FHIC: Fast Hyperspectral Image Classification Model Using ETR Dimensionality Reduction and ELU Activation Function
DOI:
https://doi.org/10.1109/TGRS.2023.3314619Keywords:
Feature extraction , Brain modeling , Adaptation models , Hyperspectral imaging , Data models , Atmospheric modeling , TrainingAbstract
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.References
Vidal, M., & Amigo, J. M. (2012). Pre-processing of hyperspectral images. Essential steps before image analysis. Chemometrics and Intelligent Laboratory Systems, 117, 138–148. https://doi.org/10.1016/j.chemolab.2012.05.009
Paoletti, M. E., Haut, J. M., Plaza, J., & Plaza, A. (2019). Deep learning classifiers for hyperspectral imaging: A review. ISPRS Journal of Photogrammetry and Remote Sensing, 158, 279–317. https://doi.org/10.1016/j.isprsjprs.2019.09.006
Rasti, B., Scheunders, P., Ghamisi, P., Licciardi, G., & Chanussot, J. (2018). Noise reduction in hyperspectral imagery: Overview and application. Remote Sensing, 10(3), Article 482. https://doi.org/10.3390/rs10030482
Ma, W. (2021). Hyperspectral image classification based on spatial and spectral kernels generation network. Information Sciences, 578, 435–456. https://doi.org/10.1016/j.ins.2021.07.043
Li, D., Wang, Q., & Kong, F. (2020). Adaptive kernel sparse representation based on multiple feature learning for hyperspectral image classification. Neurocomputing, 400, 97–112. https://doi.org/10.1016/j.neucom.2020.03.022
Fang, J., & Cao, X. (2020). Multidimensional relation learning for hyperspectral image classification. Neurocomputing, 410, 211–219. https://doi.org/10.1016/j.neucom.2020.05.034
Al-Alimi, D., Cai, Z., Al-Qaness, M. A. A., Alawamy, E. A., & Alalimi, A. (2023). ETR: Enhancing transformation reduction for reducing dimensionality and classification complexity in hyperspectral images. Expert Systems with Applications, 213, Article 118971. https://doi.org/10.1016/j.eswa.2022.118971
Al-Alimi, D., Cai, Z., Al-Qaness, M. A. A., Dahou, A., Alawamy, E. A., & Issaka, S. (2022). Compression and reinforce variation with convolutional neural networks for hyperspectral image classification. Applied Soft Computing, 130, Article 109650. https://doi.org/10.1016/j.asoc.2022.109650
Roy, S. K., Krishna, G., Dubey, S. R., & Chaudhuri, B. B. (2020). HybridSN: Exploring 3-D–2-D CNN feature hierarchy for hyperspectral image classification. IEEE Geoscience and Remote Sensing Letters, 17(2), 277–281. https://doi.org/10.1109/LGRS.2019.2918719
Al-Alimi, D., Al-Qaness, M. A. A., Cai, Z., Dahou, A., Shao, Y., & Issaka, S. (2022). Meta-learner hybrid models to classify hyperspectral images. Remote Sensing, 14(4), Article 1038. https://doi.org/10.3390/rs14041038
Cao, F., & Guo, W. (2020). Cascaded dual-scale crossover network for hyperspectral image classification. Knowledge-Based Systems, 189, Article 105122. https://doi.org/10.1016/j.knosys.2019.105122
Wang, W., Han, Y., Deng, C., & Li, Z. (2022). Hyperspectral image classification via deep structure dictionary learning. Remote Sensing, 14(9), Article 2266. https://doi.org/10.3390/rs14092266
Roy, S. K., Dubey, S. R., Chatterjee, S., & Chaudhuri, B. B. (2020). FuSENet: Fused squeeze-and-excitation network for spectral–spatial hyperspectral image classification. IET Image Processing, 14(8), 1653–1661. https://doi.org/10.1049/iet-ipr.2019.1462
Ghaderizadeh, S., Abbasi-Moghadam, D., Sharifi, A., Zhao, N., & Tariq, A. (2021). Hyperspectral image classification using a hybrid 3D-2D convolutional neural networks. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14, 7570–7588. https://doi.org/10.1109/JSTARS.2021.3099118
