Rxivist logo

Simulated Plant Images Improve Maize Leaf Counting Accuracy

By Chenyong Miao, Thomas P. Hoban, Alejandro Pages, Zheng Xu, Eric Rodene, Jordan Ubbens, Ian Stavness, Jinliang Yang, James C Schnable

Posted 18 Jul 2019
bioRxiv DOI: 10.1101/706994

Automatically scoring plant traits using a combination of imaging and deep learning holds promise to accelerate data collection, scientific inquiry, and breeding progress. However, applications of this approach are currently held back by the availability of large and suitably annotated training datasets. Early training datasets targeted arabidopsis or tobacco. The morphology of these plants quite different from that of grass species like maize. Two sets of maize training data, one real-world and one synthetic were generated and annotated for late vegetative stage maize plants using leaf count as a model trait. Convolutional neural networks (CNNs) trained on entirely synthetic data provided predictive power for scoring leaf number in real-world images. This power was less than CNNs trained with equal numbers of real-world images, however, in some cases CNNs trained with larger numbers of synthetic images outperformed CNNs trained with smaller numbers of real-world images. When real-world training images were scarce, augmenting real-world training data with synthetic data provided improved prediction accuracy. Quantifying leaf number over time can provide insight into plant growth rates and stress responses, and can help to parameterize crop growth models. The approaches and annotated training data described here may help future efforts to develop accurate leaf counting algorithms for maize.

Download data

  • Downloaded 923 times
  • Download rankings, all-time:
    • Site-wide: 29,855
    • In plant biology: 491
  • Year to date:
    • Site-wide: 56,042
  • Since beginning of last month:
    • Site-wide: 66,486

Altmetric data

Downloads over time

Distribution of downloads per paper, site-wide