Non-destructive Ripeness Detection of Avocados (Persea Americana Mill) using Vision and Tactile Perception Information Fusion Method

IF 5.3 2区 农林科学 Q1 FOOD SCIENCE & TECHNOLOGY
Junchang Zhang, Leqin Qin, Guang Wang, Qing Wang, Xiaoshuan Zhang
{"title":"Non-destructive Ripeness Detection of Avocados (Persea Americana Mill) using Vision and Tactile Perception Information Fusion Method","authors":"Junchang Zhang, Leqin Qin, Guang Wang, Qing Wang, Xiaoshuan Zhang","doi":"10.1007/s11947-024-03505-x","DOIUrl":null,"url":null,"abstract":"<p>Vision (skin color) and tactile (firmness) characteristics of avocado are important characteristics associated with the level of ripeness. Avocados do not soften uniformly during ripening, and it is difficult to measure the firmness value at each location. Machine learning-based visual characteristic grading is difficult to analyze quantitatively. It works poorly for more refined grading and is better suited for coarse grading. In addition, there are asynchronous changes in the tactile and vision characteristics of avocado fruit during the ripening period. In this study, combining the tactile-based ripeness grading technique with the vision-based ripeness grading technique is proposed to obtain more stable and reliable grading results. In the first phase, visual characteristic (skin color) of avocado images is graded based on the ResNet-34 model, and three maturity classes (A, B and C) were initially identified. The second stage uses a pneumatic flexible sensing soft manipulator. It integrates four flexible pressure sensors to grasp avocados one by one and sense their firmness. The second stage is subdivided into six maturity classes (A1, A2, B1, B2, C1, C2) based on the first stage. This study achieves more refined grading (6 levels) and high accuracy (96.0% grading success rate), which is superior to visual or tactile grading only and manual maturity grading commonly used in current production. </p>","PeriodicalId":562,"journal":{"name":"Food and Bioprocess Technology","volume":"63 1","pages":""},"PeriodicalIF":5.3000,"publicationDate":"2024-07-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Food and Bioprocess Technology","FirstCategoryId":"97","ListUrlMain":"https://doi.org/10.1007/s11947-024-03505-x","RegionNum":2,"RegionCategory":"农林科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"FOOD SCIENCE & TECHNOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

Vision (skin color) and tactile (firmness) characteristics of avocado are important characteristics associated with the level of ripeness. Avocados do not soften uniformly during ripening, and it is difficult to measure the firmness value at each location. Machine learning-based visual characteristic grading is difficult to analyze quantitatively. It works poorly for more refined grading and is better suited for coarse grading. In addition, there are asynchronous changes in the tactile and vision characteristics of avocado fruit during the ripening period. In this study, combining the tactile-based ripeness grading technique with the vision-based ripeness grading technique is proposed to obtain more stable and reliable grading results. In the first phase, visual characteristic (skin color) of avocado images is graded based on the ResNet-34 model, and three maturity classes (A, B and C) were initially identified. The second stage uses a pneumatic flexible sensing soft manipulator. It integrates four flexible pressure sensors to grasp avocados one by one and sense their firmness. The second stage is subdivided into six maturity classes (A1, A2, B1, B2, C1, C2) based on the first stage. This study achieves more refined grading (6 levels) and high accuracy (96.0% grading success rate), which is superior to visual or tactile grading only and manual maturity grading commonly used in current production.

Abstract Image

利用视觉和触觉信息融合法对鳄梨(Persea Americana Mill)进行非破坏性成熟度检测
牛油果的视觉(表皮颜色)和触觉(硬度)特征是与成熟度相关的重要特征。牛油果在成熟过程中不会均匀软化,因此很难测量每个位置的硬度值。基于机器学习的视觉特征分级很难进行定量分析。它对更精细的分级效果不佳,更适合粗分级。此外,鳄梨果实在成熟期的触觉和视觉特征会发生不同步的变化。本研究提出将基于触觉的成熟度分级技术与基于视觉的成熟度分级技术相结合,以获得更稳定可靠的分级结果。在第一阶段,根据 ResNet-34 模型对牛油果图像的视觉特征(表皮颜色)进行分级,并初步确定了三个成熟度等级(A、B 和 C)。第二阶段使用气动柔性传感软机械手。它集成了四个柔性压力传感器,可逐个抓取鳄梨并感知其硬度。第二阶段在第一阶段的基础上细分为六个成熟度等级(A1、A2、B1、B2、C1、C2)。这项研究实现了更精细的分级(6 级)和更高的准确性(分级成功率达 96.0%),优于目前生产中常用的仅靠视觉或触觉分级以及人工成熟度分级。
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
Food and Bioprocess Technology
Food and Bioprocess Technology 农林科学-食品科技
CiteScore
9.50
自引率
19.60%
发文量
200
审稿时长
2.8 months
期刊介绍: Food and Bioprocess Technology provides an effective and timely platform for cutting-edge high quality original papers in the engineering and science of all types of food processing technologies, from the original food supply source to the consumer’s dinner table. It aims to be a leading international journal for the multidisciplinary agri-food research community. The journal focuses especially on experimental or theoretical research findings that have the potential for helping the agri-food industry to improve process efficiency, enhance product quality and, extend shelf-life of fresh and processed agri-food products. The editors present critical reviews on new perspectives to established processes, innovative and emerging technologies, and trends and future research in food and bioproducts processing. The journal also publishes short communications for rapidly disseminating preliminary results, letters to the Editor on recent developments and controversy, and book reviews.
×
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:481959085
Book学术官方微信