FHIC: Fast Hyperspectral Image Classification Model Using ETR Dimensionality Reduction and ELU Activation Function
DOI:
https://doi.org/10.1109/TGRS.2023.3314619الكلمات المفتاحية:
Feature extraction ، Brain modeling ، Adaptation models ، Hyperspectral imaging ، Data models ، Atmospheric modeling ، Trainingالملخص
Hyperspectral images (HSIs) are typically utilized in a wide variety of practical applications. HSI is replete with spatial and spectral information, which provides precise data for material detection. HSIs are characterized by a high degree of variations and undesirable pixel distributions, providing major processing challenges. This article introduces the fast hyperspectral image classification (FHIC) model, a rapid model for classifying HSIs and resolving their associated challenges. It uses the enhancing transformation reduction (ETR) method to address the HSI difficulties and enhance classes’ differentiation. It also uses exponential linear units (ELUs) to smooth and speed the classification processing. The structure of the FHIC model is designed to be very flexible and suitable for a range of HSIs. The model reduced execution time and RAM consumption, and provided superior performance compared to seven of the most advanced analysis models for three well-known HSIs. In some cases, it was 60% faster than other models. In addition, this work presents a new and highly effective method for measuring the performance of the compared models in terms of their accuracy and processing speed to provide an easy evaluation method. The code of the FHIC model is available at this link: https://github.com/DalalAL-Alimi/FHIC.المراجع
1.M. Vidal and J. M. Amigo, “Pre-processing of hyperspectral images. Essential steps before image analysis,” Chemometric Intell. Lab. Syst., vol. 117, pp. 138–148, Aug. 2012, doi: 10.1016/j.chemolab.2012.05.009.
2.M. E. Paoletti, J. M. Haut, J. Plaza, and A. Plaza, “Deep learning classifiers for hyperspectral imaging: A review,” ISPRS J. Photogramm. Remote Sens., vol. 158, pp. 279–317, Dec. 2019, doi: 10.1016/j.isprsjprs.2019.09.006.
3.B. Rasti, P. Scheunders, P. Ghamisi, G. Licciardi, and J. Chanussot, “Noise reduction in hyperspectral imagery: Overview and application,” Remote Sens., vol. 10, no. 3, p. 482, Mar. 2018, doi: 10.3390/rs10030482.
4.W. Ma, “Hyperspectral image classification based on spatial and spectral kernels generation network,” Inf. Sci., vol. 578, pp. 435–456, Nov. 2021, doi: 10.1016/j.ins.2021.07.043.
5.D. Li, Q. Wang, and F. Kong, “Adaptive kernel sparse representation based on multiple feature learning for hyperspectral image classification,” Neurocomputing, vol. 400, pp. 97–112, Aug. 2020, doi: 10.1016/j.neucom.2020.03.022.
6.J. Fang and X. Cao, “Multidimensional relation learning for hyperspectral image classification,” Neurocomputing, vol. 410, pp. 211–219, Oct. 2020, doi: 10.1016/j.neucom.2020.05.034.
7.D. AL-Alimi, Z. Cai, M. A. A. Al-qaness, E. A. Alawamy, and A. Alalimi, “ETR: Enhancing transformation reduction for reducing dimensionality and classification complexity in hyperspectral images,” Expert Syst. Appl., vol. 213, Mar. 2023, Art. no. 118971, doi: 10.1016/j.eswa.2022.118971.
8.D. AL-Alimi, Z. Cai, M. A. A. Al-qaness, A. Dahou, E. A. Alawamy, and S. Issaka, “Compression and reinforce variation with convolutional neural networks for hyperspectral image classification,” Appl. Soft Comput., vol. 130, Nov. 2022, Art. no. 109650, doi: 10.1016/j.asoc.2022.109650.
9.S. K. Roy, G. Krishna, S. R. Dubey, and B. B. Chaudhuri, “HybridSN: Exploring 3-D–2-D CNN feature hierarchy for hyperspectral image classification,” IEEE Geosci. Remote Sens. Lett., vol. 17, no. 2, pp. 277–281, Feb. 2020, doi: 10.1109/LGRS.2019.2918719.
10.D. AL-Alimi, M. A. A. Al-qaness, Z. Cai, A. Dahou, Y. Shao, and S. Issaka, “Meta-learner hybrid models to classify hyperspectral images,” Remote Sens., vol. 14, no. 4, p. 1038, Feb. 2022, doi: 10.3390/rs14041038.
11.F. Cao and W. Guo, “Cascaded dual-scale crossover network for hyperspectral image classification,” Knowl.-Based Syst., vol. 189, Feb. 2020, Art. no. 105122, doi: 10.1016/j.knosys.2019.105122.
12.W. Wang, Y. Han, C. Deng, and Z. Li, “Hyperspectral image classification via deep structure dictionary learning,” Remote Sens., vol. 14, no. 9, p. 2266, May 2022, doi: 10.3390/rs14092266.
