Automatic plankton image classification combining multiple view features via multiple kernel learning
Tóm tắt
Plankton, including phytoplankton and zooplankton, are the main source of food for organisms in the ocean and form the base of marine food chain. As the fundamental components of marine ecosystems, plankton is very sensitive to environment changes, and the study of plankton abundance and distribution is crucial, in order to understand environment changes and protect marine ecosystems. This study was carried out to develop an extensive applicable plankton classification system with high accuracy for the increasing number of various imaging devices. Literature shows that most plankton image classification systems were limited to only one specific imaging device and a relatively narrow taxonomic scope. The real practical system for automatic plankton classification is even non-existent and this study is partly to fill this gap. Inspired by the analysis of literature and development of technology, we focused on the requirements of practical application and proposed an automatic system for plankton image classification combining multiple view features via multiple kernel learning (MKL). For one thing, in order to describe the biomorphic characteristics of plankton more completely and comprehensively, we combined general features with robust features, especially by adding features like Inner-Distance Shape Context for morphological representation. For another, we divided all the features into different types from multiple views and feed them to multiple classifiers instead of only one by combining different kernel matrices computed from different types of features optimally via multiple kernel learning. Moreover, we also applied feature selection method to choose the optimal feature subsets from redundant features for satisfying different datasets from different imaging devices. We implemented our proposed classification system on three different datasets across more than 20 categories from phytoplankton to zooplankton. The experimental results validated that our system outperforms state-of-the-art plankton image classification systems in terms of accuracy and robustness. This study demonstrated automatic plankton image classification system combining multiple view features using multiple kernel learning. The results indicated that multiple view features combined by NLMKL using three kernel functions (linear, polynomial and Gaussian kernel functions) can describe and use information of features better so that achieve a higher classification accuracy.
Tài liệu tham khảo
Davis CS, Thwaites FT, Gallager SM, Hu Q. A three-axis fast-tow digital Video Plankton Recorder for rapid surveys of plankton taxa and hydrography. Limnol Oceanogr Meth. 2005; 3:59–74.
Picheral M, Guidi L, Stemmann L, Karl DM, Iddaoud G, Gorsky G. The Underwater Vision Profiler 5: An advanced instrument for high spatial resolution studies of particle size spectra and zooplankton. Limnol Oceanogr Meth. 2010; 8:462–73.
Samson S, Hopkins T, Remsen A, Langebrake L, Sutton T, Patten J. A system for high-resolution zooplankton imaging. IEEE J Oceanic Eng. 2001; 26:671–6.
Benfield MC, Schwehm CJ, Keenan SF. ZOOVIS: a high resolution digital camera system for quantifying zooplankton abundance and environmental data. Proc Am Soc Limnol Oceanogr. 2001;12–17.
Jaffe JS. To sea and to see: That is the answer. Meth Oceanogr. 2016; 15:3–20.
Olson RJ, Sosik HM. A submersible imaging-in-flow instrument to analyze nano-and microplankton: Imaging FlowCytobot. Limnol Oceanogr Meth. 2007; 5:195–203.
Cowen RK, Guigand CM. In situ ichthyoplankton imaging system (isiis): system design and preliminary results. Limnol Oceanogr Meth. 2008; 6:126–32.
Gorsky G, Ohman MD, Picheral M, Gasparini S, Stemmann L, Romagnan JB, Cawood A, Pesant S, García-Comas C, Prejger F. Digital zooplankton image analysis using the ZooScan integrated system. J Plankton Res. 2010; 32:285–303.
MacLeod N, Benfield M, Culverhouse P. Time to automate identification. Nat. 2010; 467:154–5.
Benfield MC, Grosjean P, Culverhouse PF, Irigoien X, Sieracki ME, Lopez-Urrutia A, Dam HG, Hu Q, Davis CS, Hansen A, Pilskaln CH, Riseman EM, Schultz H, Utgoff PE, Gorsky G. RAPID: research on automated plankton identification. Oceanogr. 2007; 20:172–87.
