Précédent|Prochain

Classifier mechanism embedded feature-extraction method for hyperspectral images

  • role： First author第一作者
  • Affiliation：

    School of Information and Control Engineering, China University of Mining and Technology, Xuzhou 221116

  • Email：xingcd_nuaa@163.com
  • Introduction：邢长达， 研究方向为基于机器学习的遥感图像智能分析。E-mail： xingcd_nuaa@163.com
XING Changda1,  
  • role： Corresponding author通信作者
  • Affiliation：

    College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing 211106

  • Email：mely_nuaa@163.com
  • Introduction：汪美玲， 研究方向为基于机器学习的智能计算。E-mail： mely_nuaa@163.com
WANG Meiling2*,  
  • Affiliation：

    College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 211106

XU Yongchang3,  
  • Affiliation：

    College of Automation Engineering, Nanjing University of Aeronautics and Astronautics, Nanjing 211106

WANG Zhisheng3

résumé

As an important technique in image interpretation, hyperspectral image (HSI) classification is extensively used in many fields, such as remote-sensing observation and intelligent medical service. HSI classification may comprise label prediction based on feature extraction and based on classifiers. Although deep learning can directly obtain the classification results by one step, which is achieved by the end-to-end network structure from data input to classification result output, they are actually viewed as a direct cascade of both feature extraction based on deep networks (such as deep autoencoder and convolutional neural network) and classifiers (such as softmax and logistic regression). Most current classification approaches do not consider the influence of classifiers on feature extraction, which may cause the incompatibility between the extracted features and the used classifier. This incompatibility is reflected in the poor matching relationship between the classifier model and its input feature data, leading to poor prediction results.Method To remedy such deficiency, this paper presents a novel kind of HSI feature-extraction methods embedded by the classifier mechanism, which can ensure the compatibility between feature extraction and the used classifier. Thus, the features can be more easily calculated by classifier accurately, and classification prediction results can be improved. Two specific forms are given in this paper. 1) The sparse representation (SR)feature-extraction model compatible with Support Vector Machine (SVM) classifier is built, which embeds the SVM property into the SR. 2) The deep autoencoder (DAE) feature-extraction model compatible with softmax classifier is constructed, which integrates the softmax function into DAE network. We also provide the optimization strategy to obtain the optimal solutions of the SR and DAE models.Results The proposed SR and DAE models are experimentally evaluated on the remote-sensing HSI data and medical HSI data. The experiments consist of parameter analysis, algorithm comparison, ablation study, and convergence analysis. According to the parameter analysis, we validate that the values of important parameters have obvious impact on the performance of our methods and successfully select the best values of these parameters. As suggested by the algorithm comparison, the proposed methods achieve better classification performance than some state-of-the-art approaches, which have obvious effectiveness and superiority. The overall accuracy, average accuracy, and Kappa indices in the HSI classification task are, on average, higher by 5.03%, 5.13%, and 7.30%, respectively. An ablation study is conducted to demonstrate the effectiveness of the compatibility between feature extraction and the bedded classifiers for the performance improvement of HSI classification. Convergence analysis indicates that the designed optimization-solution strategy can meet the application requirements of reliability and rapidity.Conclusion The proposed SR and DAE methods realize good compatibility between feature extraction and classifiers. Accordingly, the extracted features can be better calculated by classifiers, and more competitive classification performance can be achieved.

mots-clés

hyperspectral image classification;feature extraction;classifier mechanism;sparse representation;deep autoencoder network

