Soft Computing

, Volume 21, Issue 23, pp 7053–7065 | Cite as

SVM or deep learning? A comparative study on remote sensing image classification

  • Peng Liu
  • Kim-Kwang Raymond Choo
  • Lizhe Wang
  • Fang Huang
Methodologies and Application


With constant advancements in remote sensing technologies resulting in higher image resolution, there is a corresponding need to be able to mine useful data and information from remote sensing images. In this paper, we study auto-encoder (SAE) and support vector machine (SVM), and to examine their sensitivity, we include additional umber of training samples using the active learning frame. We then conduct a comparative evaluation. When classifying remote sensing images, SVM can also perform better than SAE in some circumstances, and active learning schemes can be used to achieve high classification accuracy in both methods.


Spatial big data Sparse auto-encoder Support vector machine Active learning Remote sensing 



This study is supported by the National Natural Science Foundation of China (No. 41471368 and No. 41571413).

Compliance with ethical standards

Conflict of interest

All authors declare that they have no conflict of interest.

Ethical standard

This article does not contain any studies with human participants or animals performed by any of the authors.


  1. Bengio Yoshua, Lamblin Pascal, Popovici Dan, Larochelle Hugo (2007) Greedy layer-wise training of deep networks. Adv Neural Inf Process Syst 19:153Google Scholar
  2. Burges Christopher JC (1998) A tutorial on support vector machines for pattern recognition. Data Min Knowl Discov 2(2):121–167CrossRefGoogle Scholar
  3. Chen S, Wang H, Xu F, Jin YQ (2016) Target classification using the deep convolutional networks for sar images. IEEE Trans Geosci Remote Sens 54(8):4806–4817Google Scholar
  4. Ciodaro T, Deva D, De Seixas JM and Damazio D (2012) Online particle detection with neural networks based on topological calorimetry information. In: Journal of physics: conference series, vol 368, p 012–030. IOP PublishingGoogle Scholar
  5. Collobert Ronan, Weston Jason, Bottou Léon, Karlen Michael, Kavukcuoglu Koray, Kuksa Pavel (2011) Natural language processing (almost) from scratch. J Mach Learn Res 12:2493–2537zbMATHGoogle Scholar
  6. Farabet Clement, Couprie Camille, Najman Laurent, LeCun Yann (2013) Learning hierarchical features for scene labeling. IEEE Trans Pattern Anal Mach Intell 35(8):1915–1929CrossRefGoogle Scholar
  7. Han J, Zhang D, Cheng G, Guo L, Ren J (2015) Object detection in optical remote sensing images based on weakly supervised learning and high-level feature learning. IEEE Trans Geosci Remote Sens 53(6):3325–3337CrossRefGoogle Scholar
  8. Helmstaedter Moritz, Briggman Kevin L, Turaga Srinivas C, Jain Viren, Seung H Sebastian, Denk Winfried (2013) Connectomic reconstruction of the inner plexiform layer in the mouse retina. Nature 500(7461):168–174CrossRefGoogle Scholar
  9. Hinton Geoffrey, Deng Li, Dong Yu, Dahl George E, Mohamed Abdel-rahman, Jaitly Navdeep, Senior Andrew, Vanhoucke Vincent, Nguyen Patrick, Sainath Tara N et al (2012) Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups. Signal Process Mag, IEEE 29(6):82–97CrossRefGoogle Scholar
  10. Hinton RR, Salakhutdinov GE (2006) Reducing the dimensionality of data with neural networks. Science 313(5786):504–507CrossRefzbMATHMathSciNetGoogle Scholar
  11. Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Advances in neural information processing systems (NIPS’12), pp 1097–1105Google Scholar
  12. LeCun Yann, Bengio Yoshua, Hinton Geoffrey (2015) Deep learning. Nature 521(7553):436–444CrossRefGoogle Scholar
  13. Leung Michael KK, Xiong Hui Yuan, Lee Leo J, Frey Brendan J (2014) Deep learning of the tissue-regulated splicing code. Bioinformatics 30(12):i121–i129CrossRefGoogle Scholar
  14. Ma Junshui, Sheridan Robert P, Liaw Andy, Dahl George E, Svetnik Vladimir (2015) Deep neural nets as a method for quantitative structure-activity relationships. J Chem Inf Model 55(2):263–274CrossRefGoogle Scholar
  15. McCulloch Warren S, Pitts Walter (1943) A logical calculus of the ideas immanent in nervous activity. Bull Math Biophys 5(4):115–133CrossRefzbMATHMathSciNetGoogle Scholar
  16. Melgani Farid, Bruzzone Lorenzo (2004) Classification of hyperspectral remote sensing images with support vector machines. IEEE Trans Geosci Remote Sens 42(8):1778–1790CrossRefGoogle Scholar
