Evaluation of the ripening stages of apple (Golden Delicious) by means of computer vision system

Research output: Contribution to journalArticle

21 Citations (Scopus)

Abstract

© 2017 IAgrE Mexican apple production suffers high losses due to poor handling in processing. Implementation of a straightforward, low cost method to sort apples by their ripening stage is required. A set of Golden Delicious apples was used to monitor their physicochemical properties and external colour, a second set of apples was used to validate the method. To classify the stages, a ripening index (RPI) was proposed, in which three stages were identified; unripe, ripe and senescent. Weibull model was applied to the physicochemical parameters in order to describe their kinetic behaviour. The three RPI stages were compared with colour variability using the CIELab colour space, chroma (C∗) and hue angle (h∗), allowing the identification of the three ripening stages. Principal component analysis was used to evaluate the correlation between variables. A first correlation was performed between physicochemical and colour parameters and variables correlated correctly between each other except for L∗, but both described the samples variability with 91.05% reliability. Using only colour parameters, the samples were described accurately with 95.06% reliability. Multivariate discriminant analysis (MDA) was done in order to validate the method. A cross-validation was performed with an initial set of apples used as trial samples and a second set of apples for validation. MDA was capable of classifying apples in their correct ripening stage with 100% accuracy. A second analysis was carried out using four colour parameters (a∗, b∗, C and h∗), and results indicated that the ripening stages can be classified with 100% accuracy.
Original languageAmerican English
Pages (from-to)46-58
Number of pages40
JournalBiosystems Engineering
DOIs
StatePublished - 1 Jul 2017

Fingerprint

computer vision
Artificial Intelligence
ripening
Malus
Computer vision
apples
Color
color
evaluation
Discriminant analysis
discriminant analysis
Discriminant Analysis
Multivariate Analysis
physicochemical property
principal components analysis
classifying
Principal component analysis
Principal Component Analysis
principal component analysis
sampling

Cite this

@article{d85ab82a51824400b041f74be42d1a95,
title = "Evaluation of the ripening stages of apple (Golden Delicious) by means of computer vision system",
abstract = "{\circledC} 2017 IAgrE Mexican apple production suffers high losses due to poor handling in processing. Implementation of a straightforward, low cost method to sort apples by their ripening stage is required. A set of Golden Delicious apples was used to monitor their physicochemical properties and external colour, a second set of apples was used to validate the method. To classify the stages, a ripening index (RPI) was proposed, in which three stages were identified; unripe, ripe and senescent. Weibull model was applied to the physicochemical parameters in order to describe their kinetic behaviour. The three RPI stages were compared with colour variability using the CIELab colour space, chroma (C∗) and hue angle (h∗), allowing the identification of the three ripening stages. Principal component analysis was used to evaluate the correlation between variables. A first correlation was performed between physicochemical and colour parameters and variables correlated correctly between each other except for L∗, but both described the samples variability with 91.05{\%} reliability. Using only colour parameters, the samples were described accurately with 95.06{\%} reliability. Multivariate discriminant analysis (MDA) was done in order to validate the method. A cross-validation was performed with an initial set of apples used as trial samples and a second set of apples for validation. MDA was capable of classifying apples in their correct ripening stage with 100{\%} accuracy. A second analysis was carried out using four colour parameters (a∗, b∗, C and h∗), and results indicated that the ripening stages can be classified with 100{\%} accuracy.",
author = "Stefany C{\'a}rdenas-P{\'e}rez and Jorge Chanona-P{\'e}rez and M{\'e}ndez-M{\'e}ndez, {Juan V.} and Georgina Calder{\'o}n-Dom{\'i}nguez and Rub{\'e}n L{\'o}pez-Santiago and Perea-Flores, {Mar{\'i}a J.} and Israel Arzate-V{\'a}zquez",
year = "2017",
month = "7",
day = "1",
doi = "10.1016/j.biosystemseng.2017.04.009",
language = "American English",
pages = "46--58",
journal = "Biosystems Engineering",
issn = "1537-5110",
publisher = "Academic Press Inc.",

}

TY - JOUR

T1 - Evaluation of the ripening stages of apple (Golden Delicious) by means of computer vision system

AU - Cárdenas-Pérez, Stefany

AU - Chanona-Pérez, Jorge

AU - Méndez-Méndez, Juan V.

AU - Calderón-Domínguez, Georgina

AU - López-Santiago, Rubén

AU - Perea-Flores, María J.

AU - Arzate-Vázquez, Israel

PY - 2017/7/1

Y1 - 2017/7/1

N2 - © 2017 IAgrE Mexican apple production suffers high losses due to poor handling in processing. Implementation of a straightforward, low cost method to sort apples by their ripening stage is required. A set of Golden Delicious apples was used to monitor their physicochemical properties and external colour, a second set of apples was used to validate the method. To classify the stages, a ripening index (RPI) was proposed, in which three stages were identified; unripe, ripe and senescent. Weibull model was applied to the physicochemical parameters in order to describe their kinetic behaviour. The three RPI stages were compared with colour variability using the CIELab colour space, chroma (C∗) and hue angle (h∗), allowing the identification of the three ripening stages. Principal component analysis was used to evaluate the correlation between variables. A first correlation was performed between physicochemical and colour parameters and variables correlated correctly between each other except for L∗, but both described the samples variability with 91.05% reliability. Using only colour parameters, the samples were described accurately with 95.06% reliability. Multivariate discriminant analysis (MDA) was done in order to validate the method. A cross-validation was performed with an initial set of apples used as trial samples and a second set of apples for validation. MDA was capable of classifying apples in their correct ripening stage with 100% accuracy. A second analysis was carried out using four colour parameters (a∗, b∗, C and h∗), and results indicated that the ripening stages can be classified with 100% accuracy.

AB - © 2017 IAgrE Mexican apple production suffers high losses due to poor handling in processing. Implementation of a straightforward, low cost method to sort apples by their ripening stage is required. A set of Golden Delicious apples was used to monitor their physicochemical properties and external colour, a second set of apples was used to validate the method. To classify the stages, a ripening index (RPI) was proposed, in which three stages were identified; unripe, ripe and senescent. Weibull model was applied to the physicochemical parameters in order to describe their kinetic behaviour. The three RPI stages were compared with colour variability using the CIELab colour space, chroma (C∗) and hue angle (h∗), allowing the identification of the three ripening stages. Principal component analysis was used to evaluate the correlation between variables. A first correlation was performed between physicochemical and colour parameters and variables correlated correctly between each other except for L∗, but both described the samples variability with 91.05% reliability. Using only colour parameters, the samples were described accurately with 95.06% reliability. Multivariate discriminant analysis (MDA) was done in order to validate the method. A cross-validation was performed with an initial set of apples used as trial samples and a second set of apples for validation. MDA was capable of classifying apples in their correct ripening stage with 100% accuracy. A second analysis was carried out using four colour parameters (a∗, b∗, C and h∗), and results indicated that the ripening stages can be classified with 100% accuracy.

UR - https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=85019035047&origin=inward

UR - https://www.scopus.com/inward/citedby.uri?partnerID=HzOxMe3b&scp=85019035047&origin=inward

U2 - 10.1016/j.biosystemseng.2017.04.009

DO - 10.1016/j.biosystemseng.2017.04.009

M3 - Article

SP - 46

EP - 58

JO - Biosystems Engineering

JF - Biosystems Engineering

SN - 1537-5110

ER -