Zheng, J., Feng, Y., Bai, C., & Zhang, J. (2021). Hyperspectral image classification using mixed convolutions and covariance pooling. IEEE Transactions on Geoscience and Remote Sensing, 59(1), 522–534. https://doi.org/10.1109/TGRS.2020.2995575
Paul, A., Bhoumik, S., & Chaki, N. (2021). SSNET: An improved deep hybrid network for hyperspectral image classification. Neural Computing and Applications, 33(5), 1575–1585. https://doi.org/10.1007/s00521-020-05069-1
Deng, C., Xue, Y., Liu, X., Li, C., & Tao, D. (2019). Active transfer learning network: A unified deep joint spectral–spatial feature learning model for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 57(3), 1741–1754. https://doi.org/10.1109/TGRS.2018.2868851
Liu, Y., Gao, L., Xiao, C., Qu, Y., Zheng, K., & Marinoni, A. (2020). Hyperspectral image classification based on a shuffled group convolutional neural network with transfer learning. Remote Sensing, 12(11), Article 1780. https://doi.org/10.3390/rs12111780
Wambugu, N. (2021). Hyperspectral image classification on insufficient-sample and feature learning using deep neural networks: A review. International Journal of Applied Earth Observation and Geoinformation, 105, Article 102603. https://doi.org/10.1016/j.jag.2021.102603
Yang, L., Zhang, F., Wang, P. S. P., Li, X., & Meng, Z. (2022). Multi-scale spatial–spectral fusion based on multi-input fusion calculation and coordinate attention for hyperspectral image classification. Pattern Recognition, 122, Article 108348. https://doi.org/10.1016/j.patcog.2021.108348
Hang, R., Li, Z., Liu, Q., Ghamisi, P., & Bhattacharyya, S. S. (2021). Hyperspectral image classification with attention-aided CNNs. IEEE Transactions on Geoscience and Remote Sensing, 59(3), 2281–2293. https://doi.org/10.1109/TGRS.2020.3007921
Pande, S., & Banerjee, B. (2022). HyperLoopNet: Hyperspectral image classification using multiscale self-looping convolutional networks. ISPRS Journal of Photogrammetry and Remote Sensing, 183, 422–438. https://doi.org/10.1016/j.isprsjprs.2021.11.021
Feng, Y., Zheng, J., Qin, M., Bai, C., & Zhang, J. (2021). 3D octave and 2D vanilla mixed convolutional neural network for hyperspectral image classification with limited samples. Remote Sensing, 13(21), Article 4407. https://doi.org/10.3390/rs13214407
Huang, L., & Chen, Y. (2021). Dual-path Siamese CNN for hyperspectral image classification with limited training samples. IEEE Geoscience and Remote Sensing Letters, 18(3), 518–522. https://doi.org/10.1109/LGRS.2020.2979604
Chen, R., & Li, G. (2021). Spectral–spatial feature fusion via dual-stream deep architecture for hyperspectral image classification. Infrared Physics & Technology, 119, Article 103935. https://doi.org/10.1016/j.infrared.2021.103935
Pu, C., Huang, H., & Yang, L. (2021). An attention-driven convolutional neural network-based multi-level spectral–spatial feature learning for hyperspectral image classification. Expert Systems with Applications, 185, Article 115663. https://doi.org/10.1016/j.eswa.2021.115663
Bandyopadhyay, M. (2021). Multi-stack hybrid CNN with non-monotonic activation functions for hyperspectral satellite image classification. Neural Computing and Applications, 33(21), 14809–14822. https://doi.org/10.1007/s00521-021-06120-5
Guo, Y., Cao, H., Bai, J., & Bai, Y. (2019). High efficient deep feature extraction and classification of spectral–spatial hyperspectral image using cross domain convolutional neural networks. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 12(1), 345–356. https://doi.org/10.1109/JSTARS.2018.2888808
Azar, S. G., Meshgini, S., Rezaii, T. Y., & Beheshti, S. (2020). Hyperspectral image classification based on sparse modeling of spectral blocks. Neurocomputing, 407, 12–23. https://doi.org/10.1016/j.neucom.2020.04.138
