Автоматическое фенотипирование морфологии колоса тетра- и гексаплоидных видов пшеницы методами компьютерного зрения

Translated title of the contribution: Automatic morphology phenotyping of tetra-and hexaploid wheat spike using computer vision methods

A. Y. Pronozin, A. A. Paulish, E. A. Zavarzin, A. Y. Prikhodko, N. M. Prokhoshin, Y. V. Kruchinina, N. P. Goncharov, E. G. Komyshev, M. A. Genaev

Research output: Contribution to journalArticlepeer-review

1 Citation (Scopus)


Intraspecif ic classif ication of cultivated plants is necessary for the conservation of biological diversity, study of their origin and their phylogeny. The modern cultivated wheat species originated from three wild diploid ancestors as a result of several rounds of genome doubling and are represented by di-, tetra-and hexaploid species. The identif ication of wheat ploidy level is one of the main stages of their taxonomy. Such classif ication is possible based on visual analysis of the wheat spike traits. The aim of this study is to investigate the morphological characteristics of spikes for hexa-and tetraploid wheat species based on the method of high-performance phenotyping. Phenotyping of the quantitative characteristics of the spike of 17 wheat species (595 plants, 3348 images), including eight tetraploids (Triticum aethiopicum, T. dicoccoides, T. dicoccum, T. durum, T. militinae, T. polonicum, T. timopheevii, and T. turgidum) and nine hexaploids (T. compactum, T. aestivum, i:ANK-23 (near-isogenic line of T. aestivum cv. Novosibirskaya 67), T. antiquorum, T. spelta (including cv. Rother Sommer Kolben), T. petropavlovskyi, T. yunnanense, T. macha, T. sphaerococcum, and T. vavilovii), was performed. Wheat spike morphology was described on the basis of nine quantitative traits including shape, size and awns area of the spike. The traits were obtained as a result of image analysis using the WERecognizer program. A cluster analysis of plants according to the characteristics of the spike shape and comparison of their distributions in tetraploid and hexaploid species showed a higher variability of traits in hexaploid species compared to tetraploid ones. At the same time, the species themselves form two clusters in the visual characteristics of the spike. One type is predominantly hexaploid species (with the exception of one tetraploid, T. dicoccoides). The other group includes tetraploid ones (with the exception of three hexaploid ones, T. compactum, T. antiquorum, T. sphaerococcum, and i:ANK-23). Thus, it has been shown that the morphological characteristics of spikes for hexaploid and tetraploid wheat species, obtained on the basis of computer analysis of images, include differences, which are further used to develop methods for plant classif ications by ploidy level and their species in an automatic mode.

Translated title of the contributionAutomatic morphology phenotyping of tetra-and hexaploid wheat spike using computer vision methods
Original languageRussian
Article number8
Pages (from-to)71-81
Number of pages11
JournalVavilovskii Zhurnal Genetiki i Selektsii
Issue number1
Publication statusPublished - 2021


  • Biotechnology
  • Computer vision
  • Image processing
  • Machine learning
  • Phenomics
  • Wheat
  • Wheat spike morphology



State classification of scientific and technological information

  • 34 BIOLOGY


Dive into the research topics of 'Automatic morphology phenotyping of tetra-and hexaploid wheat spike using computer vision methods'. Together they form a unique fingerprint.

Cite this