Detecting Maturity in Fresh <i>Lycium barbarum</i> L. Fruit Using Color Information

The accurate quantitative maturity detection of fresh <i>Lycium barbarum</i> L. (<i>L. barbarum</i>) fruit is the key to determine whether fruit are suitable for harvesting or not and can also be helpful to improve the quality of post-harvest processing. To achieve this goal,...

Full description

Bibliographic Details
Main Authors: Jian Zhao, Jun Chen
Format: Article
Language:English
Published: MDPI AG 2021-05-01
Series:Horticulturae
Subjects:
Online Access:https://www.mdpi.com/2311-7524/7/5/108
id doaj-6ba8c59244c442b7aba11d6302194232
record_format Article
spelling doaj-6ba8c59244c442b7aba11d63021942322021-05-31T23:38:47ZengMDPI AGHorticulturae2311-75242021-05-01710810810.3390/horticulturae7050108Detecting Maturity in Fresh <i>Lycium barbarum</i> L. Fruit Using Color InformationJian Zhao0Jun Chen1College of Mechanical and Electronic Engineering, Northwest A&F University, Xianyang 712100, ChinaCollege of Mechanical and Electronic Engineering, Northwest A&F University, Xianyang 712100, ChinaThe accurate quantitative maturity detection of fresh <i>Lycium barbarum</i> L. (<i>L. barbarum</i>) fruit is the key to determine whether fruit are suitable for harvesting or not and can also be helpful to improve the quality of post-harvest processing. To achieve this goal, abnormal samples were eliminated by the Mahalanobis Distance (MD), and nine components (i.e., R, G, B, H, S, V, L, a, and b) of the ripe fruit, half-ripe fruit, and unripe fruit were extracted, firstly. Then, significant component combinations of the three fruits beneficial to the extraction of their areas were determined. Through binary processing, morphology processing, and other image processing methods, a quantitative maturity detection model of fruit was established based on the support vector machine (SVM) model. On this basis, field experiments were conducted to verify and compare the relationship between the prediction results of the model and the picking forces of fruit. Field experiments showed that the accuracies of both the training set and prediction set were 100% and the prediction results of the model were consistent with the picking forces of fruit. Findings provided a theoretical basis for the accurate quantitative maturity detection of fresh <i>L. barbarum</i> fruit.https://www.mdpi.com/2311-7524/7/5/108<i>L.</i> <i>barbarum</i>maturity detectioncolor informationMahalanobis distanceimage processingsupport vector machine
collection DOAJ
language English
format Article
sources DOAJ
author Jian Zhao
Jun Chen
spellingShingle Jian Zhao
Jun Chen
Detecting Maturity in Fresh <i>Lycium barbarum</i> L. Fruit Using Color Information
Horticulturae
<i>L.</i> <i>barbarum</i>
maturity detection
color information
Mahalanobis distance
image processing
support vector machine
author_facet Jian Zhao
Jun Chen
author_sort Jian Zhao
title Detecting Maturity in Fresh <i>Lycium barbarum</i> L. Fruit Using Color Information
title_short Detecting Maturity in Fresh <i>Lycium barbarum</i> L. Fruit Using Color Information
title_full Detecting Maturity in Fresh <i>Lycium barbarum</i> L. Fruit Using Color Information
title_fullStr Detecting Maturity in Fresh <i>Lycium barbarum</i> L. Fruit Using Color Information
title_full_unstemmed Detecting Maturity in Fresh <i>Lycium barbarum</i> L. Fruit Using Color Information
title_sort detecting maturity in fresh <i>lycium barbarum</i> l. fruit using color information
publisher MDPI AG
series Horticulturae
issn 2311-7524
publishDate 2021-05-01
description The accurate quantitative maturity detection of fresh <i>Lycium barbarum</i> L. (<i>L. barbarum</i>) fruit is the key to determine whether fruit are suitable for harvesting or not and can also be helpful to improve the quality of post-harvest processing. To achieve this goal, abnormal samples were eliminated by the Mahalanobis Distance (MD), and nine components (i.e., R, G, B, H, S, V, L, a, and b) of the ripe fruit, half-ripe fruit, and unripe fruit were extracted, firstly. Then, significant component combinations of the three fruits beneficial to the extraction of their areas were determined. Through binary processing, morphology processing, and other image processing methods, a quantitative maturity detection model of fruit was established based on the support vector machine (SVM) model. On this basis, field experiments were conducted to verify and compare the relationship between the prediction results of the model and the picking forces of fruit. Field experiments showed that the accuracies of both the training set and prediction set were 100% and the prediction results of the model were consistent with the picking forces of fruit. Findings provided a theoretical basis for the accurate quantitative maturity detection of fresh <i>L. barbarum</i> fruit.
topic <i>L.</i> <i>barbarum</i>
maturity detection
color information
Mahalanobis distance
image processing
support vector machine
url https://www.mdpi.com/2311-7524/7/5/108
work_keys_str_mv AT jianzhao detectingmaturityinfreshilyciumbarbarumilfruitusingcolorinformation
AT junchen detectingmaturityinfreshilyciumbarbarumilfruitusingcolorinformation
_version_ 1721416938685464576