A Performance Evaluation of Two Hyperspectral Imaging Systems for the Prediction of Strawberries' Pomological Traits.

Abstract

Pomological traits are the major factors determining the quality and price of fresh fruits. This research was aimed to investigate the feasibility of using two hyperspectral imaging (HSI) systems in the wavelength regions comprising visible to near infrared (VisNIR) (400-1000 nm) and short-wave infrared (SWIR) (935-1720 nm) for predicting four strawberry quality attributes (firmness-FF, total soluble solid content-TSS, titratable acidity-TA, and dry matter-DM). Prediction models were developed based on artificial neural networks (ANN). The entire strawberry VisNIR reflectance spectra resulted in accurate predictions of TSS (R 2 = 0.959), DM (R 2 = 0.947), and TA (R 2 = 0.877), whereas good prediction was observed for FF (R 2 = 0.808). As for models from the SWIR system, good correlations were found between each of the physicochemical indices and the spectral information (R 2 = 0.924 for DM; R 2 = 0.898 for TSS; R 2 = 0.953 for TA; R 2 = 0.820 for FF). Finally, data fusion demonstrated a higher ability to predict fruit internal quality (R 2 = 0.942 for DM; R 2 = 0. 981 for TSS; R 2 = 0.976 for TA; R 2 = 0.951 for FF). The results confirmed the potential of these two HSI systems as a rapid and nondestructive tool for evaluating fruit quality and enhancing the product's marketability.

Plant phenotyping relevance

2種類のハイパースペクトル画像システムを用いてイチゴ果実の品質形質を非破壊推定し、ANNモデル、性能評価、データ融合を検証しており、フェノタイピング手法が中心である。

Code and data availability

The paper describes hyperspectral imaging of strawberries and ANN prediction models, but no public phenotype dataset, hyperspectral images, analysis code, or trained model deposit is mentioned. The supplementary materials contain only tables of ANN architectures and correlation coefficients, not the underlying data or.

No evidence-backed public reproduction asset is currently recorded.