Current Science

Open Access Open Access  Restricted Access Subscription Access

A Methodology for Unsupervised Feature Learning in Hyperspectral Imagery Using Deep Belief Network


Affiliations
1 Department of Electronics and Communication Engineering, Sri Venkateswara College of Engineering, Sriperumbudur 602 117, India
 

Deep learning approaches have received major interest in the field of remote sensing. Hyperspectral imaging has rich data that are distributed in multi-dimensions. It is challenging to apply deep learning algorithms due to the limited amount of labelled data. So, unsupervised feature extraction approaches are used to overcome this limitation. In this study, we propose an unsupervised feature learning approach using deep belief network (DBN). In the proposed framework, the input hyperspectral image is segmented using entropy rate superpixel segmentation and filtered by domain transform recursive filter which extracts spatial and spectral information effectively. Then the features are learned by improved DBN. In the traditional methods, DBN is stacked with restricted Boltzmann machine (RBM) which is suitable for only binary value data. In the proposed framework, we used Gaussian–Bernoulli RBM which was constructed for real value data such as images. The experiments were carried out using Pavia University dataset. The results show that the proposed network has good performance in terms of classification accuracy and computation time.

Keywords

Deep Belief Network, Hyperspectral Image, Remote Sensing, Spatial–Spectral Classification, Superpixel Segmentation.
User
Notifications
Font Size

  • Khan, M. J., Khan, H. S., Yousaf, A., Khurshid, K. and Abbas, A., Modern trends in hyperspectral image analysis: a review. IEEE Access, 2018, 6, 14118–14129.

  • Massoudifar, P., Rangarajan, A. and Gader, P., Superpixel estimation for hyperspectral imagery. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2014, pp. 287–292; doi:10.1109/CVPRW.2014.51.

  • Felzenszwalb, P. F. and Huttenlocher, D. P., Efficient graph-based image segmentation. Int. J. Comput. Vis., 2004, 59, 167–181.

  • Levinshtein, A. et al., TurboPixels: fast superpixels using geometric flows. IEEE Trans. Pattern Anal. Mach. Intell., 2009, 31, 2290– 2297.

  • Achanta, R., Shaji, A., Smith, K. and Lucchi, A., SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans. Pattern Anal. Mach. Intell., 2012, 34, 2274–2282.

  • Liu, M. Y., Tuzel, O., Ramalingam, S. and Chellappa, R., Entropy rate superpixel segmentation. In Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2011, pp. 2097–2104; doi:10.1109/CVPR.2011.5995323.

  • Xie, F., Lei, C., Yang, J. and Jin, C., An effective classification scheme for hyperspectral image based on superpixel and discontinuity preserving relaxation. Remote Sensing, 2019, 11, 1149.

  • Hughes, G. F., On the mean accuracy of statistical pattern recognizers. IEEE Trans. Inf. Theory, 1968, 14, 55–63.

  • Prasad, S. and Bruce, L. M., Limitations of principal components analysis for hyperspectral target recognition. IEEE Geosci. Remote Sensing Lett., 2008, 5, 625–629.

  • Villa, A., Benediktsson, J. A., Chanussot, J. and Jutten, C., Hyperspectral image classification with independent component discriminant analysis. IEEE Trans. Geosci. Remote Sensing, 2011, 49, 4865–4876.

  • Liao, W., Pižurica, A., Scheunders, P., Philips, W. and Pi, Y., Semisupervised local discriminant analysis for feature extraction in hyperspectral images. IEEE Trans. Geosci. Remote Sensing, 2013, 51, 184–198.

  • Chen, Z., Jiang, J., Jiang, X., Fang, X. and Cai, Z., Spectral– spatial feature extraction of hyperspectral images based on propagation filter. Sensors (Switzerland), 2018, 18, 1–15.

  • Tu, B., Yang, X., Li, N., Ou, X. and He, W., Hyperspectral image classification via superpixel correlation coefficient representation. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sensing, 2018, 11, 4113–4127.

