Skip to main content

Automatic diatom identification using contour analysis by morphological curvature scale spaces

Abstract

A method for automatic identification of diatoms (single-celled algae with silica shells) based on extraction of features on the contour of the cells by multi-scale mathematical morphology is presented. After extracting the contour of the cell, it is smoothed adaptively, encoded using Freeman chain code, and converted into a curvature representation which is invariant under translation and scale change. A curvature scale space is built from these data, and the most important features are extracted from it by unsupervised cluster analysis. The resulting pattern vectors, which are also rotation-invariant, provide the input for automatic identification of diatoms by decision trees and k-nearest neighbor classifiers. The method is tested on two large sets of diatom images. The techniques used are applicable to other shapes besides diatoms.

This is a preview of subscription content, access via your institution.

References

  1. 1.

    Bangham, J.A., Chardaire, P., Pye, C.J., Ling, P.D.: Multiscale nonlinear decomposition: the sieve decomposition theorem. IEEE Trans. Pattern Anal. Machine Intell. 18, 529–538 (1996)

    Google Scholar 

  2. 2.

    Bangham, J.A., Ling, P.D., Harvey, R.: Scale-space from nonlinear filters. IEEE Trans. Pattern Anal. Machine Intell. 18, 520–528 (1996)

    Google Scholar 

  3. 3.

    Breen, E.J., Jones, R.: Attribute openings, thinnings and granulometries. Comput. Vision Image Understanding 64(3), 377–389 (1996)

    Google Scholar 

  4. 4.

    Breiman, L.: Bagging predictors. Machine Learning 24(2), 123–140 (1996)

    MATH  MathSciNet  Google Scholar 

  5. 5.

    du Buf, H., Bayer, M., Droop, S., Head, R., Juggins, S., Fischer, S., Bunke, H., Roerdink, M.W., Pech-Pacheco, J., Christobal, G., Shahbazkia, H., Ciobanu, A.: Diatom identification: a double challenge called ADIAC. In: Proceedings of ICIAP, Venice, pp. 734–739 (1999)

  6. 6.

    du Buf, H., Bayer, M.M.: ADIAC achievements and future work. In: du Buf J.M.H., Bayer M.M.(eds.) Automatic Diatom Identification, Series in Machine Perception and Artificial Intelligence, vol. 51, chap. 14, pp. 289–298. World Scientific, Singapore (2002)

  7. 7.

    Chen, M.H., Yan, P.F.: A multiscale approach based on morphological filtering. IEEE Trans. Pattern Anal. Machine Intell. 11, 694–700 (1989)

    MATH  Google Scholar 

  8. 8.

    Ciobanu, A., du Buf, H.: Identification by contour profiling and Legendre polynomials. In: du Buf J.M.H., Bayer M.M.(eds.) Automatic Diatom Identification, Series in Machine Perception and Artificial Intelligence, vol. 51, chap. 9, pp. 167–185. World Scientific, Singapore (2002)

  9. 9.

    Comaniciu, D., Meer, P.: Mean shift: a robust approach toward feature space analysis. IEEE Trans. Pattern Anal. Machine Intell. 24(5), 603–619 (2002)

    Article  Google Scholar 

  10. 10.

    Epanechnikov, V.A.: Nonparametric estimation of a multidimensioal probability density. Theor. Prob. Appl. 14, 153–158 (1969)

    Article  Google Scholar 

  11. 11.

    Fischer, S., Bunke, H.: Identification using classical and new features in combination with decision tree ensembles. In: du Buf, J.M.H., Bayer, M.M. (eds.) Automatic Diatom Identification, Series in Machine Perception and Artificial Intelligence, vol. 51, chap. 6, pp. 109–140. World Scientific, Singapore (2002)

  12. 12.

    Fischer, S., Shahbazkia, H.R., Bunke, H.: Contour extraction. In: du Buf, J.M.H., Bayer, M.M. (eds.) Automatic Diatom Identification, Series in Machine Perception and Artificial Intelligence, vol. 51, chap. 6, pp. 93–107. World Scientific, Singapore (2002)

  13. 13.

    Flusser, J., Suk, T.: Pattern recognition by affine moment invariants. Pattern Recognition 26, 167–174 (1993)

    Article  MathSciNet  Google Scholar 

  14. 14.

    Fukunaga, K., Hostetler, L.D.: Estimation of the gradient of a density function with applications in pattern recognition. IEEE Trans. Inform. Theor. 21, 32–40 (1975)

    MathSciNet  MATH  Google Scholar 

  15. 15.

    Gil, J., Werman, M.: Computing 2-D min, median, and max filters. IEEE Trans. Pattern Anal. Machine Intell. 15, 504–507 (1993)

    Article  Google Scholar 

  16. 16.

    Gonzalez, R.C., Woods, R.E.: Digital Image Processing. Addison-Wesley, Reading, MA (1992)

    Google Scholar 

  17. 17.

    Gose, E., Johnsonbaugh, R., Jost, S.: Pattern Recognition and Image Analysis. Prentice Hall PTR, Englewood Cliffs, NJ (1996)

    Google Scholar 

  18. 18.

