Plant Systematics and Evolution

, Volume 270, Issue 1–2, pp 95–108 | Cite as

Camellia japonica L. genotypes identified by an artificial neural network based on phyllometric and fractal parameters

  • S. Mugnai
  • C. Pandolfi
  • E. Azzarello
  • E. Masi
  • S. Mancuso


The potential application of phyllometric and fractal parameters for the objective quantitative description of leaf morphology, combined with the use of Back Propagation Neural Network (BPNN) for data modelling, was evaluated to characterize and identify 25 Camellia japonica L. accessions from an Italian historical collection. Results show that the construction of a BPNN based on phyllometric and fractal analysis could be effectively and successfully used to discriminate Camellia japonica genotypes using simple dedicated instruments, such as a personal computer and an easily available optical scanner.


backpropagation neural network (BPNN) Camellia cluster analysis cultivar identification fractal spectrum 


Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.


  1. Chang HT, Bartholomew B (1984) Camellias. Timber Press, Portland (USA)Google Scholar
  2. Clark JY (2004) Identification of botanical specimens using artificial neural networks. In: Proceedings of the 2004 IEEE symposium on computational intelligence in bioinformatics and computational biology, La Jolla (USA), 7–8th October 2004, pp 87–94Google Scholar
  3. Clark JY, Warwick K (1998) Artificial keys for botanical identification using a multilayer perceptron neural network (MLP). Artif Intell Rev 12: 95–115CrossRefGoogle Scholar
  4. Corneo A, Remotti D, Accati E (2000) Camelie dell’Ottocento nel Verbano. Regione Piemonte, Torino, ItalyGoogle Scholar
  5. Durrant T (1982) The camellia story. Heinemann Publishers, Auckland, New ZealandGoogle Scholar
  6. Eder R, Wendelin S, Barna J (1994) Classification of red wine cultivars by means of anthocyanin analysis. Mitt Klosterneuburg 44: 201–212Google Scholar
  7. Grilli M (1881) Varietà di Camelie ottenute in Firenze. Bull Reale Soc Ort Tosc 6: 297–300Google Scholar
  8. Grilli M (1883) Nuove varietà di Camelie ottenute in Firenze. Bull Reale Soc Ort Tosc 8: 169–171Google Scholar
  9. Haykin S (1999) Neural Networks: A comprehensive foundation, 2nd Ed. Pearson Prentice Hall, USAGoogle Scholar
  10. Hertz J, Krogh A, Palmer R (1991) Introduction to the Theory of Neural Computation. Addison-Wesley, Redwood City (USA)Google Scholar
  11. Lombard V, Dubreuil P, Dilmann C, Baril C (2001) Genetic distance estimators based on molecular data for plant registration and protection: a review. Acta Hort 546: 55–63Google Scholar
  12. Mancuso S (2002) Discrimination of grapevine (Vitis vinifera L.) leaf shape by fractal spectrum. Vitis 41: 137–142Google Scholar
  13. Mancuso S (1999a) Elliptic Fourier analysis (EFA) and artificial neural networks (ANNs) for the identification of grapevine (Vitis vinifera L.) genotypes. Vitis 38: 73–77Google Scholar
  14. Mancuso S (1999b) Fractal geometry-based image analysis of grapevine leaves using the box counting algorithm. Vitis 38: 97–100Google Scholar
  15. Mancuso S, Nicese FP (1999) Identifying olive (Olea europaea L.) cultivars using artificial neural networks. J Am Soc Hort Sci 124: 527–531Google Scholar
  16. Mancuso S, Ferrini F, Nicese FP (1999) Chestnut (Castanea sativa L.) genotype identification: an artificial neural network approach. J Hort Sci Biotech 74: 777–784Google Scholar
  17. Mancuso S, Nicese FP, Azzarello E (2003) The fractal spectrum of the leaves as a tool for measuring frost hardiness in plants. J Hort Sci Biotech 78: 610–616Google Scholar
  18. Mancuso S, Nicese FP, Azzarello E (2004) Comparing fractal analysis, electrical impedance and electrolyte leakage for the assessment of cold tolerance in Callistemon and Grevillea spp. J Hort Sci Biotech 79: 627–632Google Scholar
  19. Pandolfi C, Mugnai S, Azzarello E, Masi E, Mancuso S (2006) Fractal geometry and neural networks for the identification and characterization of ornamental plants. In: Teixiera da Silva J (ed) Floriculture, ornamental and plant biotechnology: advances and topical issues. vol. IV reprint, Kyoto (Japan), pp 213–225Google Scholar
  20. Petrova E (1996) Genetic resources of ornamental flower in the Czech Republic. Zahradnictvi 23: 109–112Google Scholar
  21. Parks CR, Yoshikawa N, Prince L, Thakor B (1995) The application of isozymic and molecular evidence to taxonomic and breeding problems in the genus Camellia. Int Camellia J 27: 103–111Google Scholar
  22. Prince LM, Parks CR (2001) Phylogenetic relationships of Theaceae inferred from chloroplast DNA sequence data. Am J Bot 88: 2309–2320CrossRefGoogle Scholar
  23. Remotti D (2002) Identification and morpho-botanic characterization of old Camellia japonica L. cultivars grown in historic gardens of the Lake Maggiore (Italy). Acta Hort 572: 179–188Google Scholar
  24. Rumelhart DE, Hinton GE, Williams RJ (1986) Learning representations by back-propagating errors. Nature 323: 533–536CrossRefGoogle Scholar
  25. Rumelhart DE, McClelland JL (1988) Exploration in parallel distributed processing. Cambridge (USA), MIT PressGoogle Scholar
  26. Sànchez-Escribano EM, Martìn JP, Carreno J, Cenis JL (1999) Use of sequence-tagged microsatellite site markers for characterizing table grape cultivars. Genome 42: 87–93CrossRefGoogle Scholar
  27. Sefc KM, Lopes MS, Lefort F, Botta R, Ibáñez J, Pejic I, Wagner HW, Glössl J, Steinkellner H (2000) Microsatellite variability in grapevine cultivars from different European regions and evaluation of assignment testing to assess the geographic origin of cultivars. Theor Appl Genet 100: 498–505CrossRefGoogle Scholar
  28. Ueno S, Tomaru N, Yoshimaru H, Manabe T, Yamamoto S (2000) Genetic structure of Camellia japonica L. in an old-growth evergreen forest, Tsushima, Japan. Mol Ecol 9: 647– 656CrossRefGoogle Scholar
  29. Ueno S, Tomaru N, Yoshimaru H, Manabe T, Yamamoto S (2002) Size-class differences in genetic structure and individual distribution of Camellia japonica L. in a Japanese old-growth evergreen forest. Heredity 89: 120–126PubMedCrossRefGoogle Scholar
  30. Żebrowska J I, Tyrka M (2003) The use of RAPD markers for strawberry identification and genetic diversity studies. Food Agr Environ 1: 115–117Google Scholar
  31. Zurada JM, Malinowsli A (1994) Multilayer perceptron networks: selected aspects of training optimization. Appl Math Comp Sci 4: 281–307Google Scholar

Copyright information

© Springer-Verlag 2007

Authors and Affiliations

  • S. Mugnai
    • 1
  • C. Pandolfi
    • 1
  • E. Azzarello
    • 1
  • E. Masi
    • 1
  • S. Mancuso
    • 1
  1. 1.Department of HorticultureUniversity of FlorenceSesto FiorentinoItaly

Personalised recommendations