  17. Mikolov Tomáš, Deoras Anoop, Povey Daniel, Burget Lukáš and Černockỳ Jan (2011) Strategies for training large scale neural network language models. In Automatic speech recognition and understanding (ASRU) IEEE workshop on, pp 196–201Google Scholar
  18. Nguyen A, Yosinski J and Clune J (2015) Deep neural networks are easily fooled: High confidence predictions for unrecognizable images. In 2015 IEEE conference on computer vision and pattern recognition (CVPR). pp 427–436, JuneGoogle Scholar
  19. Omer G, Mutanga O, Abdel-Rahman EM, Adam E (2015) Performance of support vector machines and artificial neural network for mapping endangered tree species using worldview-2 data in dukuduku forest, south africa. IEEE J Sel Top Appl Earth Obs Remote Sens 8(10):4825–4840CrossRefGoogle Scholar
  20. Romero A, Gatta C, Camps-Valls G (2016) Unsupervised deep feature extraction for remote sensing image classification. IEEE Trans Geosci Remote Sens 54(3):1349–1362Google Scholar
  21. Sainath Tara N, Mohamed Abdel-rahman, Kingsbury Brian and Ramabhadran Bhuvana (2013) Deep convolutional neural networks for lvcsr. In Acoustics, speech and signal processing (ICASSP), 2013 IEEE international conference on, pp 8614–8618Google Scholar
  22. Sarikaya Ruhi, Hinton Geoffrey E, Deoras Anoop (2014) Application of deep belief networks for natural language understanding. IEEE/ACM Trans Audio, Speech Lang Process 22(4):778–784CrossRefGoogle Scholar
  23. Shawe-Taylor J, Cristianini N (2004) Kernel methods for pattern analysis. Cambridge University Press, CambridgeGoogle Scholar
  24. Sutskever Ilya, Martens James, Dahl George and Hinton Geoffrey (2013) On the importance of initialization and momentum in deep learning. In Proceedings of the 30th international conference on machine learning (ICML-13), pp 1139–1147Google Scholar
  25. Sutskever I, Vinyals O, Le QV (2014) Sequence to sequence learning with neural networks. In: Advances in neural information processing systems NIPS’14, pp 3104–3112Google Scholar
  26. Tang J, Deng C, Huang GB, Zhao B (2015) Compressed-domain ship detection on spaceborne optical image using deep neural network and extreme learning machine. IEEE Trans Geosci Remote Sens 53(3):1174–1185CrossRefGoogle Scholar
  27. Tompson JJ, Jain A, LeCun Y, Bregler C (2014) Joint training of a convolutional network and a graphical model for human pose estimation. In: Advances in neural information processing systems (NIPS’14), 1799–1807Google Scholar
  28. Tsai C.-Y., Cox D. Are deep learning algorithms easily hackable?
  29. Tuia Devis, Volpi Michele, Copa Loris, Kanevski Mikhail, Munoz-Mari Jordi (2011) A survey of active learning algorithms for supervised remote sensing image classification. IEEE J Sel Topics Signal Process 5(3):606–617CrossRefGoogle Scholar
  30. Vapnik Vladimir (2013) The nature of statistical learning theory. Springer Science & Business Media, BerlinzbMATHGoogle Scholar
  31. Vincent Pascal, Larochelle Hugo, Bengio Yoshua, and Manzagol Pierre-Antoine (2008) Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th international conference on machine learning - ICML ’08, 1096–1103Google Scholar
  32. Yu Y, Li J, Guan H, Wang C (2016) Automated detection of three-dimensional cars in mobile laser scanning point clouds using dbm-hough-forests. IEEE Trans Geosci Remote Sens 54(7):4130–4142Google Scholar
  33. Zhang F, Du B, Zhang L (2016) Scene classification via a gradient boosting random convolutional network framework. IEEE Trans Geosci Remote Sens 54(3):1793–1802CrossRefGoogle Scholar
  34. Zhao W, Du S (2016) Spectral-spatial feature extraction for hyperspectral image classification: a dimension reduction and deep learning approach. IEEE Trans Geosci Remote Sens 54(8):4544–4554Google Scholar

Copyright information

© Springer-Verlag Berlin Heidelberg 2016

Authors and Affiliations

  • Peng Liu
    • 1
  • Kim-Kwang Raymond Choo
    • 3
  • Lizhe Wang
    • 1
    • 2
  • Fang Huang
    • 4
  1. 1.Institute of Remote Sensing and Digital EarthChinese Academy of SciencesBeijingPeople’s Republic of China
  2. 2.School of Computer Science China University of GeoscienceWuhanPeople’s Republic of China
  3. 3.School of Information Technology and Mathematical SciencesUniversity of South AustraliaAdelaideAustralia
  4. 4.School of Resources and EnvironmentUniversity of Electronic Science and Technology of ChinaChengduPeople’s Republic of China

Personalised recommendations