Deep learning approach for automated ‘Kent’ mango maturity grading in compliance with Peruvian standards

Q3 Mathematics
Orlando Salazar-Campos , Javier Moran Ruiz , José Luis Peralta , Mirian Rubio Cieza , Breysi Salazar Medina , Johonathan Salazar-Campos
{"title":"Deep learning approach for automated ‘Kent’ mango maturity grading in compliance with Peruvian standards","authors":"Orlando Salazar-Campos ,&nbsp;Javier Moran Ruiz ,&nbsp;José Luis Peralta ,&nbsp;Mirian Rubio Cieza ,&nbsp;Breysi Salazar Medina ,&nbsp;Johonathan Salazar-Campos","doi":"10.1016/j.rico.2025.100589","DOIUrl":null,"url":null,"abstract":"<div><div>Deep learning, particularly convolutional neural networks (CNNs), has significantly advanced automated fruit classification based on image analysis. However, accurate classification of <em>Mangifera indica</em> L. remains challenging due to high variability in external appearance and the subjectivity of visual maturity assessment. Misclassification contributes to post-harvest losses, reduced market value, and inconsistencies in quality control. This study develops a CNN-based model for classifying 'Kent' mangoes according to the Peruvian Technical Standard (NTP) 011.025:2023. A dataset of 603 labelled images was used to optimise the CNN architecture, systematically evaluating convolutional and pooling layers, image resolution, and training cycles. The optimised model, trained on 32× 32 pixel images, achieved 96.04 % classification accuracy, 90.91 % recall, and an F1-score of 93.57 %. To validate model robustness, 5-fold cross-validation demonstrated minimal accuracy variation (±0.5 %), while external evaluation achieved 95.8 % accuracy, confirming its real-world applicability. The lightweight single-layer CNN ensures scalable, low-cost implementation for automated sorting systems, reducing computational demands while enhancing classification efficiency. These findings establish deep learning as a viable and cost-effective solution for post-harvest fruit classification, ensuring greater consistency in quality control and supporting sustainable agricultural practices.</div></div>","PeriodicalId":34733,"journal":{"name":"Results in Control and Optimization","volume":"20 ","pages":"Article 100589"},"PeriodicalIF":0.0000,"publicationDate":"2025-07-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Results in Control and Optimization","FirstCategoryId":"1085","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S266672072500075X","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"Mathematics","Score":null,"Total":0}
引用次数: 0

Abstract

Deep learning, particularly convolutional neural networks (CNNs), has significantly advanced automated fruit classification based on image analysis. However, accurate classification of Mangifera indica L. remains challenging due to high variability in external appearance and the subjectivity of visual maturity assessment. Misclassification contributes to post-harvest losses, reduced market value, and inconsistencies in quality control. This study develops a CNN-based model for classifying 'Kent' mangoes according to the Peruvian Technical Standard (NTP) 011.025:2023. A dataset of 603 labelled images was used to optimise the CNN architecture, systematically evaluating convolutional and pooling layers, image resolution, and training cycles. The optimised model, trained on 32× 32 pixel images, achieved 96.04 % classification accuracy, 90.91 % recall, and an F1-score of 93.57 %. To validate model robustness, 5-fold cross-validation demonstrated minimal accuracy variation (±0.5 %), while external evaluation achieved 95.8 % accuracy, confirming its real-world applicability. The lightweight single-layer CNN ensures scalable, low-cost implementation for automated sorting systems, reducing computational demands while enhancing classification efficiency. These findings establish deep learning as a viable and cost-effective solution for post-harvest fruit classification, ensuring greater consistency in quality control and supporting sustainable agricultural practices.
深度学习方法自动“肯特”芒果成熟度分级符合秘鲁标准
深度学习,特别是卷积神经网络(cnn),极大地推进了基于图像分析的自动水果分类。然而,由于芒果外观的高度变异性和视觉成熟度评价的主观性,对芒果的准确分类仍然具有挑战性。错误分类导致收获后损失、市场价值降低和质量控制不一致。本研究开发了一个基于cnn的模型,根据秘鲁技术标准(NTP) 011.025:2023对“肯特”芒果进行分类。使用603个标记图像的数据集来优化CNN架构,系统地评估卷积和池化层、图像分辨率和训练周期。优化后的模型在32× 32像素图像上训练,分类准确率为96.04%,召回率为90.91%,f1得分为93.57%。为了验证模型的稳健性,5倍交叉验证显示最小的准确度变化(±0.5%),而外部评估达到95.8%的准确度,证实了其在现实世界中的适用性。轻量级的单层CNN确保了自动分拣系统的可扩展、低成本实现,减少了计算需求,同时提高了分类效率。这些研究结果表明,深度学习是收获后水果分类的可行且具有成本效益的解决方案,可确保质量控制的一致性,并支持可持续农业实践。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 求助全文
来源期刊
Results in Control and Optimization
Results in Control and Optimization Mathematics-Control and Optimization
CiteScore
3.00
自引率
0.00%
发文量
51
审稿时长
91 days
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:604180095
Book学术官方微信