Tang X, Stewart WK, Vincent L, Huang H, Marra M, Gallager SM, Davis CS. Automatic plankton image recognition. Artif Intell Rev. 1998; 12:177–99.
Hu Q, Davis C. Automatic plankton image recognition with co-occurrence matrices and support vector machine. Mar Ecol Prog Ser. 2005; 295:21–31.
Luo T, Kramer K, Goldgof DB, Hall LO, Samson S, Remsen A, Hopkins T. Recognizing plankton images from the shadow image particle profiling evaluation recorder. IEEE Trans Syst Man Cybern B. 2004; 34:1753–62.
Luo T, Kramer K, Goldgof DB, Hall LO, Samson S, Remsen A, Hopkins T. Active learning to recognize multiple types of plankton. J Mach Learn Res. 2005; 6:589–613.
Tang X, Lin F, Samson S, Remsen A. Binary plankton image classification. IEEE J Oceanic Eng. 2006; 31:728–35.
Zhao F, Lin F, Seah HS. Binary SIPPER plankton image classification using random subspace. Neurocomputing. 2010; 73:1853–60.
Sosik HM, Olson RJ. Automated taxonomic classification of phytoplankton sampled with imaging-in-flow cytometry. Limnol Oceanogr Meth. 2007; 5:204–16.
Bi H, Guo Z, Benfield MC, Fan C, Ford M, Shahrestani S, Sieracki JM. A semi-automated image analysis procedure for in situ plankton imaging systems. PLoS ONE. 2015; 10:0127121.
Faillettaz R, Picheral M, Luo JY, Guigand C, Cowen RK, Irisson JO. Imperfect automatic image classification successfully describes plankton distribution patterns. Meth Oceanogr. 2016; 15:60–77.
Du Buf H, Bayer MM. Automatic Diatom Identification. Singapore: World Scientific; 2002.
Loke RE, du Buf JH, Bayer M, Mann DG. Diatom classification in ecological applications. Pattern Recogn. 2004; 37:1283–5.
Jalba AC, Wilkinson MH, Roerdink JB, Bayer MM, Juggins S. Automatic diatom identification using contour analysis by morphological curvature scale spaces. Mach Vis Appl. 2005; 16:217–28.
Hicks YA, Marshall D, Rosin PL, Martin RR, Mann DG, Droop SJM. A model of diatom shape and texture for analysis, synthesis and identification. Mach Vis Appl. 2006; 17:297–307.
Dimitrovski I, Kocev D, Loskovska S, Džeroski S. Hierarchical classification of diatom images using ensembles of predictive clustering trees. Ecol Inform. 2012; 7:19–29.
Culverhouse PF, Herry V, Ellis R, Williams R, Reguera B, Gonzalez-Gil S, Umani SF, Cabrini M, Parisini T. Dinoflagellate categorisation by artificial neural network. Sea Technol. 2002; 43:39–46.
Bell JL, Hopcroft RR. Assessment of ZooImage as a tool for the classification of zooplankton. J Plankton Res. 2008; 30:1351–67.
Mosleh MA, Manssor H, Malek S, Milow P, Salleh A. A preliminary study on automated freshwater algae recognition and classification system. BMC Bioinformatics. 2012; (Suppl 17):25.
Santhi N, Pradeepa C, Subashini P, Kalaiselvi S. Automatic identification of algal community from microscopic images. Bioinform Biol Insights. 2013; 7:327–34.
Verikas A, Gelzinis A, Bacauskiene M, Olenina I, Vaiciukynas E. An integrated approach to analysis of phytoplankton images. IEEE J Oceanic Eng. 2015; 40:315–26.
Fan B, Wang Z, Wu F. Local Image Descriptor: Modern Approaches. Berlin: Springer; 2015.
Gönen M, Alpaydın E. Multiple kernel learning algorithms. J Mach Learn Res. 2011; 12:2211–268.
Bellman RE. Adaptive Control Processes: a Guided Tour. Princeton: Princeton University Press; 2015.