  • Kang, X., Li, S. and Benediktsson, J. A., Feature extraction of hyperspectral images with image fusion and recursive filtering. IEEE Trans. Geosci. Remote Sensing, 2014, 52, 3742–3752.

  • Chen, Z., Jiang, J., Zhou, C., Fu, S. and Cai, Z., SuperBF: superpixelbased bilateral filtering algorithm and its application in feature extraction of hyperspectral images. IEEE Access, 2019, 7, 147796–147807.

  • Melgani, F. and Bruzzone, L., Classification of hyperspectral remote sensing images with support vector machines. IEEE Trans. Geosci Remote Sensing, 2004, 42, 1778–1790.

  • Kang, X., Member, S., Li, S. and Benediktsson, J. A., Spectral – spatial hyperspectral image classification with edge-preserving filtering. IEEE Trans. Geosci. Remote Sensing, 2014, 52, 2666–2677.

  • Chen, Y., Jiang, H., Li, C., Jia, X. and Ghamisi, P., Deep feature extraction and classification of hyperspectral images based on convolutional neural networks. IEEE Trans. Geosci. Remote Sensing, 2016, 54, 6232–6251.

  • Chen, Y., Zhao, X. and Jia, X., Spectral–spatial classification of hyperspectral data based on deep belief network. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sensing, 2015, 8, 2381–2392.

  • Duan, W., Li, S. and Fang, L., Spectral-spatial hyperspectral image classification using superpixel and extreme learning machines. Commun. Comput. Inf. Sci., 2014, 483, 159–167.

  • Gastal, E. S. L. and Oliveira, M. M., Domain transform for edgeaware image and video processing. ACM Trans. Graph., 2011, 30, 1–12.

  • Hinton, G. E., Training products of experts by minimizing contrastive divergence. Neural Comput., 2002, 14, 1771–1800.

  • Cho, K. H., Raiko, T. and Ilin, A., Gaussian–Bernoulli deep Boltzmann machine. In Proceedings of the International Joint Conference on Neural Networks, 2013; doi:10.1109/IJCNN.2013.6706831.

  • Liu, P., Zhang, H. and Eom, K. B., Active deep learning for classification of hyperspectral images. IEEE J. Sel. Top. Appl. Earth Obs. Remote Sensing, 2017, 10, 712–724.

  • Hyperspectral remote sensing scenes; http://www.ehu.eus/ ccwintco/index.php/Hyperspectral_Remote_Sensing_Scenes (accessed on 6 June 2018).


Abstract Views: 350

PDF Views: 124




  • A Methodology for Unsupervised Feature Learning in Hyperspectral Imagery Using Deep Belief Network

Abstract Views: 350  |  PDF Views: 124

Authors

C. Sherin Shibi
Department of Electronics and Communication Engineering, Sri Venkateswara College of Engineering, Sriperumbudur 602 117, India
R. Gayathri
Department of Electronics and Communication Engineering, Sri Venkateswara College of Engineering, Sriperumbudur 602 117, India

Abstract


Deep learning approaches have received major interest in the field of remote sensing. Hyperspectral imaging has rich data that are distributed in multi-dimensions. It is challenging to apply deep learning algorithms due to the limited amount of labelled data. So, unsupervised feature extraction approaches are used to overcome this limitation. In this study, we propose an unsupervised feature learning approach using deep belief network (DBN). In the proposed framework, the input hyperspectral image is segmented using entropy rate superpixel segmentation and filtered by domain transform recursive filter which extracts spatial and spectral information effectively. Then the features are learned by improved DBN. In the traditional methods, DBN is stacked with restricted Boltzmann machine (RBM) which is suitable for only binary value data. In the proposed framework, we used Gaussian–Bernoulli RBM which was constructed for real value data such as images. The experiments were carried out using Pavia University dataset. The results show that the proposed network has good performance in terms of classification accuracy and computation time.

Keywords


Deep Belief Network, Hyperspectral Image, Remote Sensing, Spatial–Spectral Classification, Superpixel Segmentation.

References





DOI: https://doi.org/10.18520/cs%2Fv120%2Fi11%2F1705-1711