    Heijmans, H.J.A.M.: Morphological Image Operators, Advances in Electronics and Electron Physics, Supplement, vol. 25. Academic, New York (1994)

    Google Scholar 

  19. 19.

    Hu, M.K.: Visual pattern recognition by moment invariants. IEEE Trans. Inform. Theor. 8, 179–187 (1962)

    MATH  Google Scholar 

  20. 20.

    Jackway, P.T., Deriche, M.: Scale-space properties of the multiscale morphological dilation-erosion. IEEE Trans. Pattern Anal. Machine Intell. 18, 38–51 (1996)

    Article  Google Scholar 

  21. 21.

    Jain, A.K.: Fundamentals of Digital Image Processing. Prentice Hall, Englewood Cliffs, NJ (1989)

    MATH  Google Scholar 

  22. 22.

    Jalba, A.C., Wilkinson, M.H.F., Roerdink, J.B.T.M.: Shape representation and recognition through morphological curvature scale spaces. Technical Report IWI 2003-10-01, Institute for Mathematics and Computing Science, University of Groningen (2003)

  23. 23.

    Kelly, M.G., Bayer, M.M., Hürlimann, J., Telford, R.J.: Human error and quality assurance in diatom analysis. In: du Buf, J.M.H., Bayer, M.M. (eds.) Automatic Diatom Identification, Series in Machine Perception and Artificial Intelligence, vol. 51, chap. 5, pp. 75–91. World Scientific, Singapore (2002)

  24. 24.

    Kohavi, R.: A study of cross-validation and bootstrap for accuracy estimation and model selection. In: Proceedings of International Joint Conference on Artificial Intelligence, pp. 1137–1145 (1995)

  25. 25.

    Leymarie, F., Levine, M.D.: Curvature morphology. Technical Report TR-CIM-88-26, Computer Vision and Robotics Laboratory, McGill University, Montreal, Quebec, Canada (1988)

  26. 26.

    Leyton, M.: Symmetry-curvature duality. Comput. Vision Graph. Image Process. 38, 327–341 (1987)

    MATH  Google Scholar 

  27. 27.

    Lindeberg, T.: Scale-space theory: a basic tool for analysing structures at different scales. J. Appl. Stat. 21, 225–270 (1994)

    Google Scholar 

  28. 28.

    Meijster, A., Wilkinson, M.H.F.: A comparison of algorithms for connected set openings and closings. IEEE Trans. Pattern Anal. Machine Intell. 24(4), 484–494(2002)

    Article  Google Scholar 

  29. 29.

    Mokhtarian, F., Abbasi, S., Kittler, J.: Efficient and robust retrieval by shape content through curvature scale space. In: Smeulders, A.W.M., Jain, R. (eds.) Image DataBases and Multi-Media Search, pp. 51–58. World Scientific, Singapore (1997)

    Google Scholar 

  30. 30.

    Mokhtarian, F., Mackworth, A.K.: Scale-based description and recognition of planar curves and two-dimensional shapes. IEEE Trans. Pattern Anal. Machine Intell. 8, 34–43 (1986)

    Google Scholar 

  31. 31.

    Mokhtarian, F., Mackworth, A.K.: A theory of multiscale, curvature-based shape representation for planar curves. IEEE Trans. Pattern Anal. Machine Intell. 14, 789–805 (1992)

    Article  Google Scholar 

  32. 32.

    Nacken, P.F.M.: Chamfer metrics in mathematical morphology. J. Math. Imaging Vision 4, 233–253 (1994)

    MathSciNet  Google Scholar 

  33. 33.

    Park, K.R., Lee, C.N.: Scale-space using mathematical morphology. IEEE Trans. Pattern Anal. Machine Intell. 18, 1121–1126 (1996)

    Google Scholar 

  34. 34.

    Pavlidis, T.: Algorithms for shape analysis of contours and waveforms. IEEE Trans. Pattern Anal. Machine Intell. 2, 301–312 (1980)

    Article  Google Scholar 

  35. 35.

    Quinlan, J.R.: C4. 5: Programs for Machine Learning. Morgan Kaufmann Publishers, San Fransisco, CA (1993)

    Google Scholar 

  36. 36.

    Round, F.E., Crawford, R.M., Mann, D.G.: The Diatoms: Biology and Morphology of the Genera. Cambridge University Press, Cambridge (1990)

    Google Scholar 

  37. 37.

    Santos, L., du Buf, H.: Identification by Gabor features. In: du Buf, J.M.H., Bayer, M.M. (eds.) Automatic Diatom Identification, Series in Machine Perception and Artificial Intelligence, vol. 51, chap. 10, pp. 187–220. World Scientific, Singapore (2002)

  38. 38.

    Serra, J.: Image Analysis and Mathematical Morphology. Academic, New York (1982)

    MATH  Google Scholar 

  39. 39.

    Silverman, B.W.: Density Estimation for Statistics and Data Analysis. Chapman and Hall, London (1986)

    MATH  Google Scholar 

  40. 40.

