Login / Signup

HairNet: a deep learning model to score leaf hairiness, a key phenotype for cotton fibre yield, value and insect resistance.

Vivien RollandMoshiur R FaraziWarren C ConatyDeon CameronShiming M LiuLars PeterssonWarwick N Stiller
Published in: Plant methods (2022)
HairNet classifies images of cotton leaves according to their hairiness with very high accuracy. The simple imaging methodology presented in this study and the high accuracy on a single image per leaf achieved by HairNet demonstrates that it is implementable at scale. We propose that HairNet replaces the current visual scoring of this trait. The HairNet code and dataset can be used as a baseline to measure this trait in other species or to score other microscopic but important phenotypes.
Keyphrases
  • deep learning
  • convolutional neural network
  • artificial intelligence
  • genome wide
  • high resolution
  • machine learning
  • dna methylation
  • mass spectrometry
  • zika virus