Plant segmentation by supervised machine learning methods

Authors

Jason Adams, University of Nebraska-LincolnFollow
Yumou Qiu, University of Nebraska-LincolnFollow
Yuhang Xu, University of Nebraska-Lincoln
James C. Schnable, University of Nebraska-LincolnFollow

ORCID IDs

Jason Adams

Yumou Qiu

Yuhang Xu

James C. Schnable

Document Type

Article

Date of this Version

2020

Citation

Adams J, Qiu Y, Xu Y, Schnable JC. Plant segmentation by supervised machine learning methods. Plant Phenome J. 2020;3:e20001. https://doi.org/10.1002/ppj2.20001

Comments

© 2020 The Authors.

Abstract

High-throughput phenotyping systems provide abundant data for statistical analysis through plant imaging. Before usable data can be obtained, image processing must take place. In this study, we used supervised learning methods to segment plants from the background in such images and compared them with commonly used thresholding methods. Because obtaining accurate training data is a major obstacle to using supervised learning methods for segmentation, a novel approach to producing accurate labels was developed. We demonstrated that, with careful selection of training data through such an approach, supervised learning methods, and neural networks in particular, can outperform thresholding methods at segmentation.