Tu, X., Shen, X., Fu, P., Wang, T., Sun, Q., & Ji, Z. (2020). Discriminant sub-dictionary learning with adaptive multiscale superpixel representation for hyperspectral image classification. Neurocomputing, 409, 131–145. https://doi.org/10.1016/j.neucom.2020.05.082
An, J., Zhang, X., Zhou, H., Camp, J., & Jiao, L. (2018). Patch tensor-based sparse and low-rank graph for hyperspectral images dimensionality reduction. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 11(7), 2513–2527. https://doi.org/10.1109/JSTARS.2018.2833886
Qiumei, Z., Dan, T., & Fenghua, W. (2019). Improved convolutional neural network based on fast exponentially linear unit activation function. IEEE Access, 7, 151359–151367. https://doi.org/10.1109/ACCESS.2019.2948112
Amin, S. U., Alsulaiman, M., Muhammad, G., Mekhtiche, M. A., & Hossain, M. S. (2019). Deep learning for EEG motor imagery classification based on multi-layer CNNs feature fusion. Future Generation Computer Systems, 101, 542–554. https://doi.org/10.1016/j.future.2019.06.027
Yang, L., Chen, W., Liu, W., Zha, B., & Zhu, L. (2020). Random noise attenuation based on residual convolutional neural network in seismic datasets. IEEE Access, 8, 30271–30286. https://doi.org/10.1109/ACCESS.2020.2972464
Alom, M. Z., Taha, T. M., Yakopcic, C., Westberg, S., Sidike, P., Nasrin, M. S., Hasan, M., Van Esesn, B. C., Awwal, A. A. S., & Asari, V. K. (2019). A state-of-the-art survey on deep learning theory and architectures. Electronics, 8(3), Article 292. https://doi.org/10.3390/electronics8030292
Sun, Z., Xie, L., Hu, D., & Ying, Y. (2021). An artificial neural network model for accurate and efficient optical property mapping from spatial-frequency domain images. Computers and Electronics in Agriculture, 188, Article 106340. https://doi.org/10.1016/j.compag.2021.106340
Wu, N., Weng, S., Chen, J., Xiao, Q., Zhang, C., & He, Y. (2022). Deep convolution neural network with weighted loss to detect rice seeds vigor based on hyperspectral imaging under the sample-imbalanced condition. Computers and Electronics in Agriculture, 196, Article 106850. https://doi.org/10.1016/j.compag.2022.106850
Fan, S., Li, J., Zhang, Y., Tian, X., Wang, Q., He, X., Zhang, C., & Huang, W. (2020). On line detection of defective apples using computer vision system combined with deep learning methods. Journal of Food Engineering, 286, Article 110102. https://doi.org/10.1016/j.jfoodeng.2020.110102
Zhang, L., An, D., Wei, Y., Liu, J., & Wu, J. (2022). Prediction of oil content in single maize kernel based on hyperspectral imaging and attention convolution neural network. Food Chemistry, 395, Article 133563. https://doi.org/10.1016/j.foodchem.2022.133563
La Rosa, L. E. C., Sothe, C., Feitosa, R. Q., de Almeida, C. M., Schimalski, M. B., & Oliveira, D. A. B. (2021). Multi-task fully convolutional network for tree species mapping in dense forests using small training hyperspectral data. ISPRS Journal of Photogrammetry and Remote Sensing, 179, 35–49. https://doi.org/10.1016/j.isprsjprs.2021.07.001
Pang, L., Wang, L., Yuan, P., Yan, L., & Xiao, J. (2022). Rapid seed viability prediction of Sophora japonica by improved successive projection algorithm and hyperspectral imaging. Infrared Physics & Technology, 123, Article 104143. https://doi.org/10.1016/j.infrared.2022.104143
Dixit, Y., Al-Sarayreh, M., Craigie, C. R., & Reis, M. M. (2021). A global calibration model for prediction of intramuscular fat and pH in red meat using hyperspectral imaging. Meat Science, 181, Article 108405. https://doi.org/10.1016/j.meatsci.2020.108405
An, Z., Zhang, J., Sheng, Z., Er, X., & Lv, J. (2021). RBDN: Residual bottleneck dense network for image super-resolution. IEEE Access, 9, 103440–103451. https://doi.org/10.1109/ACCESS.2021.3096548
