Skip to main content

Plants in computer vision

New Content Item

Edited by: Dr Hannah Dee

An article collection in Plant Methods.

New methods in plant biology have led to an explosion in data types and methods of data acquisition, and much of this data is image- or video- based in nature. Computer vision, image analysis and image processing techniques are being applied to more plant data than ever before.

Inspired by the BVMA Technical Meeting: Plants in Computer Vision, this Plant Methods article collection showcases original work on the boundary between computer vision and plant science; specifically concentrating on computer algorithms, methods and systems which analyse plant images, videos and scans.  

This collection includes work on plant detection, segmentation and modelling from image data, at many different scales (from microscopic images up to field scale measurements). Some articles describe complete software, ready for biologists to use today. Other articles explore algorithm development, pointing the way towards future software capabilities.

This collection of articles has not been sponsored and articles have undergone the journal's standard peer-review process overseen by the Editors. The Editors declare no competing interests.

  1. High resolution and high throughput genotype to phenotype studies in plants are underway to accelerate breeding of climate ready crops. In the recent years, deep learning techniques and in particular Convoluti...

    Authors: Sarah Taghavi Namin, Mohammad Esmaeilzadeh, Mohammad Najafi, Tim B. Brown and Justin O. Borevitz
    Citation: Plant Methods 2018 14:66
  2. The model species Arabidopsis thaliana has extensive resources to investigate intraspecific trait variability and the genetic bases of ecologically relevant traits. However, the cost of equipment and software req...

    Authors: François Vasseur, Justine Bresson, George Wang, Rebecca Schwab and Detlef Weigel
    Citation: Plant Methods 2018 14:63
  3. The current state-of-the-art for field wood identification to combat illegal logging relies on experienced practitioners using hand lenses, specialized identification keys, atlases of woods, and field manuals....

    Authors: Prabu Ravindran, Adriana Costa, Richard Soares and Alex C. Wiedenhoeft
    Citation: Plant Methods 2018 14:25
  4. Deep learning presents many opportunities for image-based plant phenotyping. Here we consider the capability of deep convolutional neural networks to perform the leaf counting task. Deep learning techniques ty...

    Authors: Jordan Ubbens, Mikolaj Cieslak, Przemyslaw Prusinkiewicz and Ian Stavness
    Citation: Plant Methods 2018 14:6
  5. Miscanthus is a leading second generation bio-energy crop. It is mostly rhizome propagated; however, the increasing use of seed is resulting in a greater need to investigate germination. Miscanthus seed are small...

    Authors: Danny Awty-Carroll, John Clifton-Brown and Paul Robson
    Citation: Plant Methods 2018 14:5
  6. Plants demonstrate dynamic growth phenotypes that are determined by genetic and environmental factors. Phenotypic analysis of growth features over time is a key approach to understand how plants interact with ...

    Authors: Ji Zhou, Christopher Applegate, Albor Dobon Alonso, Daniel Reynolds, Simon Orford, Michal Mackiewicz, Simon Griffiths, Steven Penfield and Nick Pullen
    Citation: Plant Methods 2017 13:117
  7. Fine-grained recognition of plants from images is a challenging computer vision task, due to the diverse appearance and complex structure of plants, high intra-class variability and small inter-class differenc...

    Authors: Milan Šulc and Jiří Matas
    Citation: Plant Methods 2017 13:115
  8. Developmental biology has made great strides in recent years towards the quantification of cellular properties during development. This requires tissues to be imaged and segmented to generate computerised vers...

    Authors: Annamária Kiss, Typhaine Moreau, Vincent Mirabet, Cerasela Iliana Calugaru, Arezki Boudaoud and Pradeep Das
    Citation: Plant Methods 2017 13:114
  9. Plant science uses increasing amounts of phenotypic data to unravel the complex interactions between biological systems and their variable environments. Originally, phenotyping approaches were limited by manua...

    Authors: Benoît Valle, Thierry Simonneau, Romain Boulord, Francis Sourd, Thibault Frisson, Maxime Ryckewaert, Philippe Hamard, Nicolas Brichet, Myriam Dauzat and Angélique Christophe
    Citation: Plant Methods 2017 13:98
  10. Automated species identification is a long term research subject. Contrary to flowers and fruits, leaves are available throughout most of the year. Offering margin and texture to characterize a species, they a...

    Authors: Michael Rzanny, Marco Seeland, Jana Wäldchen and Patrick Mäder
    Citation: Plant Methods 2017 13:97
  11. In maize, silks are hundreds of filaments that simultaneously emerge from the ear for collecting pollen over a period of 1–7 days, which largely determines grain number especially under water deficit. Silk gro...

    Authors: Nicolas Brichet, Christian Fournier, Olivier Turc, Olivier Strauss, Simon Artzet, Christophe Pradal, Claude Welcker, François Tardieu and Llorenç Cabrera-Bosquet
    Citation: Plant Methods 2017 13:96
  12. Improvements in high-throughput phenotyping technologies are rapidly expanding the scope and capacity of plant biology studies to measure growth traits. Nevertheless, the costs of commercial phenotyping equipm...

    Authors: Andrei Dobrescu, Livia C. T. Scorza, Sotirios A. Tsaftaris and Alistair J. McCormick
    Citation: Plant Methods 2017 13:95
  13. Accurate and quantitative phenotypic data in plant breeding programmes is vital in breeding to assess the performance of genotypes and to make selections. Traditional strawberry phenotyping relies on the human...

    Authors: Joe Q. He, Richard J. Harrison and Bo Li
    Citation: Plant Methods 2017 13:93
  14. Wheat is one of the most widely grown crop in temperate climates for food and animal feed. In order to meet the demands of the predicted population increase in an ever-changing climate, wheat production needs ...

    Authors: Aoife Hughes, Karen Askew, Callum P. Scotson, Kevin Williams, Colin Sauze, Fiona Corke, John H. Doonan and Candida Nibau
    Citation: Plant Methods 2017 13:76
  15. Hyperspectral imaging is a technology that can be used to monitor plant responses to stress. Hyperspectral images have a full spectrum for each pixel in the image, 400–2500 nm in this case, giving detailed inf...

    Authors: Dominic Williams, Avril Britten, Susan McCallum, Hamlyn Jones, Matt Aitkenhead, Alison Karley, Ken Loades, Ankush Prashar and Julie Graham
    Citation: Plant Methods 2017 13:74