Advertisement

Multimedia Tools and Applications

, Volume 77, Issue 17, pp 21847–21860 | Cite as

FDCNet: filtering deep convolutional network for marine organism classification

  • Huimin Lu
  • Yujie Li
  • Tomoki Uemura
  • Zongyuan Ge
  • Xing Xu
  • Li He
  • Seiichi Serikawa
  • Hyoungseop Kim
Article

Abstract

Convolutional networks are currently the most popular computer vision methods for a wide variety of applications in multimedia research fields. Most recent methods have focused on solving problems with natural images and usually use a training database, such as Imagenet or Openimage, to detect the characteristics of the objects. However, in practical applications, training samples are difficult to acquire. In this study, we develop a powerful approach that can accurately learn marine organisms. The proposed filtering deep convolutional network (FDCNet) classifies deep-sea objects better than state-of-the-art classification methods, such as AlexNet, GoogLeNet, ResNet50, and ResNet101. The classification accuracy of the proposed FDCNet method is 1.8%, 2.9%, 2.0%, and 1.0% better than AlexNet, GooLeNet, ResNet50, and ResNet101, respectively. In addition, we have built the first marine organism database, Kyutech10K, with seven categories (i.e., shrimp, squid, crab, shark, sea urchin, manganese, and sand).

Keywords

Filtering deep convolutional network Marine organism classification Artificial intelligence Deep learning 

Notes

Acknowledgements

This work was supported by JSPS KAKENHI (15F15077, JSPS KAKENHI Grant Number 15 K12562, 15F15077, 16H05913), Leading Initiative for Excellent Young Researcher (LEADER) of Ministry of Education, Culture, Sports, Science and Technology-Japan (16809746), Open Research Fund of the Key Laboratory of Marine Geology and Environment in Chinese Academy of Sciences (No.MGE2015KG02), Research Fund of State Key Laboratory of Marine Geology in Tongji University (1608), Research Fund of State Key Laboratory of Ocean Engineering in Shanghai Jiaotong University (1301; 1510).