References

  1. 1.
    Bai J, Lu J W, Xiao Z, Chen Z and Jiao L C. 2022. Generative adversarial networks based on transformer encoder and convolution block for hyperspectral image classification. Remote Sensing, 14(14): 3426
  2. 2.
    Benediktsson J A, Palmason J A and Sveinsson J R. 2005. Classification of hyperspectral data from urban areas based on extended morphological profiles. IEEE Transactions on Geoscience and Remote Sensing, 43(3): 480-491
  3. 3.
    Benediktsson J A, Pesaresi M and Amason K. 2003. Classification and feature extraction for remote sensing images from urban areas based on morphological transformations. IEEE Transactions on Geoscience and Remote Sensing, 41(9): 1940-1949
  4. 4.
    Cao X Y, Yao J, Xu Z B and Meng D Y. 2020. Hyperspectral image classification with convolutional neural network and active learning. IEEE Transactions on Geoscience and Remote Sensing, 58(7): 4604-4616
  5. 5.
    Chen Y, Nasrabadi N M and Tran T D. 2011. Hyperspectral image classification using dictionary-based sparse representation. IEEE Transactions on Geoscience and Remote Sensing, 49(10): 3973-3985
  6. 6.
    Chen Y S, Lin Z H, Zhao X, Wang G and Gu Y F. 2014. Deep learning-based classification of hyperspectral data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7(6): 2094-2107
  7. 7.
    Chen Y S, Zhao X and Jia X P. 2015. Spectral-spatial classification of hyperspectral data based on deep belief network. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 8(6): 2381-2392
  8. 8.
    Chen Z, Wu X J and Kittler J. 2020. Low-rank discriminative least squares regression for image classification. Signal Processing, 173: 107485
  9. 9.
    Dong Y N, Liu Q W, Du B and Zhang L P. 2022. Weighted feature fusion of convolutional neural network and graph attention network for hyperspectral image classification. IEEE Transactions on Image Processing, 31: 1559-1572
  10. 10.
    Fang L Y, Liu G Y, Li S, Ghamisi P T and Benediktsson J A. 2019. Hyperspectral image classification with squeeze multibias network. IEEE Transactions on Geoscience and Remote Sensing, 57(3): 1291-1301
  11. 11.
    Fang L Y, Wang C, Li S T and Benediktsson J A. 2017. Hyperspectral image classification via multiple-feature-based adaptive sparse representation. IEEE Transactions on Instrumentation and Measurement, 66(7): 1646-1657
  12. 12.
    Fei B W, Akbari H and Halig L V. 2012. Hyperspectral imaging and spectral-spatial classification for cancer detection//Proceedings of the 5th International Conference on Biomedical Engineering and Informatics. Chongqing: IEEE: 62-64
  13. 13.
    Gao H M, Zhu M, Cao X Y, Li C M, Liu Q and Xu P P. 2023. A micro-hyperspectral image classification method of gallbladder cancer based on multi-scale fusion attention mechanism. Journal of Image and Graphics, 28(4): 1173-1185
  14. 14.
    Ghamisi P, Plaza J, Chen Y S, Li J and Plaza A J. 2017. Advanced spectral classifiers for hyperspectral images: a review. IEEE Geoscience and Remote Sensing Magazine, 5(1): 8-32
  15. 15.
    He Z, Liu L, Deng R R and Shen Y. 2016. Low-rank group inspired dictionary learning for hyperspectral image classification. Signal Processing, 120: 209-221
  16. 16.
    Hu W, Huang Y Y, Wei L, Zhang F and Li H C. 2015. Deep convolutional neural networks for hyperspectral image classification. Journal of Sensors, 2015: 258619
  17. 17.
    Jia S, Deng B, Zhu J S, Jia X P and Li Q Q. 2018. Local binary pattern based hyperspectral image classification with superpixel guidance. IEEE Transactions on Geoscience and Remote Sensing, 56(2): 749-759
  18. 18.
    Li W and Du Q. 2014. Gabor-filtering-based nearest regularized subspace for hyperspectral image classification. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7(4): 1012-1022
  19. 19.
    Li W, Lü M, Chen T H, Chu Z Y and Tao R. 2021. Application of a hyperspectral image in medical field: a review. Journal of Image and Graphics, 26(8): 1764-1785
  20. 20.
    Li Y S, Tang H J, Xie W X and Luo W H. 2022a. Multidimensional local binary pattern for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 60: 5505113
