TubAR: an R Package for Quantifying Tuber Shape and Skin Traits from Images

Abstract

Potato market value is heavily affected by tuber quality traits such as shape, color, and skinning. Despite this, potato breeders often rely on subjective scales that fail to precisely define phenotypes. Individual human evaluators and the environments in which ratings are taken can bias visual quality ratings. Collecting quality trait data using machine vision allows for precise measurements that will remain reliable between evaluators and breeding programs. Here we present TubAR (Tuber Analysis in R), an image analysis program designed to collect data for multiple tuber quality traits at low cost to breeders. To assess the efficacy of TubAR in comparison to visual scales, red-skinned potatoes were evaluated using both methods. Broad sense heritability was consistently higher for skinning, roundness, and length to width ratio using TubAR. TubAR collects essential data on fresh market potato breeding populations while maintaining efficiency by measuring multiple traits through one phenotyping protocol.

Plant phenotyping relevance

画像解析プログラムを開発し、ジャガイモ塊茎の形状・皮 traitsを定量化して目視評価と比較検証しているため、植物表現型取得法が中心です。

Code and data availability

The paper's authors publicly released the TubAR R package (source code, instructions, vignette, and sample tuber image data) on GitHub, directly implementing the image-analysis phenotyping pipeline described in the paper.