Abstract
Hyperspectral Image (HSI) classification is one of the fundamental tasks in the field of remote sensing data analysis. CNN (Convolutional Neural Network) has been proven to be an effective deep learning model, which can extract high-level features directly from the raw data and thereby utilize rich information contained in HSI data. However, labor cost to label enough HIS data for training model is usually expensive, so that it is a strong demand of utilizing limited training data to get a satisfied classification accuracy. In this paper, we put forward a deep cube CNN model – DCNR, which is composed of a cube neighbor HSI pixels strategy, a deep CNN and a random forest classifier. In DCNR model, cubic samples, containing spectral-spatial information, are generated by putting each target pixel and its neighbors together. Then features with high representative ability, extracted by applying a specially designed cube CNN model on each cubic sample, are fed into the random forest classifier for the classification of the target pixel. Results show that DCNR model can achieve classification accuracy of 96.78%, 96.08% and 94.85% on KSC, IP and SA datasets respectively with 20% samples as training set, and 85.03%, 83.45 and 62.17% on KSC, IP and SA datasets respectively with only 1% samples as training set, significantly outperforming random forest and cube CNN models.
Similar content being viewed by others
References
Alsmirat MA, Jararweh Y, Al-Ayyoub M et al (2017) Accelerating compute intensive medical imaging segmentation algorithms using hybrid CPU-GPU implementations[J]. Multimed Tools Appl 76(3):3537–3555
AlZain MA, Li AS, Soh B, Pardede E (2015) Multi-cloud data management using Shamir's secret sharing and quantum byzantine agreement schemes[J]. Int J Cloud Appl Comput (IJCAC) 5(3):35–52
Atawneh S, Almomani A, Al Bazar H et al (2017) Secure and imperceptible digital image steganographic algorithm based on diamond encoding in DWT domain[J]. Multimed Tools Appl 76(18):18451–18472
Bergstra J, Breuleux O, Bastien F, et al. (2010) Theano: a CPU and GPU math compiler in Python[C]//proc. 9th Python in Science Conf : 1–7
Bioucas-Dias JM, Plaza A, Camps-Valls G et al (2013) Hyperspectral remote sensing data analysis and future challenges[J]. Geosci Remote Sens Mag, IEEE 1(2):6–36
Camps-Valls G, Bruzzone L (2005) Kernel-based methods for hyperspectral image classification[J]. IEEE Trans Geosci Remote Sens 43(6):1351–1362
Camps-Valls G, Tuia D, Bruzzone L et al (2013) Advances in hyperspectral image classification: earth monitoring with statistical learning methods[J]. IEEE Signal Process Mag 31(1):45–54
Chan W, Jaitly N, Le Q et al. (2016) Listen, attend and spell: a neural network for large vocabulary conversational speech recognition[C]//acoustics, speech and signal processing (ICASSP). 2016 I.E. Int Conf. IEEE: 4960–4964
Chang X, Ma Z, Lin M, Yang Y, Hauptmann AG (2017) Feature interaction augmented sparse learning for fast kinect motion detection[J]. IEEE Trans Image Process 26(8):3911–3920
Chang X, Ma Z, Yang Y, Zeng Z, Hauptmann AG (2017) Bi-level semantic representation analysis for multimedia event detection[J]. IEEE transactions on cybernetics 47(5):1180–1197
Chang X, Yang Y (2017) Semisupervised feature analysis by mining correlations among multiple tasks[J]. IEEE Trans Neural Netwrks Learn Syst 28(10):2294–2305
Chang X, Yu YL, Yang Y, Xing EP (2017) Semantic pooling for complex event analysis in untrimmed videos[J]. IEEE Trans Pattern Anal Mach Intell 39(8):1617–1632
Chen Y, Lin Z, Zhao X, Wang G, Gu Y (2014) Deep learning-based classification of hyperspectral data[J]. IEEE J Select Top Appl Earth Observ Remote Sens 7(6):2094–2107
Chen Y, Zhao X, Jia X (2015) Spectral–spatial classification of hyperspectral data based on deep belief network[J]. IEEE J Select Top Appl Earth Observ Remote Sens 8(6):2381–2392
Gu J, Wang Z, Kuen J, et al. (2015) Recent advances in convolutional neural networks[J]. Comput Sci
Gupta S, Gupta BB (2018) XSS-secure as a service for the platforms of online social network-based multimedia web applications in cloud[J]. Multimed Tools Appl 77(4):4829–4861
Ham J, Chen Y, Crawford MM et al (2005) Investigation of the random forest framework for classification of hyperspectral data[J]. IEEE Trans Geosci Remote Sens 43(3):492–501
Harsanyi JC, Chang CI (1994) Hyperspectral image classification and dimensionality reduction: an orthogonal subspace projection approach[J]. IEEE Trans Geosci Remote Sens 32(4):779–785
Heaton JB, Polson NG, Witte JH (2017) Deep learning for finance: deep portfolios[J]. Appl Stoch Model Bus Ind 33(1):3–12
Hu W, Huang Y, Wei L et al. (2015) Deep convolutional neural networks for hyperspectral image classification[J]. J Sens: 2015
IGI Global (2016) Handbook of research on modern cryptographic solutions for computer and cyber security[M]
Jararweh Y, Al-Ayyoub M, Fakirah M, et al. (2017) Improving the performance of the needleman-wunsch algorithm using parallelization and vectorization techniques[J]. Multimed Tools Appl: 1–17
Kang X, Li S, Benediktsson JA (2014) Spectral–spatial hyperspectral image classification with edge-preserving filtering[J]. IEEE Trans Geosci Remote Sens 52(5):2666–2677