  21. 21.
    Li Z Y, Huang H, Zhang Z and Shi G Y. 2022b. Manifold-based multi-deep belief network for feature extraction of hyperspectral image. Remote Sensing, 14(6): 1484
  22. 22.
    Liang X J, Zhang Y and Zhang J P. 2021. Relative water content retrieval and refined classification of hyperspectral images based on a symbiotic neural network. National Remote Sensing Bulletin, 25(11): 2283-2302
  23. 23.
    Liao W Z, Bellens R, Pizurica A, Philips W and Pi Y G. 2012. Classification of hyperspectral data over urban areas using directional morphological profiles and semi-supervised feature extraction. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 5(4): 1177-1190
  24. 24.
    Nie J T, Zhang L, Wei W, Yan Q S, Ding C, Chen G C and Zhang Y N. 2023. A survey of hyperspectral image super-resolution method. Journal of Image and Graphics, 28(6): 1685-1697
  25. 25.
    Parikh N and Boyd S. 2014. Proximal algorithms. Foundations and Trends® in Optimization, 1(3): 127-239
  26. 26.
    Scholkopf B, Locatello F, Bauer S, Ke N R, Kalchbrenner N, Goyal A and Bengio Y. 2021. Toward causal representation learning. Proceedings of the IEEE, 109(5): 612-634
  27. 27.
    Tan S B and Wang Y F. 2007. Combining error-correcting output codes and model-refinement for text categorization//Proceedings of the 30th Annual International ACM SIGIR Conference on Research and Development in Information Retrieval. Amsterdam: ACM: 699-700
  28. 28.
    Wei X L, Li W, Zhang M M and Li Q L. 2019. Medical hyperspectral image classification based on end-to-end fusion deep neural network. IEEE Transactions on Instrumentation and Measurement, 68(11): 4481-4492
  29. 29.
    Wei X P, Yu X C, Zhang P Q, Zhi L and Yang F. 2020. CNN with local binary patterns for hyperspectral images classification. National Remote Sensing Bulletin, 24(8): 1000-1009
  30. 30.
    Wu Y F, Yang X H, Plaza A, Qiao F, Gao L R, Zhang B and Cui Y B. 2016. Approximate computing of remotely sensed data: SVM hyperspectral image classification as a case study. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 9(12): 5806-5818
  31. 31.
    Xing C D, Duan C W, Wang Z S and Wang M L. 2023. Binary feature learning with local spectral context-aware attention for classification of hyperspectral images. Pattern Recognition, 134: 109123
  32. 32.
    Xing C D, Wang M L, Dong C, Duan C W and Wang Z S. 2020. Joint sparse-collaborative representation to fuse hyperspectral and multispectral images. Signal Processing, 173: 107585
  33. 33.
    Xing C D, Wang M L, Wang Z S, Duan C W and Liu Y L. 2022. Diagonalized low-rank learning for hyperspectral image classification. IEEE Transactions on Geoscience and Remote Sensing, 60: 5507812
  34. 34.
    Xu Y H, Du B, Zhang F and Zhang L P. 2018. Hyperspectral image classification via a random patches network. ISPRS Journal of Photogrammetry and Remote Sensing, 142: 344-357
  35. 35.
    Xue Z H and Zhang Y J. 2022. Supervised hashing with RBF kernel and convolution for hyperspectral image classification. National Remote Sensing Bulletin, 26(4): 722-738
  36. 36.
    Zhang H Y, Li J Y, Huang Y C and Zhang L P. 2014. A nonlocal weighted joint sparse representation classification method for hyperspectral imagery. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 7(6): 2056-2065
  37. 37.
    Zhang S, Sun B, Li S T and Kang X D. 2021. Noise estimation of hyperspectral image in the spatial and spectral dimensions. National Remote Sensing Bulletin, 25(5): 1108-1123
  38. 38.
    Zhang X R, Weng P, Feng J, Zhang E L and Hou B. 2013. Spatial-spectral classification based on group sparse coding for hyperspectral image//Proceedings of the 2013 IEEE International Geoscience and Remote Sensing Symposium. Melbourne: IEEE: 1745-1748

Lire l'article complet

The above content is generated by Large Model Translation. The translated content is for reference only. We do not assume any commercial or legal responsibilty for any consequences arising from the use of our website