@article{feldman_scalable_2023,
  author = {Feldman, Max J. and Park, Jaebum and Miller, Nathan and Wakholi, Collins and Greene, Katelyn and Abbasi, Arash and Rippner, Devin A. and Navarre, Duroy and Schmitz Carley, Cari and Shannon, Laura M. and Novy, Rich},
  title = {A scalable, low-cost phenotyping strategy to assess tuber size, shape, and the colorimetric features of tuber skin and flesh in potato breeding populations},
  journal = {The Plant Phenome Journal},
  volume = {7},
  number = {1},
  pages = {e20099},
  doi = {https://doi.org/10.1002/ppj2.20099},
  url = {https://acsess.onlinelibrary.wiley.com/doi/abs/10.1002/ppj2.20099},
  eprint = {https://acsess.onlinelibrary.wiley.com/doi/pdf/10.1002/ppj2.20099},
  year = {2024},
  tldr = {Measures the following traits from images: length and width, aspect ratio, eccentricity, biomass profiles; uses a size marker in images. Color assessed of skin and flesh in consumer camera and flat-bed scanner images, uses color checker and perform color calibration. Deep learning to classify halved tubers as possessing the hollow heart defect. Lists tools to automate capture with python and links to code. Population of 189 tubers.}
}

Abstract Tuber size, shape, colorimetric characteristics, and defect susceptibility are all factors that influence the acceptance of new potato cultivars. Despite the importance of these characteristics, our understanding of their inheritance is substantially limited by our inability to precisely measure these features quantitatively on the scale needed to evaluate breeding populations. To alleviate this bottleneck, we developed a low-cost, semiautomated workflow to capture data and measure each of these characteristics using machine vision. This workflow was applied to assess the phenotypic variation present within 189 F1 progeny of the A08241 breeding population. Machine vision was applied to estimate linear and volumetric tuber size, assess tuber shape characteristics using aspect ratio and biomass profiles, and quantify tuber skin and flesh color; additionally, a deep learning mode was developed to classify the presence of hollow-heart defect. Our results provide an example of quantitative measurements acquired using machine vision methods that are reliable, heritable, and capable of being used to understand and select multiple traits simultaneously in structured potato breeding populations.

Publisher: http://doi.org/https://doi.org/10.1002/ppj2.20099