.png){kind=icon}
.png){kind=icon}
Return
Advancements in Citrus Quality Assessment: Utilizing X-ray Imaging with CitrusnetQuality Model for Non-Destructive Evaluation
.png){kind=icon}
PRE
AI
S
Z
M
M
T
M
S
DOI：10.1007/s10921-025-01316-4.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Citrus is a globally consumed commodity. The quality of its fruit is crucial for marketability and consumer satisfaction. Traditional methods of assessing fruit quality rely on external characteristics, which may not accurately reflect internal attributes such as sweetness, acidity, and moisture content. The current study introduces non-destructive techniques, X-ray computed tomography (CT), and machine learning for automated quality evaluation of citrus (Satsuma). A dataset of citrus samples was developed under ambient conditions with 20–22 °C temper-ature and 50–60% humidity, and the other half citrus samples were placed under refrigerated conditions with 6–8 °C temperature and 65–75% humidity to analyze quality variations. The hypothesis of the”CitrusNetQuality” model integrated Random Forest Regressor, Gradient Boosting Regressor, Partial Least Squares Regression, K-Nearest Neighbors Regressor, and Support Vector Regression, com-bined with Wavelet Transforms and Principal Component Analysis for quality prediction. The model achieved high R2 values (0.97–0.98) and low MAE values (0.01–0.08) across key parameters, outperforming existing models. By integrat-ing X-ray CT and machine learning,”CitrusNetQuality” was enhanced by fruit quality evaluation, reducing assessment challenges and improving consumer sat-isfaction. This study provided a non-destructive tool for precise citrus quality assessment.
Keywords:
Computer vision
Postharvest quality evaluation
Non-destructive analysis
Xray CT
Citrus fruits
Image classification
Journal
IF:
2.4
Papers:
265
Citations:
2.7K
Organization
Cited Papers