Browse > Article
http://dx.doi.org/10.7780/kjrs.2019.35.6.1.7

The Impact of the PCA Dimensionality Reduction for CNN based Hyperspectral Image Classification  

Kwak, Taehong (Department of Civil Engineering, Seoul National University)
Song, Ahram (Department of Civil Engineering, Seoul National University)
Kim, Yongil (Department of Civil Engineering, Seoul National University)
Publication Information
Korean Journal of Remote Sensing / v.35, no.6_1, 2019 , pp. 959-971 More about this Journal
Abstract
CNN (Convolutional Neural Network) is one representative deep learning algorithm, which can extract high-level spatial and spectral features, and has been applied for hyperspectral image classification. However, one significant drawback behind the application of CNNs in hyperspectral images is the high dimensionality of the data, which increases the training time and processing complexity. To address this problem, several CNN based hyperspectral image classification studies have exploited PCA (Principal Component Analysis) for dimensionality reduction. One limitation to this is that the spectral information of the original image can be lost through PCA. Although it is clear that the use of PCA affects the accuracy and the CNN training time, the impact of PCA for CNN based hyperspectral image classification has been understudied. The purpose of this study is to analyze the quantitative effect of PCA in CNN for hyperspectral image classification. The hyperspectral images were first transformed through PCA and applied into the CNN model by varying the size of the reduced dimensionality. In addition, 2D-CNN and 3D-CNN frameworks were applied to analyze the sensitivity of the PCA with respect to the convolution kernel in the model. Experimental results were evaluated based on classification accuracy, learning time, variance ratio, and training process. The size of the reduced dimensionality was the most efficient when the explained variance ratio recorded 99.7%~99.8%. Since the 3D kernel had higher classification accuracy in the original-CNN than the PCA-CNN in comparison to the 2D-CNN, the results revealed that the dimensionality reduction was relatively less effective in 3D kernel.
Keywords
Principal Component Analysis; Convolutional Neural Network; Dimensionality Reduction; Hyperspectral Image Classification;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Chen, Y., H. Jiang, C. Li, X. Jia, and P. Ghamisi, 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.   DOI
2 Cheng, Q., P.-K. Varshney, and M.-K. Arora, 2006. Logistic regression for feature selection and soft classification of remote sensing data, IEEE Geoscience and Remote Sensing Letters, 3(4): 491-494.   DOI
3 Rodarmel, C. and J. Shan, 2002. Principal component analysis for hyperspectral image classification, Surveying and Land Information Science, 62(2): 115-122.
4 Fauvel, M., J.-A. Benediktsson, J. Chanussot, and J.-R. Sveinsson, 2008. Spectral and spatial classification of hyperspectral data using SVMs and morphological profiles, IEEE Transactions on Geoscience and Remote Sensing, 46(11): 3804-3814.   DOI
5 Goodfellow, I., Y. Bengio, and A. Courville, 2016. Deep learning, MIT press, Cambridge, MA, USA.
6 He, M., B. Li, and H. Chen, 2017. Multi-scale 3d deep convolutional neural network for hyperspectral image classification, Proc. of 2017 IEEE International Conference on Image Processing, Beijing, China, Sep. 17-20, pp. 3904-3908.
7 Hu, W., Y. Huang, L. Wei, F. Zhang, and H. Li, 2015. Deep convolutional neural networks for hyperspectral image classification, Journal of Sensors, 2015(258619): 12.
8 Jensen, J. R. and K. Lulla, 1987. Introductory digital image processing: a remote sensing perspective, Prentice hall press, Bergen, NJ, USA.
9 Li, Y., H. Zhang, and Q. Shen, 2017. Spectral-spatial classification of hyperspectral imagery with 3D convolutional neural network, Remote Sensing, 9(1): 67.   DOI
10 Ji, S., W. Xu, M. Yang, and K. Yu, 2012. 3D convolutional neural networks for human action recognition, IEEE Transactions on Pattern Analysis and Machine Intelligence, 35(1): 221-231.   DOI
11 Liang, H. and Q. Li, 2016. Hyperspectral imagery classification using sparse representations of convolutional neural network features, Remote Sensing, 8(2): 99.   DOI
12 Lillesand, T., R.-W. Kiefer, and J. Chipman, 2015. Remote sensing and image interpretation, John Wiley & Sons, Hoboken, NJ, USA.
13 Lim, S., K.-H. Sohn, and C. Lee, 2001. Principal component analysis for compression of hyperspectral images, Proc. of IEEE 2001 International Geoscience and Remote Sensing Symposium, Sydney, NSW, Jul. 9-13, vol. 1, pp. 97-99.
14 Simonyan, K. and A. Zisserman, 2014. Very deep convolutional networks for large-scale image recognition, arXiv preprint arXiv: 1409.1556.
15 Loffe, S. and C. Szegedy, 2015. Batch normalization: Accelerating deep network training by reducing internal covariate shift, arXiv preprint arXiv:1502.03167.
16 Makantasis, K., K. Karantzalos, A. Doulamis, and N. Doulamis, 2015. Deep supervised learning for hyperspectral data classification through convolutional neural networks, Proc. of 2015 IEEE International Geoscience and Remote Sensing Symposium, Milan, Italy, Jul. 26-31, pp. 4959-4962.
17 Mei, X., E. Pan, Y. Ma, X. Dai, J. Huang, F. Fan, and J. Ma, 2019. Spectral-spatial attention networks for hyperspectral image classification, Remote Sensing, 11(8): 963.   DOI
18 Rodarmel, C. and J. Shan, 2002. Principal component analysis for hyperspectral image classification, Surveying and Land Information Science, 62(2): 115-122.
19 Samaniego, L., A. Bárdossy, and K. Schulz, 2008. Supervised classification of remotely sensed imagery using a modified k-NN technique, IEEE Transactions on Geoscience and Remote Sensing, 46(7): 2112-2125.   DOI
20 Slavkovikj, V., S. Verstockt, W. De Neve, S. Van Hoecke, and R. Van de Walle, 2015. Hyperspectral image classification with convolutional neural networks, Proc. of 23rd ACM International Conference on Multimedia, Brisbane, Australia, Oct. 26-30, pp. 1159-1162.
21 Srivastava, N., G. Hinton, A. Krizhevsky, I. Sutskever, and R. Salakhutdinov, 2014. Dropout: a simple way to prevent neural networks from overfitting, The Journal of Machine Learning Research, 15(1): 1929-1958.
22 Szegedy, C., W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, and A. Rabinovich, 2015. Going deeper with convolutions, Proc. of 2015 IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, Jun. 7-12, pp. 1-9.
23 Zhao, W. and S. Du, 2016. Spectral?spatial feature extraction for hyperspectral image classification: A dimension reduction and deep learning approach, IEEE Transactions on Geoscience and Remote Sensing, 54(8): 4544-4554.   DOI
24 Tarabalka, Y., J.-A. Benediktsson, and J. Chanussot, 2009. Spectral-spatial classification of hyperspectral imagery based on partitional clustering techniques, IEEE Transactions on Geoscience and Remote Sensing, 47(8): 2973-2987.   DOI
25 Tran, D., L. Bourdev, R. Fergus, L. Torresani, and M. Paluri, 2015. Learning spatiotemporal features with 3d convolutional networks, Proc. of 2015 IEEE International Conference on Computer Vision, Santiago, Chile, Dec. 7-13, pp. 4489-4497.
26 Zhang, H., Y. Li, Y. Zhang, and Q. Shen, 2017. Spectral-spatial classification of hyperspectral imagery using a dual-channel convolutional neural network, Remote Sensing Letters, 8(5): 438-447.   DOI