Pollen Image Classification Using the Classifynder System: Algorithm Comparison and a Case Study on New Zealand Honey

  • Ryan LagerstromEmail author
  • Katherine Holt
  • Yulia Arzhaeva
  • Leanne Bischof
  • Simon Haberle
  • Felicitas Hopf
  • David Lovell
Part of the Advances in Experimental Medicine and Biology book series (AEMB, volume 823)


We describe an investigation into how Massey University’s Pollen Classifynder can accelerate the understanding of pollen and its role in nature. The Classifynder is an imaging microscopy system that can locate, image and classify slide based pollen samples. Given the laboriousness of purely manual image acquisition and identification it is vital to exploit assistive technologies like the Classifynder to enable acquisition and analysis of pollen samples. It is also vital that we understand the strengths and limitations of automated systems so that they can be used (and improved) to compliment the strengths and weaknesses of human analysts to the greatest extent possible. This article reviews some of our experiences with the Classifynder system and our exploration of alternative classifier models to enhance both accuracy and interpretability. Our experiments in the pollen analysis problem domain have been based on samples from the Australian National University’s pollen reference collection (2,890 grains, 15 species) and images bundled with the Classifynder system (400 grains, 4 species). These samples have been represented using the Classifynder image feature set. We additionally work through a real world case study where we assess the ability of the system to determine the pollen make-up of samples of New Zealand honey. In addition to the Classifynder’s native neural network classifier, we have evaluated linear discriminant, support vector machine, decision tree and random forest classifiers on these data with encouraging results. Our hope is that our findings will help enhance the performance of future releases of the Classifynder and other systems for accelerating the acquisition and analysis of pollen samples.


Pollen Palynology Image analysis Statistical classification Automation Machine learning 


