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

Abstract

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.

Code and data availability

The paper describes root tip and shoot feature image datasets and CNN models/scripts that the authors state will be made publicly available, but no public URL, repository, or identifier is provided in any supplied block, so no qualifying asset is actionable.

No evidence-backed public reproduction asset is currently recorded.