Machine Vision and Applications

, Volume 17, Issue 5, pp 297–307 | Cite as

A model of diatom shape and texture for analysis, synthesis and identification

  • Y. A. HicksEmail author
  • D. Marshall
  • P. L. Rosin
  • R. R. Martin
  • D. G. Mann
  • S. J. M. Droop
Original Paper


We describe tools for automatic identification and classification of diatoms that compare photographs with other photographs and drawings, via a model. Identification of diatoms, i.e. assigning a new specimen to one of the known species, has applications in many disciplines, including ecology, palaeoecology and forensic science. The model we build represents life cycle and natural variation of both shape and texture over multiple diatom species, derived automatically from photographs and/or drawings. The model can be used to automatically produce drawings of diatoms at any stage of their life cycle development. Similar drawings are traditionally used for diatom identification, and encapsulate visually salient diatom features. In this article, we describe the methods used for analysis of photographs and drawings, present our model of diatom shape and texture variation, and finish with results of identification experiments using photographs and drawings as well as a detailed evaluation.


Classification Automatic drawing synthesis Principal curves Texture analysis Diatoms 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. 1.
    du Buf H., Bayer M.M. ed. (2002) Automatic Diatom Identification. vol. 51, Series in Machine Perception and Artificial Intelligence, World Scientific, SingaporeGoogle Scholar
  2. 2.
    Chang K., Ghosh J. (2001) A unified model for probabilistic principal surfaces. IEEE Trans. Pattern Anal. Mach. Intell. 23(1): 22–41CrossRefGoogle Scholar
  3. 3.
    Goldman N., Paddock T.B.B., Shaw K.M. (1990) Quantitative analysis of shape variation in populations of Surirella fastuosa. Diatom Res. 5, 25–42Google Scholar
  4. 4.
    Gonzalez R.C., Woods R.E. (1993) Digital Image Processing. Addison-Wesley, ReadingGoogle Scholar
  5. 5.
    Hastie T., Stuetzel W. (1989) Principal curves. J. Am. Stat. Assoc. 84(406): 502–516zbMATHCrossRefGoogle Scholar
  6. 6.
    Hicks Y.A., Marshall A.D., Rosin P.L., Martin R.R., Bayer M.M., Mann D.G. (2002) Modelling life cycle related and individual shape variation in biological specimens. Proc. BMVC 1, 323–332Google Scholar
  7. 7.
    Mann D.G., Droop S.J.M. (1996) Biodiversity, biogeography and conservation of diatoms. Hydrobiologia 336, 19–32Google Scholar
  8. 8.
    Mann D.G. (1999) The species concept in diatoms (Phycological Reviews 18). Phycologia 38, 437–495CrossRefGoogle Scholar
  9. 9.
    Mou D., Stoermer E. (1992) Separating Tabellaria (Bacillariophyceae) shape groups based on fourier descriptors. J. Phycol. 28, 386–395CrossRefGoogle Scholar
  10. 10.
    Murthy S., Kasif S., Salzberg S. (1994) System for induction of oblique decision trees. J. Artif. Intell. Res. 2, 1–32zbMATHGoogle Scholar
  11. 11.
    Rifkin, R. SvmFu package. Available from Scholar
  12. 12.
    Round F.E., Crawford R.M., Mann D.G. (1990) The diatoms. Biology and Morphology of the Genera. Cambridge University Press, CambridgeGoogle Scholar
  13. 13.
    Stoermer, E.F., Ladewski, T.B. Quantitative Analysis of Shape Variation in Type and Modern Populations of Gomphoneis herculeana. 73, 347–386, Nova Hedwigia, Beih (1982)Google Scholar
  14. 14.
    Zahn C.T., Roskies R.Z. (1972) Fourier descriptors for plane closed curves. IEEE Trans. Comput. c-21(3): 269–281MathSciNetCrossRefGoogle Scholar
  15. 15.
    British Diatomists of the 19th Century database. Available at Scholar

Copyright information

© Springer-Verlag 2006

Authors and Affiliations

  • Y. A. Hicks
    • 1
    Email author
  • D. Marshall
    • 2
  • P. L. Rosin
    • 2
  • R. R. Martin
    • 2
  • D. G. Mann
    • 3
  • S. J. M. Droop
    • 3
  1. 1.Cardiff School of EngineeringCardiff UniversityCardiffUK
  2. 2.School of Computer ScienceCardiff UniversityCardiffUK
  3. 3.Royal Botanic Garden EdinburghEdinburghUK

Personalised recommendations