  1. 1.
    L. Breiman, J.H. Friedman, R.A. Olschen, C.J. Stone, Classification and Regression Trees (Chapman Hall, New York, 1999)Google Scholar
  2. 2.
    L. Breiman, Random forests. Mach. Learn. 45(1), 5–32 (2001)CrossRefzbMATHGoogle Scholar
  3. 3.
    V.M. Bryant, D.C. Mildenhall, Forensic palynology in the United States of America. Palynology 14, 193–208 (1990)CrossRefGoogle Scholar
  4. 4.
    C. Cortes, V. Vapnik, Support-vector networks. Mach. Learn. 20(3), 273–297 (1995)zbMATHGoogle Scholar
  5. 5.
    C. Chun, E.A. Hendriks, R.P.W. Duin, J.H.C. Reiber, P.S. Hiemstra, L.A. de Weger, B. Stoel, Feasibility study on automated recognition of allergenic pollen: grass, birch and mugwort. Aerobiologia. 22, 275–284 (2006)CrossRefGoogle Scholar
  6. 6.
    A. Cristofori, F. Cristofolini, E. Gottardini, Twenty years of aerobiological monitoring in Trentino (Italy): assessment and evaluation of airborne pollen variability. Prog. Phys. Geogr. Aerobiol. 26, 553–261 (2010)Google Scholar
  7. 7.
    R. Dell’Anna, P. Lazzeri, M. Frisanco, F. Monti, F.M. Campeggi, E. Gottardini, M. Bersani, Pollen discrimination and classification by Fourier transform infrared (FT-IR) microspectroscopy and machine learning. Anal. Bioanal. Chem. 394, 1443–1452 (2009)CrossRefGoogle Scholar
  8. 8.
    M.P. De Sa-Otero, A.P. Gonzalez, M. Rodriguez-Damian, E. Cernadas, Computer-aided identification of allergenic species of Urticaceae pollen. Grana 43, 224–230 (2004)CrossRefGoogle Scholar
  9. 9.
    R.A. Fisher, The use of multiple measurements in taxonomic problems. Ann. Eugen. 7(2), 179–188 (1936)CrossRefGoogle Scholar
  10. 10.
    J.R. Flenley, The problem of pollen recognition, in Problems of Picture Interpretation, ed. by M.B. Clowes, J.P. Penny (CSIRO, Canberra, 1968), pp. 141–145Google Scholar
  11. 11.
    I. France, A.W.G. Duller, G.A.T. Duller, H.F. Lamb, A new approach to automated pollen analysis. Quat. Sci. Rev. 19, 537–546 (2000)CrossRefGoogle Scholar
  12. 12.
    M.H.M. Groot, R.G. Bogota, L.J. Lourens, H. Hooghiemstra, M. Vriend, J.C. Berrio, E. Tuenter, J. Van der Plicht, B. Van Geel, M. Ziegler, S.L. Weber, A. Betancourt, L. Contreras, S. Gaviria, C. Giraldo, N. Gonzalez, J.H.F. Jansen, M. Konert, D. Ortega, O. Rangel, G. Sarmiento, J. Vandenberghe, T. Van der Hammen, M. Van der Linden, W. Westerhoff, Ultra-high resolution pollen record from the northern Andes reveals rapid shifts in montane climates within the last two glacial cycles. Clim. Past 7, 299–316 (2011)CrossRefGoogle Scholar
  13. 13.
    J.A. Hertz, A. Krogh, R.G. Palmer, An Introduction to the Theory of Neural Computing (Addison-Wesley, Reading, 1991)Google Scholar
  14. 14.
    K. Holt, G. Allen, R. Hodgson, S. Marsland, J. Flenley, Progress towards an automated trainable pollen location and classifier system for use in the palynology laboratory. Rev. Palaeobot. Palynol. 167, 175–183 (2011)CrossRefGoogle Scholar
  15. 15.
    C.A. Hopping, Palynology and the oil industry. Rev. Palaeobot. Palynol. 2, 372–399 (1967)CrossRefGoogle Scholar
  16. 16.
    S. Hu, D.L. Dilcher, D.M. Jarzen, D.W. Taylor, Early steps of angiosperm-pollinator coevolution. Proc. Natl. Acad. Sci. 105, 240–245 (2007)CrossRefGoogle Scholar
  17. 17.
    G.D. Jones, V.M. Bryant, Melissopalynology in the United States: a review and critique. Palynology 16, 63–71 (1992)CrossRefGoogle Scholar
  18. 18.
    S. Kawashima, B. Clot, T. Fujita, Y. Takahashi, K. Nakamura, An algorithm and a device for counting airborne pollen automatically using laser optics. Atmos. Environ. 41, 7987–7993 (2007)CrossRefGoogle Scholar
  19. 19.
    R. Lagerstrom, Y. Arzhaeva, L. Bischof, S. Haberle, F. Hopf, D. Lovell, A comparison of classification algorithms within the classifynder pollen imaging system, in International Symposium on Computational Models for Life Sciences, Sydney, Nov 2013, vol. 1559, pp. 250–259Google Scholar
  20. 20.
    P. Li, W.J. Treloar, J.R. Flenley, L. Empson, Towards automation of palynology 2: the use of texture measures and neural network analysis for automated identification of optical images of pollen grains. J. Quat. Sci. 19, 755–762 (2004)CrossRefGoogle Scholar
  21. 21.
    L.J. Maher, Nomograms for computing 0.95 confidence limits of pollen data. Rev. Palaeobot. Palynol. 13, 85–93 (1971)Google Scholar
  22. 22.
    M. McGlone, J. Wilmshurst, Dating initial Maori environmental impact in New Zealand. Quat. Int. 59, 5–16 (1999)CrossRefGoogle Scholar
  23. 23.
    D.C. Mildenhall, R. Tremain, Pollen analysis of New Zealand honey. Institute of Geological and Nuclear Sciences science report, 2009, pp. 6–19Google Scholar
  24. 24.
    K. Mitsumoto, K. Yabusaki, K. Kobayashi, H. Aoyagi, Development of a novel real-time pollen-sorting counter using species-specific pollen autofluoresence. Aerobiologia 26, 99–111 (2010)CrossRefGoogle Scholar
  25. 25.
    B.V. Odgaard, Fossil pollen as a record of past biodiversity. J. Biogeogr. 26, 5–16 (1999)Google Scholar
  26. 26.
    S. Petersen, V.M. Bryant, The study of pollen and its role in the honey market. Am. Bee J. 151, 591–594 (2011)Google Scholar
  27. 27.
    R Development Core Team, R: A Language and Environment for Statistical Computing (R Foundation for Statistical Computing, Vienna, 2010)Google Scholar
  28. 28.
    O. Ronneberger, E. Schultz, H. Burkhardt, Automated pollen recognition using 3D volume images from fluourescence microscopy. Aerobiologia 18, 107–115 (2002)CrossRefGoogle Scholar
  29. 29.
    H. Seppa, K.D. Bennett, Quaternary pollen analysis: recent progress in palaeoecology and palaeoclimatology. Prog. Phys. Geogr. 27, 548–579 (2003)CrossRefGoogle Scholar
  30. 30.
    E.C. Stillman, J.R. Flenley, The needs and prospects for automation in palynology. Quat. Sci. Rev. 15, 1–5 (1996)CrossRefGoogle Scholar
  31. 31.
    J. Stockmarr, Tablets with spores used in absolute pollen analysis. Pollen et Spores 13, 615–621 (1971)Google Scholar
  32. 32.
    W. Von der Ohe, L. Persano Oddo, M.L. Piana, M. Morlot, P. Martin, Harmonized methods of melissopalynology. Apidologie 35, S18–S25 (2004)CrossRefGoogle Scholar
  33. 33.
    Y. Zhang, D.W. Fountain, R.M. Hodgson, J.R. Flenley, S. Gunetileke, Towards automation of palynology 3: pollen pattern recognition using Gabor transforms and digital moments. J. Quat. Sci. 19, 763–768 (2004)CrossRefGoogle Scholar

Copyright information

© Springer International Publishing Switzerland 2015

Authors and Affiliations

  • Ryan Lagerstrom
    • 1
    Email author
  • Katherine Holt
    • 2
  • Yulia Arzhaeva
    • 1
  • Leanne Bischof
    • 1
  • Simon Haberle
    • 3
  • Felicitas Hopf
    • 3
  • David Lovell
    • 4
  1. 1.Digital Productivity FlagshipCSIRONorth Ryde, SydneyAustralia
  2. 2.Institute of Natural ResourcesMassey UniversityPalmerston NorthNew Zealand
  3. 3.School of Culture, History and Language, H C Coombs Blg 9The Australian National UniversityCanberraAustralia
  4. 4.Digital Productivity FlagshipCSIROCanberraAustralia

Personalised recommendations