RT Journal Article SR Electronic T1 Deep Machine Learning provides state-of-the-art performance in image-based plant phenotyping JF bioRxiv FD Cold Spring Harbor Laboratory SP 053033 DO 10.1101/053033 A1 Michael P. Pound A1 Alexandra J. Burgess A1 Michael H. Wilson A1 Jonathan A. Atkinson A1 Marcus Griffiths A1 Aaron S. Jackson A1 Adrian Bulat A1 yorgos Tzimiropoulos A1 Darren M. Wells A1 Erik H. Murchie A1 Tony P. Pridmore A1 Andrew P. French YR 2016 UL http://biorxiv.org/content/early/2016/05/12/053033.abstract AB 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.