13.S. K. Roy, S. R. Dubey, S. Chatterjee, and B. B. Chaudhuri, “FuSENet: Fused squeeze-and-excitation network for spectral–spatial hyperspectral image classification,” IET Image Process., vol. 14, no. 8, pp. 1653–1661, Jun. 2020, doi: 10.1049/iet-ipr.2019.1462.
14.S. Ghaderizadeh, D. Abbasi-Moghadam, A. Sharifi, N. Zhao, and A. Tariq, “Hyperspectral image classification using a hybrid 3D-2D convolutional neural networks,” IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., vol. 14, pp. 7570–7588, 2021, doi: 10.1109/JSTARS.2021.3099118.
15.J. Zheng, Y. Feng, C. Bai, and J. Zhang, “Hyperspectral image classification using mixed convolutions and covariance pooling,” IEEE Trans. Geosci. Remote Sens., vol. 59, no. 1, pp. 522–534, Jan. 2021, doi: 10.1109/TGRS.2020.2995575.
16.A. Paul, S. Bhoumik, and N. Chaki, “SSNET: An improved deep hybrid network for hyperspectral image classification,” Neural Comput. Appl., vol. 33, no. 5, pp. 1575–1585, Mar. 2021, doi: 10.1007/s00521-020-05069-1.
17.C. Deng, Y. Xue, X. Liu, C. Li, and D. Tao, “Active transfer learning network: A unified deep joint spectral–spatial feature learning model for hyperspectral image classification,” IEEE Trans. Geosci. Remote Sens., vol. 57, no. 3, pp. 1741–1754, Mar. 2019, doi: 10.1109/TGRS.2018.2868851.
18.Y. Liu, L. Gao, C. Xiao, Y. Qu, K. Zheng, and A. Marinoni, “Hyperspectral image classification based on a shuffled group convolutional neural network with transfer learning,” Remote Sens., vol. 12, no. 11, p. 1780, Jun. 2020, doi: 10.3390/rs12111780.
19.N. Wambugu, “Hyperspectral image classification on insufficient-sample and feature learning using deep neural networks: A review,” Int. J. Appl. Earth Observ. Geoinf., vol. 105, Dec. 2021, Art. no. 102603, doi: 10.1016/j.jag.2021.102603.
20.L. Yang, F. Zhang, P. S.-P. Wang, X. Li, and Z. Meng, “Multi-scale spatial–spectral fusion based on multi-input fusion calculation and coordinate attention for hyperspectral image classification,” Pattern Recognit., vol. 122, Feb. 2022, Art. no. 108348, doi: 10.1016/j.patcog.2021.108348.
21.R. Hang, Z. Li, Q. Liu, P. Ghamisi, and S. S. Bhattacharyya, “Hyperspectral image classification with attention-aided CNNs,” IEEE Trans. Geosci. Remote Sens., vol. 59, no. 3, pp. 2281–2293, Mar. 2021, doi: 10.1109/TGRS.2020.3007921.
22.S. Pande and B. Banerjee, “HyperLoopNet: Hyperspectral image classification using multiscale self-looping convolutional networks,” ISPRS J. Photogramm. Remote Sens., vol. 183, pp. 422–438, Jan. 2022, doi: 10.1016/j.isprsjprs.2021.11.021.
23.Y. Feng, J. Zheng, M. Qin, C. Bai, and J. Zhang, “3D octave and 2D vanilla mixed convolutional neural network for hyperspectral image classification with limited samples,” Remote Sens., vol. 13, no. 21, p. 4407, Nov. 2021, doi: 10.3390/rs13214407.
24.L. Huang and Y. Chen, “Dual-path Siamese CNN for hyperspectral image classification with limited training samples,” IEEE Geosci. Remote Sens. Lett., vol. 18, no. 3, pp. 518–522, Mar. 2021, doi: 10.1109/LGRS.2020.2979604.
25.R. Chen and G. Li, “Spectral–spatial feature fusion via dual-stream deep architecture for hyperspectral image classification,” Infr. Phys. Technol., vol. 119, Dec. 2021, Art. no. 103935, doi: 10.1016/j.infrared.2021.103935.
26.C. Pu, H. Huang, and L. Yang, “An attention-driven convolutional neural network-based multi-level spectral–spatial feature learning for hyperspectral image classification,” Expert Syst. Appl., vol. 185, Dec. 2021, Art. no. 115663, doi: 10.1016/j.eswa.2021.115663.
27.M. Bandyopadhyay, “Multi-stack hybrid CNN with non-monotonic activation functions for hyperspectral satellite image classification,” Neural Comput. Appl., vol. 33, no. 21, pp. 14809–14822, Nov. 2021, doi: 10.1007/s00521-021-06120-5.
