TY - JOUR
T1 - Training instance segmentation neural network with synthetic datasets for crop seed phenotyping
AU - Toda, Yosuke
AU - Okura, Fumio
AU - Ito, Jun
AU - Okada, Satoshi
AU - Kinoshita, Toshinori
AU - Tsuji, Hiroyuki
AU - Saisho, Daisuke
N1 - Funding Information:
We thank Labelbox for providing the access for the academic usage of dataset labeling. We thank Ms. Yoko Tomita at Nagoya University for assistance in the labor-intensive annotation to generate a ground-truth test dataset. We also thank Dr. Miya Mizutani for a comprehensive discussion and critical reading of the paper. The graphical abstract in Fig. 1 was rendered by Dr. Issey Takahashi who is a member of the Research Promotion Division in ITbM of Nagoya University. Dr. Shunsaku Nishiuchi provided Nipponbare rice seeds used in this study. Dr. Toshiaki Tameshige amplified and provided wheat seeds. Dr. Kentaro Shimizu amplified and provided wheat Arina seeds and Drs. Shigeo Takumi and Yoshihiro Matsuoka established, amplified, and provided synthetic wheat Ldn/KU-2076 (Syn01) seeds. This work was supported by Japan Science and Technology Agency (JST) PRESTO [Grants nos. JPMJPR17O5 (Y.T.) and JPMJPR17O3 (F.O.)], JST CREST [Grant Number JPMJCR16O4 (H.T., D.S., and S.O.)], MEXT KAKENHI [Numbers 16H06466 and 16H06464 (H.T.), 16KT0148 (D.S.), and 19K05975 (J.I.)], and JST ALCA [Number JPMJAL1011 (T.K.)]. All the barley materials are provided by the National BioResource Project (NBRP: Barley).
Publisher Copyright:
© 2020, The Author(s).
PY - 2020/12/1
Y1 - 2020/12/1
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85083478802&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85083478802&partnerID=8YFLogxK
U2 - 10.1038/s42003-020-0905-5
DO - 10.1038/s42003-020-0905-5
M3 - Article
C2 - 32296118
AN - SCOPUS:85083478802
VL - 3
JO - Communications Biology
JF - Communications Biology
SN - 2399-3642
IS - 1
M1 - 173
ER -