.14899.
    [CrossRef] [Google Scholar]
  39. Mejia, Y., & Arguello, H. (2018). Binary codification design for compressive imaging by uniform sensing. IEEE Transactions on Image Processing, 27(12), 5775-5786.
    [CrossRef] [Google Scholar]
  40. Fang, L., Li, S., Duan, W., Ren, J., & Benediktsson, J. A. (2015). Classification of hyperspectral images by exploiting spectral–spatial information of superpixel via multiple kernels. IEEE transactions on geoscience and remote sensing, 53(12), 6663-6674.
    [CrossRef] [Google Scholar]
  41. Hong, D., Gao, L., Yokoya, N., Yao, J., Chanussot, J., Du, Q., & Zhang, B. (2020). More diverse means better: Multimodal deep learning meets remote-sensing imagery classification. IEEE Transactions on Geoscience and Remote Sensing, 59(5), 4340-4354.
    [CrossRef] [Google Scholar]
  42. He, X., Chen, Y., & Lin, Z. (2021). Spatial-spectral transformer for hyperspectral image classification. Remote Sensing, 13(3), 498.
    [CrossRef] [Google Scholar]

Cite This Article

APA Style
Wang, D., & Chen, Y. (2026). Adaptive Hyperspectral Direct Classification Method Based on Computational Spectral Imaging. ICCK Journal of Image Analysis and Processing, 2(2), 92-103. https://doi.org/10.62762/JIAP.2026.481080
Export Citation
RIS Format
Compatible with EndNote, Zotero, Mendeley, and other reference managers
TY  - JOUR
AU  - Wang, Dingguo
AU  - Chen, Yudi
PY  - 2026
DA  - 2026/05/07
TI  - RETRACTED: Adaptive Hyperspectral Direct Classification Method Based on Computational Spectral Imaging
JO  - ICCK Journal of Image Analysis and Processing
T2  - ICCK Journal of Image Analysis and Processing
JF  - ICCK Journal of Image Analysis and Processing
VL  - 2
IS  - 2
SP  - 92
EP  - 103
DO  - 10.62762/JIAP.2026.481080
UR  - https://www.icck.org/article/abs/JIAP.2026.481080
KW  - computational spectral imaging
KW  - hyperspectral classification
KW  - digital micromirror device
KW  - Fisher discriminant analysis
KW  - adaptive encoding template
KW  - posterior probability
AB  - Hyperspectral image classification is a central task in remote sensing information extraction. Conventional approaches follow a reconstruct-then-classify paradigm, which entails large data volumes, high computational cost, and poor real-time performance. This paper presents an adaptive hyperspectral direct classification method based on computational spectral imaging. A Digital Micromirror Device (DMD) is used to spectrally encode and modulate the incident light, enabling direct output of two-dimensional spatial classification results without reconstructing the three-dimensional spectral data cube. First, a classification-oriented encoding template is designed via Fisher discriminant analysis to maximize inter-class separability. Second, classification decisions are made in the measurement space using Bayesian posterior probabilities, where the class-conditional probability is modeled as a multivariate Gaussian distribution and the maximum a posteriori (MAP) criterion is adopted. Third, an adaptive encoding template optimization mechanism driven by posterior probability weighting is introduced, which progressively improves classification accuracy through iterative feedback. Experiments on the Indian Pines and Pavia University datasets demonstrate that the proposed method achieves overall accuracies of 66.97% and 72.96%, respectively, using only 15-dimensional measurements (8.4% and 14.6% of the original spectral dimensions), with several individual class accuracies exceeding those of the standard Support Vector Machine (SVM) method, thereby confirming the feasibility and generalizability of the classify without reconstruction paradigm.
SN  - 3068-6679
PB  - Institute of Central Computation and Knowledge
LA  - English
ER  -
BibTeX Format
Compatible with LaTeX, BibTeX, and other reference managers
@article{Wang2026RETRACTED,
  author = {Dingguo Wang and Yudi Chen},
  title = {RETRACTED: Adaptive Hyperspectral Direct Classification Method Based on Computational Spectral Imaging},
  journal = {ICCK Journal of Image Analysis and Processing},
  year = {2026},
  volume = {2},
  number = {2},
  pages = {92-103},
  doi = {10.62762/JIAP.2026.481080},
  url = {https://www.icck.org/article/abs/JIAP.2026.481080},
  abstract = {Hyperspectral image classification is a central task in remote sensing information extraction. Conventional approaches follow a reconstruct-then-classify paradigm, which entails large data volumes, high computational cost, and poor real-time performance. This paper presents an adaptive hyperspectral direct classification method based on computational spectral imaging. A Digital Micromirror Device (DMD) is used to spectrally encode and modulate the incident light, enabling direct output of two-dimensional spatial classification results without reconstructing the three-dimensional spectral data cube. First, a classification-oriented encoding template is designed via Fisher discriminant analysis to maximize inter-class separability. Second, classification decisions are made in the measurement space using Bayesian posterior probabilities, where the class-conditional probability is modeled as a multivariate Gaussian distribution and the maximum a posteriori (MAP) criterion is adopted. Third, an adaptive encoding template optimization mechanism driven by posterior probability weighting is introduced, which progressively improves classification accuracy through iterative feedback. Experiments on the Indian Pines and Pavia University datasets demonstrate that the proposed method achieves overall accuracies of 66.97\% and 72.96\%, respectively, using only 15-dimensional measurements (8.4\% and 14.6\% of the original spectral dimensions), with several individual class accuracies exceeding those of the standard Support Vector Machine (SVM) method, thereby confirming the feasibility and generalizability of the classify without reconstruction paradigm.},
  keywords = {computational spectral imaging, hyperspectral classification, digital micromirror device, Fisher discriminant analysis, adaptive encoding template, posterior probability},
  issn = {3068-6679},
  publisher = {Institute of Central Computation and Knowledge}
}

Article Metrics

Citations
Crossref
0
Scopus
0
Views
1030
PDF Downloads
241

Publisher's Note

ICCK stays neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and Permissions

CC BY Copyright © 2026 by the Author(s). Published by Institute of Central Computation and Knowledge. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/), which permits use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if changes were made.
ICCK Journal of Image Analysis and Processing
ICCK Journal of Image Analysis and Processing
ISSN: 3068-6679 (Online)
Portico
Preserved at
Portico

Article QR Code

Article QR Code
Scan to read this article
Submit Manuscript Edit a Special Issue

Popular Articles

Share This Article