Stacked sparse autoencoder in hyperspectral data classification using spectral-spatial, higher order statistics and multifractal spectrum features

Infrared Physics and Technology

Volumn 86, Issue , 2017, Pages 77-89

  Wan, Xiaoqing ^a   Zhao, Chunhui ^a   Wang, Yanchun ^b   Liu, Wu ^a  

^a HARBIN ENGINEERING UNIVERSITY   (China)

^b QIQIHAR UNIVERSITY   (China)

Author keywords

Classification; Feature level fusion (FLF); Hyperspectral imagery; Random forest (RF); Stacked sparse autoencoder (SSA)

Indexed keywords

DECISION TREES; FRACTALS; HIGHER ORDER STATISTICS; LEARNING SYSTEMS; SPECTROSCOPY; SPECTRUM ANALYSIS;

AUTO ENCODERS; FEATURE LEVEL FUSION; HIGH-LEVEL FEATURES; HYPER-SPECTRAL IMAGERIES; HYPERSPECTRAL DATA CLASSIFICATION; MULTI-FRACTAL SPECTRUM; RANDOM FOREST CLASSIFIER; RANDOM FORESTS;

CLASSIFICATION (OF INFORMATION);

EID: 85028702520     PISSN: 13504495     EISSN: None     Source Type: Journal    
DOI: 10.1016/j.infrared.2017.08.021     Document Type: Article

References (40)

