Corrigendum: Deep Plant Phenomics: A Deep Learning Platform for Complex Plant Phenotyping Tasks
- Department of Computer Science, University of Saskatchewan, Saskatoon, SK, Canada
by Ubbens, J. R., and Stavness, I. (2017). Front. Plant Sci. 8:1190. doi: 10.3389/fpls.2017.01190
The dataset referred to as the IPPN dataset (p. 4) in the original article is now referred to by its authors as the PRL dataset1. This dataset was used because it includes annotations for all three of the tasks performed in the validation experiments2. In the results on the leaf counting task (Table 2), the proposed method was compared against two results from the literature. However, the results reported in the cited papers were performed on a different version of the dataset, which is referred to by its authors as CVPPP 2015_LCC (for the leaf counting competition of the 2015 Computer Vision Problems in Plant Phenotyping workshop). Therefore, the direct comparison is not warranted. However, R2 between the actual and predicted leaf counts for the Plant/Ara2012, Plant/Ara2013-Canon, and Plant/Tobacco leaf counting datasets as presented in the article are 0.85, 0.90, and 0.74, respectively, demonstrating strong performance without the context of this comparison. This error does not change the scientific conclusions of the article in any way.
Conflict of Interest Statement
The authors declare that the research was conducted in the absence of any commercial or financial relationships that could be construed as a potential conflict of interest.
Keywords: phenotyping, deep learning, methods, computer vision, machine learning
Citation: Ubbens JR and Stavness I (2018) Corrigendum: Deep Plant Phenomics: A Deep Learning Platform for Complex Plant Phenotyping Tasks. Front. Plant Sci. 8:2245. doi: 10.3389/fpls.2017.02245
Received: 12 October 2017; Accepted: 20 December 2017;
Published: 15 January 2018.
Edited and reviewed by: Roger Deal, Emory University, United States
Copyright © 2018 Ubbens and Stavness. This is an open-access article distributed under the terms of the Creative Commons Attribution License (CC BY). The use, distribution or reproduction in other forums is permitted, provided the original author(s) or licensor are credited and that the original publication in this journal is cited, in accordance with accepted academic practice. No use, distribution or reproduction is permitted which does not comply with these terms.
*Correspondence: Ian Stavness, email@example.com