Using Novel Optimized Deep Learning Techniques for Detecting Fungal Infections in Hazelnuts Kernels Based on Shell Color Changes

IF 2.6 3区 农林科学 Q2 FOOD SCIENCE & TECHNOLOGY
Mehdi Farahani, Hossein Bagherpour
{"title":"Using Novel Optimized Deep Learning Techniques for Detecting Fungal Infections in Hazelnuts Kernels Based on Shell Color Changes","authors":"Mehdi Farahani,&nbsp;Hossein Bagherpour","doi":"10.1155/jfq/3350046","DOIUrl":null,"url":null,"abstract":"<div>\n <p>Improper environmental or storage conditions can lead to fungal development in some hazelnuts. This type of fungus causes a slight discoloration on the hazelnut shell. To increase the marketability of the product, it is essential to separate these defective samples from sound ones. Due to the high color similarity between defective and sound samples, manual separation is prone to significant errors, necessitating an automated process. Furthermore, given the strong feature identification and extraction capabilities of convolutional neural networks (CNNs), this model was employed for the classification task. This study investigated the effect of some important factors such as input image size, flattening methods (global average pooling (GAP) and fully connected layer (FCL)), as well as the number of hidden layers and dropout on the model performance. In examining the effect of input image size on the models’ performance, the highest classification accuracy was obtained with a moderate image size of 128 × 128. Comparing the FCL and GAP methods indicated that the GAP method not only increased training speed but also minimized overfitting, resulting in overall better performance than FCL. The results of the models revealed that the proposed CNN model with four convolutional layers, employing the GAP method, a dropout rate of 0.5, and no hidden layers achieved the highest performance. The results demonstrate that the proposed CNN model effectively classified hazelnuts based on subtle color variations on their shells. It achieved a 0.8% improvement in detection accuracy compared to the manual classification method.</p>\n </div>","PeriodicalId":15951,"journal":{"name":"Journal of Food Quality","volume":"2025 1","pages":""},"PeriodicalIF":2.6000,"publicationDate":"2025-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1155/jfq/3350046","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of Food Quality","FirstCategoryId":"97","ListUrlMain":"https://onlinelibrary.wiley.com/doi/10.1155/jfq/3350046","RegionNum":3,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"FOOD SCIENCE & TECHNOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

Improper environmental or storage conditions can lead to fungal development in some hazelnuts. This type of fungus causes a slight discoloration on the hazelnut shell. To increase the marketability of the product, it is essential to separate these defective samples from sound ones. Due to the high color similarity between defective and sound samples, manual separation is prone to significant errors, necessitating an automated process. Furthermore, given the strong feature identification and extraction capabilities of convolutional neural networks (CNNs), this model was employed for the classification task. This study investigated the effect of some important factors such as input image size, flattening methods (global average pooling (GAP) and fully connected layer (FCL)), as well as the number of hidden layers and dropout on the model performance. In examining the effect of input image size on the models’ performance, the highest classification accuracy was obtained with a moderate image size of 128 × 128. Comparing the FCL and GAP methods indicated that the GAP method not only increased training speed but also minimized overfitting, resulting in overall better performance than FCL. The results of the models revealed that the proposed CNN model with four convolutional layers, employing the GAP method, a dropout rate of 0.5, and no hidden layers achieved the highest performance. The results demonstrate that the proposed CNN model effectively classified hazelnuts based on subtle color variations on their shells. It achieved a 0.8% improvement in detection accuracy compared to the manual classification method.

Abstract Image

基于壳颜色变化的新型优化深度学习技术检测榛子仁真菌感染
不适当的环境或储存条件可能导致真菌在一些榛子中发展。这种真菌会导致榛子壳轻微变色。为了提高产品的适销性,有必要将这些有缺陷的样品与完好的样品分开。由于缺陷样品和正常样品之间的颜色高度相似,人工分离容易产生重大错误,因此需要自动化过程。此外,考虑到卷积神经网络(cnn)强大的特征识别和提取能力,该模型被用于分类任务。研究了输入图像大小、平坦化方法(global average pooling, GAP)和完全连接层(fully connected layer, FCL)、隐藏层数和dropout等重要因素对模型性能的影响。在研究输入图像大小对模型性能的影响时,当图像大小为128 × 128时,获得了最高的分类精度。对比FCL方法和GAP方法,GAP方法不仅提高了训练速度,而且最小化了过拟合,总体性能优于FCL方法。模型结果表明,采用GAP方法、dropout率为0.5、无隐藏层的4层卷积CNN模型的性能最好。结果表明,所提出的CNN模型基于榛子壳上细微的颜色变化有效地分类了榛子。与人工分类方法相比,该方法的检测准确率提高了0.8%。
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
Journal of Food Quality
Journal of Food Quality 工程技术-食品科技
CiteScore
5.90
自引率
6.10%
发文量
285
审稿时长
>36 weeks
期刊介绍: Journal of Food Quality is a peer-reviewed, Open Access journal that publishes original research articles as well as review articles related to all aspects of food quality characteristics acceptable to consumers. The journal aims to provide a valuable resource for food scientists, nutritionists, food producers, the public health sector, and governmental and non-governmental agencies with an interest in food quality.
×
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