28.Y. Guo, H. Cao, J. Bai, and Y. Bai, “High efficient deep feature extraction and classification of spectral–spatial hyperspectral image using cross domain convolutional neural networks,” IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., vol. 12, no. 1, pp. 345–356, Jan. 2019, doi: 10.1109/JSTARS.2018.2888808.
29.S. G. Azar, S. Meshgini, T. Y. Rezaii, and S. Beheshti, “Hyperspectral image classification based on sparse modeling of spectral blocks,” Neurocomputing, vol. 407, pp. 12–23, Sep. 2020, doi: 10.1016/j.neucom.2020.04.138.
30.X. Tu, X. Shen, P. Fu, T. Wang, Q. Sun, and Z. Ji, “Discriminant sub-dictionary learning with adaptive multiscale superpixel representation for hyperspectral image classification,” Neurocomputing, vol. 409, pp. 131–145, Oct. 2020, doi: 10.1016/j.neucom.2020.05.082.
31.J. An, X. Zhang, H. Zhou, J. Feng, and L. Jiao, “Patch tensor-based sparse and low-rank graph for hyperspectral images dimensionality reduction,” IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., vol. 11, no. 7, pp. 2513–2527, Jul. 2018, doi: 10.1109/JSTARS.2018.2833886.
32.Z. Qiumei, T. Dan, and W. Fenghua, “Improved convolutional neural network based on fast exponentially linear unit activation function,” IEEE Access, vol. 7, pp. 151359–151367, 2019, doi: 10.1109/ACCESS.2019.2948112.
33.S. U. Amin, M. Alsulaiman, G. Muhammad, M. A. Mekhtiche, and M. S. Hossain, “Deep learning for EEG motor imagery classification based on multi-layer CNNs feature fusion,” Future Gener. Comput. Syst., vol. 101, pp. 542–554, Dec. 2019, doi: 10.1016/j.future.2019.06.027.
34.L. Yang, W. Chen, W. Liu, B. Zha, and L. Zhu, “Random noise attenuation based on residual convolutional neural network in seismic datasets,” IEEE Access, vol. 8, pp. 30271–30286, 2020, doi: 10.1109/ACCESS.2020.2972464.
35.
M. Z. Alom, “A state-of-the-art survey on deep learning theory and architectures,” Electronics, vol. 8, no. 3, p. 292, Mar. 2019, doi: 10.3390/electronics8030292.
36.Z. Sun, L. Xie, D. Hu, and Y. Ying, “An artificial neural network model for accurate and efficient optical property mapping from spatial-frequency domain images,” Comput. Electron. Agricult., vol. 188, Sep. 2021, Art. no. 106340, doi: 10.1016/j.compag.2021.106340.
37.N. Wu, S. Weng, J. Chen, Q. Xiao, C. Zhang, and Y. He, “Deep convolution neural network with weighted loss to detect rice seeds vigor based on hyperspectral imaging under the sample-imbalanced condition,” Comput. Electron. Agricult., vol. 196, May 2022, Art. no. 106850, doi: 10.1016/j.compag.2022.106850.
38.S. Fan, “On line detection of defective apples using computer vision system combined with deep learning methods,” J. Food Eng., vol. 286, Dec. 2020, Art. no. 110102, doi: 10.1016/j.jfoodeng.2020.110102.
39.L. Zhang, D. An, Y. Wei, J. Liu, and J. Wu, “Prediction of oil content in single maize kernel based on hyperspectral imaging and attention convolution neural network,” Food Chem., vol. 395, Nov. 2022, Art. no. 133563, doi: 10.1016/j.foodchem.2022.133563.
40.L. E. C. La Rosa, C. Sothe, R. Q. Feitosa, C. M. de Almeida, M. B. Schimalski, and D. A. B. Oliveira, “Multi-task fully convolutional network for tree species mapping in dense forests using small training hyperspectral data,” ISPRS J. Photogramm. Remote Sens., vol. 179, pp. 35–49, Sep. 2021, doi: 10.1016/j.isprsjprs.2021.07.001.
41.L. Pang, L. Wang, P. Yuan, L. Yan, and J. Xiao, “Rapid seed viability prediction of Sophora japonica by improved successive projection algorithm and hyperspectral imaging,” Infr. Phys. Technol., vol. 123, Jun. 2022, Art. no. 104143, doi: 10.1016/j.infrared.2022.104143.
42.Y. Dixit, M. Al-Sarayreh, C. R. Craigie, and M. M. Reis, “A global calibration model for prediction of intramuscular fat and pH in red meat using hyperspectral imaging,” Meat Sci., vol. 181, Nov. 2021, Art. no. 108405, doi: 10.1016/j.meatsci.2020.108405.