Reference

  1. 1.
    Arora S, Bhaskara A, Ge R, and Ma T (2013) Provable bounds for learning some deep representations, CoRR, abs/1310.6343Google Scholar
  2. 2.
    Bell R, Koren Y (2007) Lessons from the Netflix prize challenge. ACM SIGKDD Explorations Newsletter 9(2):75–79CrossRefGoogle Scholar
  3. 3.
    Chiang JY, Chen YC (2012) Underwater image enhancement by wavelength compensation and dehazing. IEEE Trans Image Process 21(4):1756–1769MathSciNetCrossRefMATHGoogle Scholar
  4. 4.
    Deza E, and Deza M, Encyclopedia of distances Springer book, pp.1–583Google Scholar
  5. 5.
    Dong C, Loy C, He K, and Tang X 2014 Learning a deep convolutional network for image super-resolution,” In Computer Vision –ECCV, pp.184–199Google Scholar
  6. 6.
    Fattal R (2014) Dehazing using color-lines. ACM Trans Graphics 34(1):1–10CrossRefGoogle Scholar
  7. 7.
    Gibson KB, Vo DT, Nguyen TQ (2012) An investigation of dehazing effects on image and video coding. IEEE Trans Image Process 21(2):662–673MathSciNetCrossRefMATHGoogle Scholar
  8. 8.
    Girshick R, Donahue J, Darrell T and Malik J 2014 Rich feature hierarchies for accurate object detection and semantic segmentation, In Proc. Of IEEE Conf Comput Vis Pattern RecognitGoogle Scholar
  9. 9.
    He K, Sun J, Tang X (2011) Single image haze removal using dark channel prior. IEEE Trans Pattern Anal Mach Intell 33(12):2341–2353CrossRefGoogle Scholar
  10. 10.
    He K, Zhang X, Ren S, Sun J, (2016) Deep residual learning for image recognition In Proc. Of IEEE Conf Comput Vis Pattern Recognit, pp.1–12Google Scholar
  11. 11.
    Joachims T (2006) Training linear SVMs in linear time, In Proc Of ACM KDD pp.1–10Google Scholar
  12. 12.
    Karpathy A, Toderici G, Shetty S, Leung T, Sukthankar R, and Li F, 2014 Large-scale video classification with convolutional neural networks, In Proc Of IEEE Conf Comput Vis Pattern Recognit, pp.1725–1732Google Scholar
  13. 13.
    LeCun Y, Boser B, Denker J, Henderson D, Howard R, Hubbard W, Jackel L (1989) Backpropagation applied to handwritten zip code recognition. Neural Comput 1(4):541–551CrossRefGoogle Scholar
  14. 14.
    Lee Y, Gibson K, Lee Z, and Nguyen T, (2014) Stereo image defogging, In Proc. of IEEE ICIP, pp.5427–5431Google Scholar
  15. 15.
    Li Y, Lu H, Li J, Li X, Li Y, Serikawa S (2016) Underwater image de-scattering and classification by deep neural network. Comput Electr Eng 54:68–77CrossRefGoogle Scholar
  16. 16.
    Liu F, Shen C, Lin G, Reid I (2016) Learning depth from single monocular images using deep convolutional neural fields. IEEE Trans Pattern Anal Mach Intell 38(10):2024–2039CrossRefGoogle Scholar
  17. 17.
    Long J, Shelhamer E, and Darrel T 2015 Fully convolutional networks for semantic segmentation, In Proc. Of IEEE Conf Comput Vis Pattern Recognit, pp.3431–3440Google Scholar
  18. 18.
    Lu H, Li Y, Zhang L, Serikawa S (2015a) Contrast enhancement for images in turbid water. Journal of Optical Society of America A 32(5):886–893CrossRefGoogle Scholar
  19. 19.
    Lu H, Li Y, and Serikawa S (2015b) Single underwater image descattering and color correction, In Proc. of IEEE Acoust Speech Signal Process, pp.1–5Google Scholar
  20. 20.
    Lu H, Li B, Zhu J, Li Y, Li Y, He L, Li J, and Serikawa S 2016a Wound intensity correction and segmentation with convolutional neural networks, Concurrency Comput: Prac Experience, pp.1–10Google Scholar
  21. 21.
    Lu H, Li Y, Nakashima S, Serikawa S (2016b) Turbidity underwater image restoration using spectral properties and light compensation. IEICE Trans Inf Syst E99D(1):219–227CrossRefGoogle Scholar
  22. 22.
    Maji S, Berg A, Malik J (2013) Efficient classification for additive kernel SVMs. IEEE Trans Pattern Anal Mach Intell 35(1):66–77CrossRefGoogle Scholar
  23. 23.
    Nicholas C-B, Anush M, and Eustice RM (2010) Initial results in underwater single image dehazing, In Proc. of IEEE OCEANS, pp. 1–8Google Scholar
  24. 24.
    Ren J, and Xu L 2015 On vectorization of deep convolutional neural networks for vision tasks, In Proc Of AAAI Artif Intell, pp.1840–1846Google Scholar
  25. 25.
    Serikawa S, Lu H (2014) Underwater image dehazing using joint trilateral filter. Computers & Electrical Engineering 40(1):41–50CrossRefGoogle Scholar
  26. 26.
    Simonyan K, and Zisserman A (2015) Very deep convolutional networks for large-scale image recognition, In Proc. Of IEEE ICLR2015, pp.1–14Google Scholar
  27. 27.
    Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A 2015 Going deeper with convolutions, In Proc. Of IEEE Conf Comput Vis Pattern Recognit, pp.1–12Google Scholar
  28. 28.
    Tarel J-P, Hautiere N, Caraffa L, Cord A, Halmaoui H, Gruyer D (2012) Vision enhancement in homogeneous and heterogeneous fog. IEEE Intell Transp Syst Mag 4(2):6–20CrossRefGoogle Scholar
  29. 29.
    Toshev A and Szegedy C Deeppose: human pose estimation via deep neural networks, In Proc. Of IEEE Conf Comput Vis Pattern Recognit, pp.1653–1660, 2014Google Scholar
  30. 30.
    Wang Y, and Hebert M 2016 Learning to learn: model regression networks for easy small sample learning, In Comput Vis –ECCV pp.1–10Google Scholar
  31. 31.
    Wang N, and Yeung DY 2013 Learning a deep compact image representation for visual tracking, In Adv Neural Inf Proces Syst, pp.809–817, .Google Scholar
  32. 32.
    Maji S, Berg A, and Malik J (2008) Classification using intersection kernel support vector machines is efficient, In Proc Of IEEE Comput Vis Pattern Recognit, pp.1–8Google Scholar
  33. 33.
    Yu K, Zhang T, and Gong Y, (2009) Nonlinear learning using local coordinate coding, In NIPSGoogle Scholar
  34. 34.
    Zhang Y (2016) Grorec: a group-centric intelligent recommender system integrating social, mobile and big data technologies. IEEE Trans Serv Comput. doi: 10.1109/TSC.2016.2592520 Google Scholar
  35. 35.
    Wang S, Zhang Y et al (2016) Pathological brain detection by artificial intelligence in magnetic resonance imaging scanning. Prog Electromagn Res 165:105–133CrossRefGoogle Scholar
  36. 36.
    Zhang Y et al (2016) iDoctor: personalized and professionalized medical recommendations based on hybrid matrix factorization. Futur Gener Comput Syst. doi: 10.1016/j.future.2015.12.001 Google Scholar

Copyright information

© Springer Science+Business Media New York 2017

Authors and Affiliations

  1. 1.Kyushu Institute of TechnologyFukuokaJapan
  2. 2.Chinese Academy of ScienceBeijingChina
  3. 3.Yangzhou UniversityYangzhouChina
  4. 4.IBM Australia Inc.West Pennant HillsAustralia
  5. 5.University of Electronic Science and Technology of ChinaChengduChina
  6. 6.Qualcomm Inc.San DiegoUSA

Personalised recommendations