Ahmad, M., Khan, A. M., Mazzara, M., Distefano, S., Ali, M., & Shahid, M. S. (2022). Hyperspectral image classification—Traditional to deep models: A survey for future prospects. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 15, 968–999. https://doi.org/10.1109/JSTARS.2021.3133021
Erhan, D., Bengio, Y., Courville, A., Manzagol, P. A., Vincent, P., & Bengio, S. (2010). Why does unsupervised pre-training help deep learning? Journal of Machine Learning Research, 11(19), 625–660. https://jmlr.org/papers/v11/erhan10a.html
He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 770–778. https://doi.org/10.1109/CVPR.2016.90
Lin, T. Y., Dollár, P., Girshick, R., He, K., Hariharan, B., & Belongie, S. (2017). Feature pyramid networks for object detection. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 936–944. https://doi.org/10.1109/CVPR.2017.106
Zhong, Y., Hu, X., Luo, C., Wang, X., Zhao, J., & Zhang, L. (2020). WHU-Hi: UAV-borne hyperspectral with high spatial resolution (H2) benchmark datasets and classifier for precise crop identification based on deep convolutional neural network with CRF. Remote Sensing of Environment, 250, Article 112012. https://doi.org/10.1016/j.rse.2020.112012
Mohan, A., & Venkatesan, M. (2020). HybridCNN based hyperspectral image classification using multiscale spatiospectral features. Infrared Physics & Technology, 108, Article 103326. https://doi.org/10.1016/j.infrared.2020.103326
Zhang, X., Chen, S., Zhu, P., Tang, X., Feng, J., & Jiao, L. (2022). Spatial pooling graph convolutional network for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 60, Article 5521315. https://doi.org/10.1109/TGRS.2022.3140353
Al-Alimi, D., M. A. A. Al-Qaness, Cai, Z., & Alawamy, E. A. (2023). IDA: Improving distribution analysis for reducing data complexity and dimensionality in hyperspectral images. Pattern Recognition, 134, Article 109096. https://doi.org/10.1016/j.patcog.2022.109096
Xi, B., Li, J., Li, Y., Song, R., Shi, Y., & Du, Q. (2022). Multi-direction networks with attentional spectral prior for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 60, Article 5500915. https://doi.org/10.1109/TGRS.2020.3047682
Bai, J., Yuan, A., Xiao, Z., Wang, J., & Jiao, L. (2022). Hyperspectral image classification based on multibranch attention transformer networks. IEEE Transactions on Geoscience and Remote Sensing, 60, Article 5535317. https://doi.org/10.1109/TGRS.2022.3196661
Ge, Z., Cao, G., Zhang, Y., Li, X., Shi, H., & Fu, P. (2022). Adaptive hash attention and lower triangular network for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 60, Article 5509119. https://doi.org/10.1109/TGRS.2021.3075546
Al-Alimi, D., Al-Qaness, M. A. A., & Cai, Z. (2023). Speeding up and enhancing the hyperspectral images classification. In M. A. Elaziz, M. M. Gaber, S. El-Sappagh, M. A. A. Al-Qaness, & A. A. Ewees (Eds.), Proceedings of the International Conference on Artificial Intelligence Sciences and Applications (CAISA) (pp. 53–62). Springer. https://doi.org/10.1007/978-3-031-28106-8_4
Shang, R., Zhang, J., Wang, L., Zhang, J., & Jiao, L. (2022). Hyperspectral image classification based on pyramid coordinate attention and weighted self-distillation. IEEE Transactions on Geoscience and Remote Sensing, 60, Article 5544316. https://doi.org/10.1109/TGRS.2022.3224604
Bai, J., Yuan, A., & Jiao, L. (2022). Few-shot hyperspectral image classification based on adaptive subspaces and feature transformation. IEEE Transactions on Geoscience and Remote Sensing, 60, Article 5523917. https://doi.org/10.1109/TGRS.2022.3149947
Liu, Q., Dong, Y., Zhang, Y., & Luo, H. (2022). A fast dynamic graph convolutional network and CNN parallel network for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 60, Article 5530215. https://doi.org/10.1109/TGRS.2022.3179419