    Stoermer, E.F., Smol, J.P.(eds.): The Diatoms: Applications for the Environmental and Earth Sciences. Cambridge University Press, Cambridge (1999)

    Google Scholar 

  41. 41.

    Webb, A.: Statistical Pattern Recognition. Arnold, London (1999)

    MATH  Google Scholar 

  42. 42.

    Westenberg, M.A.: Roerdink JBTM Mixed-method identifications. In: du Buf, J.M.H., Bayer, M.M. (eds.) Automatic Diatom Identification, Series in Machine Perception and Artificial Intelligence, vol. 51, chap. 12, pp. 245–257. World Scientific, Singapore (2002)

    Google Scholar 

  43. 43.

    Wilkinson, M.H.F., Jalba, A.C., Urbach, E.R., Roerdink, J.B.T.M.: Identification by mathematical morphology. In: du Buf, J.M.H., Bayer, M.M. (eds.) Automatic Diatom Identification, Series in Machine Perception and Artificial Intelligence, vol. 51, chap. 11, pp. 221–244. World Scientific, Singapore (2002)

    Google Scholar 

  44. 44.

    Wilkinson, M.H.F., Roerdink, J.B.T.M., Droop, S., Bayer, M.: Diatom contour analysis using morphological curvature scale spaces. In: Proceedings of 15th International Conference on Pattern Recognition (ICPR'2000), pp. 656–659. Barcelona, Spain (2000)

  45. 45.

    Witkin, A.P.: Scale-space filtering. In: Proceedings of International Joint Conference on Artificial Intelligence, pp. 1019–1022. Palo Alto, CA (1983)

  46. 46.

    Zahn, C.T., Roskies, R.Z.: Fourier descriptors for plane closed curves. IEEE Trans. Comput. 21, 269–281 (1972)

    MathSciNet  MATH  Article  Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Jos B. T. M. Roerdink.

Additional information

Andrei C. Jalba received his B.Sc. (1998) and M.Sc. (1999) in Applied Electronics and Information Engineering from “Politehnica” University of Bucharest, Romania. He recently obtained a Ph.D. degree at the Institute for Mathematics and Computing Science of the University of Groningen, where he now is a postdoctoral researcher. His research interests include computer vision, pattern recognition, image processing, and parallel computing.

Michael Wilkinson obtained an M.Sc. in astronomy from the Kapteyn Laboratory, University of Groningen (RuG) in 1993, after which he worked on image analysis of intestinal bacteria at the Department of Medical Microbiology, RuG. This work formed the basis of his Ph.D. at the Institute of Mathematics and Computing Science (IWI), RuG, in 1995. He was appointed as researcher at the Centre for High Performance Computing (also RuG) working on simulating the intestinal microbial ecosystem on parallel computers. During that time he edited the book “Digital Image Analysis of Microbes” (John Wiley, UK, 1998) together with Frits Schut. After this he worked as a researcher at the IWI on image analysis of diatoms. He is currently assistant professor at the IWI.

Jos B.T.M. Roerdink received his M.Sc. (1979) in theoretical physics from the University of Nijmegen, the Netherlands. Following his Ph.D. (1983) from the University of Utrecht and a 2-year position (1983--1985) as a Postdoctoral Fellow at the University of California, San Diego, both in the area of stochastic processes, he joined the Centre for Mathematics and Computer Science in Amsterdam. There he worked from 1986-1992 on image processing and tomographic reconstruction. He was appointed associate professor (1992) and full professor (2003), respectively, at the Institute for Mathematics and Computing Science of the University of Groningen, where he currently holds a chair in Scientific Visualization and Computer Graphics. His current research interests include biomedical visualization, neuroimaging and bioinformatics.

Micha Bayer graduated from St. Andrews University, Scotland, with an M.Sc. in Marine Biology in 1994. He obtained his Ph.D. in Marine Biology from there in 1998, and then followed this up with two postdoctoral positions at the Royal Botanic Garden Edinburgh, Scotland, first on the ADIAC and then on the DIADIST project. In both of these projects he was responsible for establishing the collections of diatom training data to be used for the pattern recognition systems. From 2002–2003 he was enrolled for an M.Sc. in information technology at the University of Glasgow, Scotland, and is now working as a grid developer at the National e-Science Centre at Glasgow University.

Stephen Juggins is a senior lecturer at the School of Geography, Politics and Sociology, University of Newcastle. His research focuses on the use of diatoms for monitoring environmental change and on the analysis of ecological and palaeoecological data. He has worked in Europe, North America and Central Asia on problems of river water quality, historical lake acidification, coastal eutrophication and Quaternary climate change.

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Jalba, A.C., Wilkinson, M.H.F., Roerdink, J.B.T.M. et al. Automatic diatom identification using contour analysis by morphological curvature scale spaces. Machine Vision and Applications 16, 217–228 (2005). https://doi.org/10.1007/s00138-005-0175-8

Download citation

Keywords

  • Diatom identification
  • Mathematical morphology
  • Contour analysis
  • Curvature scale spaces
  • Multi-scale analysis
  • Decision trees