Ontology highlight
ABSTRACT:
SUBMITTER: Toda Y
PROVIDER: S-EPMC7160130 | biostudies-literature | 2020 Apr
REPOSITORIES: biostudies-literature
Toda Yosuke Y Okura Fumio F Ito Jun J Okada Satoshi S Kinoshita Toshinori T Tsuji Hiroyuki H Saisho Daisuke D
Communications biology 20200415 1
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 i ...[more]