Deep Machine Learning provides state-of-the-art performance in image-based plant phenotyping

  1. Michael P. Pound
  2. Alexandra J. Burgess
  3. Michael H. Wilson
  4. Jonathan A. Atkinson
  5. Marcus Griffiths
  6. Aaron S. Jackson
  7. Adrian Bulat
  8. yorgos Tzimiropoulos
  9. Darren M. Wells
  10. Erik H. Murchie
  11. Tony P. Pridmore
  12. Andrew P. French

Reviewed by

Read the full article

Listed in

Log in to save this article

Abstract

Deep learning is an emerging field that promises unparalleled results on many data analysis problems. We show the success offered by such techniques when applied to the challenging problem of image-based plant phenotyping, and demonstrate state-of-the-art results for root and shoot feature identification and localisation. We predict a paradigm shift in image-based phenotyping thanks to deep learning approaches.

Article activity feed

  1. GigaScience

    Now published in GigaScience doi: 10.1093/gigascience/gix083

    Michael P. Pound 1The School of Computer Science, University of Nottingham,UKFind this author on Google ScholarFind this author on PubMedSearch for this author on this siteORCID record for Michael P. PoundAlexandra J. Burgess 2The School of Biosciences, University of Nottingham, UKFind this author on Google ScholarFind this author on PubMedSearch for this author on this siteORCID record for Alexandra J. BurgessMichael H. Wilson 3Centre for Plant Sciences, Faculty of Biological Sciences, University of Leeds, Leeds, UKFind this author on Google ScholarFind this author on PubMedSearch for this author on this siteORCID record for Michael H. WilsonJonathan A. Atkinson 2The School of Biosciences, University of Nottingham, UKFind this author on Google ScholarFind this author on PubMedSearch for this author on this siteORCID record for Jonathan A. AtkinsonMarcus Griffiths 2The School of Biosciences, University of Nottingham, UKFind this author on Google ScholarFind this author on PubMedSearch for this author on this siteAaron S. Jackson 1The School of Computer Science, University of Nottingham,UKFind this author on Google ScholarFind this author on PubMedSearch for this author on this siteAdrian Bulat 1The School of Computer Science, University of Nottingham,UKFind this author on Google ScholarFind this author on PubMedSearch for this author on this siteyorgos Tzimiropoulos 1The School of Computer Science, University of Nottingham,UKFind this author on Google ScholarFind this author on PubMedSearch for this author on this siteORCID record for yorgos TzimiropoulosDarren M. Wells 2The School of Biosciences, University of Nottingham, UKFind this author on Google ScholarFind this author on PubMedSearch for this author on this siteORCID record for Darren M. WellsErik H. Murchie 2The School of Biosciences, University of Nottingham, UKFind this author on Google ScholarFind this author on PubMedSearch for this author on this siteORCID record for Erik H. MurchieTony P. Pridmore 1The School of Computer Science, University of Nottingham,UKFind this author on Google ScholarFind this author on PubMedSearch for this author on this siteORCID record for Tony P. PridmoreAndrew P. French 1The School of Computer Science, University of Nottingham,UK2The School of Biosciences, University of Nottingham, UKFind this author on Google ScholarFind this author on PubMedSearch for this author on this siteORCID record for Andrew P. FrenchFor correspondence: andrew.p.french@nottingham.ac.uk

    A version of this preprint has been published in the Open Access journal GigaScience (see paper https://doi.org/10.1093/gigascience/gix083 ), where the paper and peer reviews are published openly under a CC-BY 4.0 license.

    These peer reviews were as follows:

    Reviewer 1: http://dx.doi.org/10.5524/REVIEW.100812 Reviewer 2: http://dx.doi.org/10.5524/REVIEW.100813

  2. Version published to 10.1101/053033v1 on bioRxiv