1. Bian, X., Zhang, X., Liu, R., Ma, L., Fu, X., Adaptive classification of hyperspectral images using local consistency. J. Electron. Imaging, 23, 2014, 10.1117/1.JEI.23.6.063014 063014–063014.
2. Shen, L., Jia, S., Three-dimensional Gabor wavelets for pixel-based hyperspectral imagery classification. IEEE Trans. Geosci. Rem. Sens. 49 (2011), 5039–5046, 10.1109/TGRS.2011.2157166.
3. Wang, Z., Nasrabadi, N.M., Huang, T.S., Spatial-spectral classification of hyperspectral images using discriminative dictionary designed by learning vector quantization. IEEE Trans. Geosci. Rem. Sens. 52 (2014), 4808–4822, 10.1109/TGRS. 2013. 2285049.
4. M. Toshniwal, An optimized approach to application of neural networks to classification of multispectral, remote sensing data, in: IEEE International Conference on Networking, Sensing and Control, 2005, pp. 235–240. 10.1109/ICNSC.2005.1461193.
5. Ham, J., Chen, Y., Crawford, M.M., Ghosh, J., Investigation of the random forest framework for classification of hyperspectral data. IEEE Trans. Geosci. Rem. Sens. 43 (2005), 492–501, 10.1109/TGRS.2004.842481.
6. Du, Q., Chang, C.I., A linear constrained distance-based discriminant analysis for hyperspectral image classification. Pattern Recogn. 34 (2001), 361–373.
7. Perkins, S.J., Harvey, N.R., Brumby, S.P., Support vector machines for broad-area feature classification in remotely sensed images. Int. Soc. Opt. Eng. 4381 (2001), 286–295.
8. Pal, M., Mather, P.M., Assessment of the effectiveness of support vector machines for hyperspectral data. Fut. Gener. Comput. Syst. 20 (2004), 1215–1225, 10.1016/j.future.2003.11.011.
9. Fauvel, M., Benediktsson, J.A., Chanussot, J., Sveinsson, J.R., Spectral and spatial classification of hyperspectral data using SVMs and morphological profiles. IEEE Trans. Geosci. Rem. Sens. 46 (2007), 3804–3814, 10.1109/TGRS. 2008.922034.
10. Z. He, Y. Shen, M. Zhang, Q. Wang, Spectral-spatial hyperspectral image classification via SVM and superpixel segmentation, in: IEEE Instrumentation and Measurement Technology Conference, 2014, pp. 422–427. 10.1109/I2MTC.2014.6860780.
11. Sahadevan, A.S., Routray, A., Das, B.S., Ahmad, S., Hyperspectral image preprocessing with bilateral filter for improving the classification accuracy of support vector machines. J. Appl. Rem. Sens. 10 (2016), 2–17, 10.1117/1.JRS.10.025004.
12. Zhang, Y., Tian, X., Ren, P., An adaptive bilateral filter based framework for image denoising. Neurocomputing 140 (2014), 299–316, 10.1016/j.neucom.2014.03.008.
13. Chen, S., Shi, W., Zhang, W., An efficient universal noise removal algorithm combining spatial gradient and impulse statistic. Math. Prob. Eng. 2013 (2013), 14–26, 10.1155/2013/480274.
14. Swami, P.D., Jain, A., Image denoising by supervised adaptive fusion of decomposed images restored using wave atom, curvelet and wavelet transform. SIViP 8 (2014), 443–459, 10.1007/s11760-012-0343-z.
15. Du, Y., Liu, G., Feng, G., Chen, Z., Speckle reduction in optical coherence tomography images based on wave atoms. J. Biomed. Opt. 19 (2014), 1–7, 10.1117/1. JBO.19.5.056009.
16. Villa, A., Chanussot, J., Benediktsson, J.A., Jutten, C., Dambreville, R., Unsupervised methods for the classification of hyperspectral images with low spatial resolution. Pattern Recogn. 46 (2013), 1556–15687, 10.1016/j.patcog. 2012.10.030.
17. Iordache, M.D., Bioucas-Dias, J.M., Plaza, A., Total variation spatial regularization for sparse hyperspectral unmixing. IEEE Trans. Geosci. Rem. Sens. 50 (2012), 4484–4502, 10.1109/TGRS.2012.2191590.
18. Shahid, S., Walker, J., Lyons, G.M., Byrne, C.A., Nene, A.V., Application of higher order statistics techniques to EMG signals to characterize the motor unit action potential. IEEE Trans. Biomed. Eng. 52 (2005), 1195–1209, 10.1109/TBME. 2005. 847525.
19. Chua, K.C., Chandran, V., Acharya, U.R., Lim, C.M., Application of higher order statistics/spectra in biomedical signals-a review. Med. Eng. Phys. 32 (2010), 679–689, 10.1016/j.medengphy. 2010.04.009.
20. Shrivastava, V.K., Londhe, N.D., Sonawane, R.S., Suri, J.S., Computer-aided diagnosis of psoriasis skin images with HOS, texture and color features: a first comparative study of its kind. Comput. Methods Prog. Biomed. 126 (2016), 98–109, 10.1016/j.cmpb.2015.11.013.
21. Acharya, U.R., Chua, C.K., Ng, E.Y., Yu, W., Chee, C., Application of higher order spectra for the identification of diabetes retinopathy stages. J. Med. Syst. 32 (2008), 481–488, 10.1007/s10916-008-9154-8.
22. Falconer, K., Techniques in Fractal Geometry. 1997, John Wiley and Sons Ltd., New York.
23. Xiong, G., Zhang, S., Liu, Q., The time-singularity multifractal spectrum distribution. Phys. A Stat. Mech. Appl. 391 (2012), 4727–4739, 10.1016/j.physa.2012.05. 026.
24. G. Wang, J. Ning, Q. Zhang, W. Liu, L. Tang, Multifractal spectrum analysis on microscope image of eutectic carbides by a quadratic function fitting, in: International Joint Conference on Inc, IEEE Computer Society, 2009, pp. 1623–1627. 10.1109/NCM.2009.291.
25. Li, N., Zhao, H., Huang, P., Jia, G., Bai, X., A novel logistic multi-class supervised classification model based on multi-fractal spectrum parameters for hyperspectral data. Int. J. Comput. Math. 92 (2014), 1–14, 10.1080/00207160.2014.915957.
26. Yu, L., Qi, D., Applying multifractal spectrum combined with fractal discrete brownian motion model to wood defects recognition for sawing. Wood Sci. Technol. 45 (2011), 511–519, 10.1007/s00226-010-0341-7.
27. Hinton, G.E., Osindero, S., The, Y.W., A fast learning algorithm for deep belief nets. Neural Comput. 18 (1960), 1527–1554.
28. Lenz, I., Lee, H., Saxena, A., Deep learning for detecting robotic grasps. Int. J. Robot. Res. 34 (2013), 705–724, 10.1177/0278364914549607.
29. Guo, Y., Gao, Y., Shen, D., Deformable MR prostate segmentation via deep feature learning and sparse patch matching. IEEE Trans. Med. Imaging 35 (2015), 1077–1089, 10.1109/TMI.2015. 2508280.
30. Chen, Y., Lin, Z., Zhao, X., Wang, G., Gu, Y., Deep learning-based classification of hyperspectral data. IEEE J. Sel. Top. Appl. Earth Obs. Rem. Sens. 7 (2014), 2094–2107, 10.1109/JSTARS.2014.2329330.
31. Romero, A., Gatta, C., Camps-Valls, G., Unsupervised deep feature extraction for remote sensing image classification. IEEE Trans. Geosci. Rem. Sens. 54 (2015), 1–14, 10.1109/TGRS. 2015.2478379.
32. Demanet, L., Ying, L., Wave atoms and sparsity of oscillatory patterns. Appl. Comput. Harmon. Anal. 23 (2007), 368–387, 10.1016/j.acha.2007.03.003.
33. C. Tomasi, R. Manduchi, Bilateral filtering for gray and color images, in: IEEE International Conference on Computer Vision, 1998, pp. 839–846.
34. Chandran, V., Elgar, S.L., Pattern recognition using invariants defined from higher order spectra-one dimensional inputs. IEEE Trans. Sign. Process. 41 (1993), 205–212.
35. T.T. Ng, S.F. Chang, Q. Sun, Blind detection of photomontage using higher order statistics, in: IEEE International Symposium on Circuits and Systems, vol. 5, 2004, pp. 688–691. 10.1109/ISCAS.2004.1329901.
36. Zhang, J.W., Zheng, C.X., Xie, A., Bispectrum analysis of focal ischemic cerebral EEG signal using third-order recursion method. IEEE Trans. Biomed. Eng. 47 (2000), 352–359, 10.1109/10.827210.1109/10.82729696.
37. Chua, K.C., Chandran, V., Acharya, U.R., Lim, C.M., Cardiac state diagnosis using higher order spectra of heart rate variability. J. Med. Eng. Technol. 32 (2009), 145–155, 10.1080/03091900601050862.
38. Zhou, S.M., Gan, J.Q., Sepulveda, F., Classifying mental tasks based on features of higher-order statistics from EEG signals in brain-computer interface. Inf. Sci. 178 (2008), 1629–1640, 10.1016/j.ins.2007.11.012.
39. Xu, J., Xiang, L., Liu, Q., Gilmore, H., Wu, J., Tang, J., Madabhushi, A., Stacked sparse autoencoder (SSAE) for nuclei detection on breast cancer histopathology images. IEEE Trans. Med. Imaging 35 (2015), 119–130, 10.1109/TMI. 2015. 2458702.
40. Tao, C., Pan, H., Li, Y., Zou, Z., Unsupervised spectral-spatial feature learning with stacked sparse autoencoder for hyperspectral imagery classification. IEEE Geosci. Rem. Sens. Lett. 12 (2015), 2438–2442, 10.1109/LGRS.2015.2482520.