Kim Y (2014) Convolutional neural networks for sentence classification[J]. arXiv preprint arXiv:1408.5882
Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks[C]//. Adv Neural Inf Proces Syst: 1097–1105
LeCun Y, Bengio Y, Hinton G (2015) Deep learning[J]. Nature 521(7553):436–444
Leng J, Li T, Bai G, et al. (2016) Cube-CNN-SVM: a novel hyperspectral image classification method[C]//tools with artificial intelligence (ICTAI). 2016 I.E. 28th Int Conf. IEEE: 1027–1034
Li J, Huang X, Gamba P, Bioucas-Dias JMB, Zhang L, Benediktsson JA, Plaza A (2015) Multiple feature learning for hyperspectral image classification[J]. IEEE Trans Geosci Remote Sens 53(3):1592–1606
Li Y, Peng Z, Liang D, Chang H, Cai Z (2016) Facial age estimation by using stacked feature composition and selection. Vis Comput 32(12):1525–1536. https://doi.org/10.1007/s00371-015-1137-4
Li W, Prasad S, Fowler JE, Bruce LM (2011) Locality-preserving discriminant analysis in kernel-induced feature spaces for hyperspectral image classification[J]. IEEE Geosci Remote Sens Lett 8(5):894–898
Li Y, Wang G, Nie L, Wang Q, Tan W (2018) Distance metric optimization driven convolutional neural network for age invariant face recognition[J]. Pattern Recogn 75:51–62. https://doi.org/10.1016/j.patcog.2017.10.015
Liaw A, Wiener M (2002) Classification and regression by random forest[J]. R News 2(3):18–22
Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M, van der Laak JAWM, van Ginneken B, Sánchez CI (2017) A survey on deep learning in medical image analysis[J]. Med Image Anal 42:60–88
Maggiori E, Tarabalka Y, Charpiat G, Alliez P (2017) Convolutional neural networks for large-scale remote-sensing image classification[J]. IEEE Trans Geosci Remote Sens 55(2):645–657
Mairal J, Bach F, Ponce J et al. (2009) Online dictionary learning for sparse coding[C]//. Int Conf Mach Learn, ICML 2009, Montreal, Quebec, Canada, June. DBLP:689–696
Majumder N, Poria S, Gelbukh A, Cambria E (2017) Deep learning-based document modeling for personality detection from text[J]. IEEE Intell Syst 32(2):74–79
Nair V, Hinton G E. (2010) Rectified linear units improve restricted Boltzmann machines[C]//. Int Conf Mach Learn. DBLP, 807–814
Qi CR, Su H, Mo K et al (2017) Pointnet: deep learning on point sets for 3d classification and segmentation[J]. Proc Comput Vision Pattern Recogn (CVPR), IEEE 1(2):4
Quang D, Xie X, Dan Q (2016) A hybrid convolutional and recurrent deep neural network for quantifying the function of DNA sequences[J]. Nucleic Acids Res 44(11):e107
Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition[J]. arXiv preprint arXiv:1409.1556,
Vincent P, Larochelle H, Bengio Y et al. (2008) Extracting and composing robust features with denoising autoencoders[C]//. Int Conf :1096–1103
Vincent P, Larochelle H, Lajoie I et al (2010) Stacked denoising autoencoders: learning useful representations in a deep network with a local denoising criterion.[J]. J Mach Learn Res 11(12):3371–3408
Wang K, Zhang D, Ya L, Zhang R, Lin L (2017) Cost-effective active learning for deep image classification. IEEE Trans Circ Syst Video Technol (T-CSVT) 27(12):2591–2600
Xia J, Du P, He X et al (2014) Hyperspectral remote sensing image classification based on rotation forest[J]. IEEE Geosci Remote Sens Lett 11(1):239–243
Xie L, Li G, Xiao M, Peng L, Chen Q (2017) Hyperspectral image classification using discrete space model and support vector machines[J]. IEEE Geosci Remote Sens Lett 14(3):374–378
Yuan C, Li X, Wu QMJ et al (2017) Fingerprint liveness detection from different fingerprint materials using convolutional neural network and principal component analysis[J].CMC: computers. Mater Continua 53(3):357–371. https://doi.org/10.3970/cmc.2017.053.357
Zeng S, Bai J, Jiang L, et al. (2017) Multiple kernel fuzzy discriminant analysis for hyperspectral imaging classification[C]//fuzzy systems (FUZZ-IEEE). 2017 I.E. Int Conf IEEE: 1–6
Zhang L, Zhang L, Tao D, Huang X (2012) On combining multiple features for hyperspectral remote sensing image classification[J]. IEEE Trans Geosci Remote Sens 50(3):879–893
Zhao W, Du S (2016) Spectral–spatial feature extraction for hyperspectral image classification: a dimension reduction and deep learning approach[J]. IEEE Trans Geosci Remote Sens 54(8):4544–4554
Funding
This study was funded by the Natural Science Foundation of Tianjin under Grant No. 16JCYBJC15200, the Major Science and Technology Program of Big Data and Cloud Computing of Tianjin No. 15ZXDSGX00020, the Science and Technology Commission of Tianjin Binhai New Area No. BHXQKJXM-PT-ZJSHJ-2017005, the National Key Research and Development Program of China (2016YFC0400709), and the Fundamental Research Funds for the Central Universities.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Conflict of interest
The authors declare that they have no conflict of interest.
Rights and permissions
About this article
Cite this article
Li, T., Leng, J., Kong, L. et al. DCNR: deep cube CNN with random forest for hyperspectral image classification. Multimed Tools Appl 78, 3411–3433 (2019). https://doi.org/10.1007/s11042-018-5986-5
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11042-018-5986-5