43.Z. An, J. Zhang, Z. Sheng, X. Er, and J. Lv, “RBDN: Residual bottleneck dense network for image super-resolution,” IEEE Access, vol. 9, pp. 103440–103451, 2021, doi: 10.1109/ACCESS.2021.3096548.
44.M. Ahmad, “Hyperspectral image classification—Traditional to deep models: A survey for future prospects,” IEEE J. Sel. Topics Appl. Earth Observ. Remote Sens., vol. 15, pp. 968–999, 2022, doi: 10.1109/JSTARS.2021.3133021.
45.D. Erhan, Y. Bengio, A. Courville, P.-A. Manzagol, P. Vincent, and S. Bengio, “Why does unsupervised pre-training help deep learning? ” J. Mach. Learn. Res., vol. 11, no. 19, pp. 625–660, 2010. [Online]. Available: https://jmlr.org/papers/v11/erhan10a.html
46.K. He, X. Zhang, S. Ren, and J. Sun, “Deep residual learning for image recognition,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit., Jun. 2016, pp. 770–778, doi: 10.1109/CVPR.2016.90.
47.T.-Y. Lin, P. Dollár, R. Girshick, K. He, B. Hariharan, and S. Belongie, “Feature pyramid networks for object detection,” in Proc. IEEE Conf. Comput. Vis. Pattern Recognit. (CVPR), Jul. 2017, pp. 936–944, doi: 10.1109/CVPR.2017.106.
48.Y. Zhong, X. Hu, C. Luo, X. Wang, J. Zhao, and L. Zhang, “WHU-Hi: UAV-borne hyperspectral with high spatial resolution (H 2 ) benchmark datasets and classifier for precise crop identification based on deep convolutional neural network with CRF,” Remote Sens. Environ., vol. 250, Dec. 2020, Art. no. 112012, doi: 10.1016/j.rse.2020.112012.
49.A. Mohan and M. Venkatesan, “HybridCNN based hyperspectral image classification using multiscale spatiospectral features,” Infr. Phys. Technol., vol. 108, Aug. 2020, Art. no. 103326, doi: 10.1016/j.infrared.2020.103326.
50.X. Zhang, S. Chen, P. Zhu, X. Tang, J. Feng, and L. Jiao, “Spatial pooling graph convolutional network for hyperspectral image classification,” IEEE Trans. Geosci. Remote Sens., vol. 60, 2022, Art. no. 5521315, doi: 10.1109/TGRS.2022.3140353.
51.D. AL-Alimi, M. A. A. Al-qaness, Z. Cai, and E. A. Alawamy, “IDA: Improving distribution analysis for reducing data complexity and dimensionality in hyperspectral images,” Pattern Recognit., vol. 134, Feb. 2023, Art. no. 109096, doi: 10.1016/j.patcog.2022.109096.
52.B. Xi, “Multi-direction networks with attentional spectral prior for hyperspectral image classification,” IEEE Trans. Geosci. Remote Sens., vol. 60, 2022, Art. no. 5500915, doi: 10.1109/TGRS.2020.3047682.
53.J. Bai, “Hyperspectral image classification based on multibranch attention transformer networks,” IEEE Trans. Geosci. Remote Sens., vol. 60, 2022, Art. no. 5535317, doi: 10.1109/TGRS.2022.3196661.
54.Z. Ge, G. Cao, Y. Zhang, X. Li, H. Shi, and P. Fu, “Adaptive hash attention and lower triangular network for hyperspectral image classification,” IEEE Trans. Geosci. Remote Sens., vol. 60, 2022, Art. no. 5509119, doi: 10.1109/TGRS.2021.3075546.
55.D. AL-Alimi, M. A. A. Al-qaness, and Z. Cai, “Speeding up and enhancing the hyperspectral images classification,” in Proc. Int. Conf. Artif. Intell. Sci. Appl. (CAISA), M. A. Elaziz, M. M. Gaber, S. El-Sappagh, M. A. A. Al-qaness, and A. A. Ewees, Eds. Cham, Switzerland : Springer, 2023, pp. 53–62, doi: 10.1007/978-3-031-28106-8_4.
56.R. Shang, “Hyperspectral image classification based on pyramid coordinate attention and weighted self-distillation,” IEEE Trans. Geosci. Remote Sens., vol. 60, 2022, Art. no. 5544316, doi: 10.1109/TGRS.2022.3224604.
57.J. Bai, “Few-shot hyperspectral image classification based on adaptive subspaces and feature transformation,” IEEE Trans. Geosci. Remote Sens., vol. 60, 2022, Art. no. 5523917, doi: 10.1109/TGRS.2022.3149947.
58.Q. Liu, Y. Dong, Y. Zhang, and H. Luo, “A fast dynamic graph convolutional network and CNN parallel network for hyperspectral image classification,” IEEE Trans. Geosci. Remote Sens., vol. 60, 2022, Art. no. 5530215, doi: 10.1109/TGRS.2022.3179419.
