A Performance Evaluation of Two Hyperspectral Imaging Systems for the Prediction of Strawberries’ Pomological Traits
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 infr...
| Published in: | Sensors |
|---|---|
| Main Authors: | , , , , |
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-12-01
|
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/1/174 |
| _version_ | 1850017758197055488 |
|---|---|
| author | Tiziana Amoriello Roberto Ciorba Gaia Ruggiero Monica Amoriello Roberto Ciccoritti |
| author_facet | Tiziana Amoriello Roberto Ciorba Gaia Ruggiero Monica Amoriello Roberto Ciccoritti |
| author_sort | Tiziana Amoriello |
| collection | DOAJ |
| container_title | Sensors |
| description | 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<sup>2</sup> = 0.959), DM (R<sup>2</sup> = 0.947), and TA (R<sup>2</sup> = 0.877), whereas good prediction was observed for FF (R<sup>2</sup> = 0.808). As for models from the SWIR system, good correlations were found between each of the physicochemical indices and the spectral information (R<sup>2</sup> = 0.924 for DM; R<sup>2</sup> = 0.898 for TSS; R<sup>2</sup> = 0.953 for TA; R<sup>2</sup> = 0.820 for FF). Finally, data fusion demonstrated a higher ability to predict fruit internal quality (R<sup>2</sup> = 0.942 for DM; R<sup>2</sup> = 0. 981 for TSS; R<sup>2</sup> = 0.976 for TA; R<sup>2</sup> = 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. |
| format | Article |
| id | doaj-art-9d40a1f4e57a4a168d34f04ba7b2ffc0 |
| institution | Directory of Open Access Journals |
| issn | 1424-8220 |
| language | English |
| publishDate | 2023-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| spelling | doaj-art-9d40a1f4e57a4a168d34f04ba7b2ffc02025-08-20T00:41:22ZengMDPI AGSensors1424-82202023-12-0124117410.3390/s24010174A Performance Evaluation of Two Hyperspectral Imaging Systems for the Prediction of Strawberries’ Pomological TraitsTiziana Amoriello0Roberto Ciorba1Gaia Ruggiero2Monica Amoriello3Roberto Ciccoritti4CREA—Research Centre for Food and Nutrition, Via Ardeatina 546, 00178 Rome, ItalyCREA—Research Centre for Olive, Fruit and Citrus Crops, Via di Fioranello 52, 00134 Rome, ItalyCREA—Research Centre for Olive, Fruit and Citrus Crops, Via di Fioranello 52, 00134 Rome, ItalyCREA—Central Administration, Via Archimede 59, 00197 Rome, ItalyCREA—Research Centre for Olive, Fruit and Citrus Crops, Via di Fioranello 52, 00134 Rome, ItalyPomological 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<sup>2</sup> = 0.959), DM (R<sup>2</sup> = 0.947), and TA (R<sup>2</sup> = 0.877), whereas good prediction was observed for FF (R<sup>2</sup> = 0.808). As for models from the SWIR system, good correlations were found between each of the physicochemical indices and the spectral information (R<sup>2</sup> = 0.924 for DM; R<sup>2</sup> = 0.898 for TSS; R<sup>2</sup> = 0.953 for TA; R<sup>2</sup> = 0.820 for FF). Finally, data fusion demonstrated a higher ability to predict fruit internal quality (R<sup>2</sup> = 0.942 for DM; R<sup>2</sup> = 0. 981 for TSS; R<sup>2</sup> = 0.976 for TA; R<sup>2</sup> = 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.https://www.mdpi.com/1424-8220/24/1/174quality attributesvisible–near infrared systemshort-wave infrared systemartificial neural networksdata fusion |
| spellingShingle | Tiziana Amoriello Roberto Ciorba Gaia Ruggiero Monica Amoriello Roberto Ciccoritti A Performance Evaluation of Two Hyperspectral Imaging Systems for the Prediction of Strawberries’ Pomological Traits quality attributes visible–near infrared system short-wave infrared system artificial neural networks data fusion |
| title | A Performance Evaluation of Two Hyperspectral Imaging Systems for the Prediction of Strawberries’ Pomological Traits |
| title_full | A Performance Evaluation of Two Hyperspectral Imaging Systems for the Prediction of Strawberries’ Pomological Traits |
| title_fullStr | A Performance Evaluation of Two Hyperspectral Imaging Systems for the Prediction of Strawberries’ Pomological Traits |
| title_full_unstemmed | A Performance Evaluation of Two Hyperspectral Imaging Systems for the Prediction of Strawberries’ Pomological Traits |
| title_short | A Performance Evaluation of Two Hyperspectral Imaging Systems for the Prediction of Strawberries’ Pomological Traits |
| title_sort | performance evaluation of two hyperspectral imaging systems for the prediction of strawberries pomological traits |
| topic | quality attributes visible–near infrared system short-wave infrared system artificial neural networks data fusion |
| url | https://www.mdpi.com/1424-8220/24/1/174 |
| work_keys_str_mv | AT tizianaamoriello aperformanceevaluationoftwohyperspectralimagingsystemsforthepredictionofstrawberriespomologicaltraits AT robertociorba aperformanceevaluationoftwohyperspectralimagingsystemsforthepredictionofstrawberriespomologicaltraits AT gaiaruggiero aperformanceevaluationoftwohyperspectralimagingsystemsforthepredictionofstrawberriespomologicaltraits AT monicaamoriello aperformanceevaluationoftwohyperspectralimagingsystemsforthepredictionofstrawberriespomologicaltraits AT robertociccoritti aperformanceevaluationoftwohyperspectralimagingsystemsforthepredictionofstrawberriespomologicaltraits AT tizianaamoriello performanceevaluationoftwohyperspectralimagingsystemsforthepredictionofstrawberriespomologicaltraits AT robertociorba performanceevaluationoftwohyperspectralimagingsystemsforthepredictionofstrawberriespomologicaltraits AT gaiaruggiero performanceevaluationoftwohyperspectralimagingsystemsforthepredictionofstrawberriespomologicaltraits AT monicaamoriello performanceevaluationoftwohyperspectralimagingsystemsforthepredictionofstrawberriespomologicaltraits AT robertociccoritti performanceevaluationoftwohyperspectralimagingsystemsforthepredictionofstrawberriespomologicaltraits |