Training instance segmentation neural network with synthetic datasets for crop seed phenotyping

Yosuke Toda, Fumio Okura, Jun Ito, Satoshi Okada, Toshinori Kinoshita, Hiroyuki Tsuji, Daisuke Saisho

Research output: Contribution to journalArticlepeer-review

Abstract

In order to train the neural network for plant phenotyping, a sufficient amount of training data must be prepared, which requires time-consuming manual data annotation process that often becomes the limiting step. Here, we show that an instance segmentation neural network aimed to phenotype the barley seed morphology of various cultivars, can be sufficiently trained purely by a synthetically generated dataset. Our attempt is based on the concept of domain randomization, where a large amount of image is generated by randomly orienting the seed object to a virtual canvas. The trained model showed 96% recall and 95% average Precision against the real-world test dataset. We show that our approach is effective also for various crops including rice, lettuce, oat, and wheat. Constructing and utilizing such synthetic data can be a powerful method to alleviate human labor costs for deploying deep learning-based analysis in the agricultural domain.

Original languageEnglish
Article number173
JournalCommunications Biology
Volume3
Issue number1
DOIs
Publication statusPublished - Dec 1 2020

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)
  • Medicine (miscellaneous)

Fingerprint Dive into the research topics of 'Training instance segmentation neural network with synthetic datasets for crop seed phenotyping'. Together they form a unique fingerprint.

Cite this