Jouenne F, Probert I, Vaulot D. Plankton taxonomy in the computer age. Cah Biol Mar. 2008; 49:355–67.
Idrissa M, Acheroy M. Texture classification using Gabor filters. Pattern Recogn Lett. 2002; 23:1095–102.
Ahonen T, Hadid A, Pietikainen M. Face description with local binary patterns: Application to face recognition. IEEE Trans Pattern Anal Mach Intell. 2006; 28:2037–41.
Fernández A, Álvarez MX, Bianconi F. Image classification with binary gradient contours. Opt Laser Eng. 2011; 49:1177–84.
Matheron G. Randoms Sets and Integral Equation. New York: Wiley; 1978.
Dalal N, Triggs B. Histograms of oriented gradients for human detection. In: Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition. San Diego: IEEE;2005. p. 886–93.
Lowe DG. Object recognition from local scale-invariant features. In: Proceedings of IEEE International Conference on Computer Vision. Kerkyra: IEEE;1999. p. 1150–57.
Ling H, Jacobs DW. Shape classification using the inner-distance. IEEE Trans Pattern Anal Mach Intell. 2007; 29:286–99.
Belongie S, Malik J, Puzicha J. Shape matching and object recognition using shape contexts. IEEE Trans Pattern Anal Mach Intell. 2002; 24:509–22.
Kohavi R, John GH. Wrappers for feature subset selection. Artif Intell. 1997; 97:273–324.
Bucak SS, Jin R, Jain AK. Multiple kernel learning for visual object recognition: A review. IEEE Trans Pattern Anal Mach Intell. 2014; 36:1354–69.
Li J, Huang X, Gamba P, Bioucas-Dias JM, Zhang L, Benediktsson JA, Plaza A. Multiple feature learning for hyperspectral image classification. IEEE Trans Geosci Remote Sens. 2015; 53:1592–06.
Rakotomamonjy A, Bach FR, Canu S, Grandvalet Y. SimpleMKL. J Mach Learn Res. 2008; 9:2491–521.
Xu Z, Jin R, Yang H, King I, Lyu MR. Simple and efficient multiple kernel learning by group lasso. In: Proceedings of International Conference on Machine Learning. Haifa: Omnipress;2010. p. 1175–82.
Varma M, Babu BR. More generality in efficient multiple kernel learning. In: Proceedings of International Conference on Machine Learning. Montreal: ACM;2009. p. 1065–72.
Cortes C, Mohri M, Rostamizadeh A. Learning non-linear combinations of kernels. In: Proceedings of Advances in Neural Information Processing Systems. Vancouver: Curran Associates;2009. p. 396–404.
Gönen M, Alpaydin E. Localized multiple kernel learning. In: Proceedings of International Conference on Machine Learning. Helsinki: ACM;2008. p. 352–9.
Althloothi S, Mahoor MH, Zhang X, Voyles RM. Human activity recognition using multi-features and multiple kernel learning. Pattern Recogn. 2014; 47:1800–12.
Luo W, Yang J, Xu W, Li J, Zhang J. Higher-level feature combination via multiple kernel learning for image classification. Neurocomputing. 2015; 167:209–17.
LeCun Y, Bengio Y, Hinton G. Deep learning. Nat. 2015; 521:436–44.
Dai J, Wang R, Zheng H, Ji G, Qiao X. ZooplanktoNet: Deep convolutional network for zooplankton classification. In: Proceedings of OCEANS MTS/IEEE Shanghai. Shanghai: IEEE;2016. p. 1–6.
Li X, Cui Z. Deep residual networks for plankton classification. In: Proceedings of OCEANS MTS/IEEE Monterey. Monterey: IEEE;2016. p. 1–4.
Lee H, Park M, Kim J. Plankton classification on imbalanced large scale database via convolutional neural networks with transfer learning. In: Proceedings of IEEE International Conference on Image Processing. Phoenix: IEEE;2016. p. 3713–717.