Color and Grey-Level Co-Occurrence Matrix Analysis for Predicting Sensory and Biochemical Traits in Sweet Potato and Potato.

Abstract

In sweet potato and potato, sensory traits are critical for acceptance by consumers, growers, and traders, hence underpinning the success or failure of a new cultivar. A quick analytical method for the sensory traits could expedite the selection process in breeding programs. In this paper, the relationship between sensory panel and instrumental color plus texture features was evaluated. Results have shown a high correlation between the sensory panel and instrumental color in both sweet potato (up to r = 0.84) and potato ( r > 0.78), implying that imaging is a potential alternative to the sensory panel for color scoring. High correlations between sensory panel aroma and flavor with instrumental color were detected (up to r = 0.66), although the validity of these correlations needs to be tested. With instrumental color and texture parameters as predictors, low to moderate accuracy was detected in the machine learning models developed to predict sensory panel traits. Overall, the performance of the eXtreme Gradient Boosting (XGboost) was comparable to the radial-based support vector machine (NL-SVM) algorithm, and these could be used for the initial selection of genotypes for aromas and flavors ( r 2 = 0.64-0.72) and texture attributes like moisture or mealiness ( r 2 > 50). Among the chemical properties screened in sweet potato, only starch showed a moderate correlation with sensory features like mealiness ( r = 0.54) and instrumental color ( r = 0.65). From the results, we can conclude that the instrumental scores of color are equivalent to those scored by the sensory panel, and the former could be adopted for quick analysis. Further investigations may be required to understand the association between color and aroma or flavor.

Plant phenotyping relevance

育種選抜を目的に、画像由来の色・テクスチャ特徴と機械学習でサツマイモ・ジャガイモの感覚形質を推定し、官能評価との相関・予測精度を検証しているため、表現型取得・推定法が中心である。

Code and data availability

The article states data are available only within the article and its supporting information (summary statistics/correlation tables, not raw phenotype or image data). No author analysis code, scripts, models, or public data deposit is provided. The glcm R package is a generic third-party library, and the SweetGAINS URL

No evidence-backed public reproduction asset is currently recorded.