Detection of skin defects on loquat using the hyperspectral imaging combining both band radio and improved three-phase level set segmentation method

IF 3 3区农林科学 Q2 FOOD SCIENCE & TECHNOLOGY

Food Quality and Safety Pub Date : 2022-10-28 DOI:10.1093/fqsafe/fyac065

Zhao Han, Bin Li, Qiu Wang, Zhaoxia Sun, Yande Liu

{"title":"Detection of skin defects on loquat using the hyperspectral imaging combining both band radio and improved three-phase level set segmentation method","authors":"Zhao Han, Bin Li, Qiu Wang, Zhaoxia Sun, Yande Liu","doi":"10.1093/fqsafe/fyac065","DOIUrl":null,"url":null,"abstract":"\n \n \n Skin defects are one of the primary problems that occur in post-harvest grading and processing of loquats. The loquats with skin defects will lead to the loquat being easily destroyed during transportation and storage, which will cause the risk of other loquats being infected, affecting the selling price of loquat.\n \n \n \n In this paper, a method combining band radio image with improved three-phase level set segmentation algorithm (ITPLSSM) is proposed to achieve high accuracy, rapid, and non-destructive detection of skin defects of loquats. Principal component analysis (PCA) was used to find the characteristic wavelength and PC images to distinguish between four types of skin defects. Determine the best band ratio image based on characteristic wavelength.\n \n \n \n The band ratio image (Q782/944) based on PC2 image is the best segmented image. Based on Pseudo-color image enhancement, morphological processing, and local clustering criteria, the band ratio image (Q782/944) has better contrast between defective area and normal area in loquat. Finally, the ITPLSSM was used to segment the processing band ratio image (Q782/944), with the accuracy is 95.28 %.\n \n \n \n The proposed ITPLSSM method is effective in distinguishing with four types of skin defects. Meanwhile, it also effectively segments the images with intensity inhomogeneities.\n","PeriodicalId":12427,"journal":{"name":"Food Quality and Safety","volume":" ","pages":""},"PeriodicalIF":3.0000,"publicationDate":"2022-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Food Quality and Safety","FirstCategoryId":"97","ListUrlMain":"https://doi.org/10.1093/fqsafe/fyac065","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: 1

Abstract

Skin defects are one of the primary problems that occur in post-harvest grading and processing of loquats. The loquats with skin defects will lead to the loquat being easily destroyed during transportation and storage, which will cause the risk of other loquats being infected, affecting the selling price of loquat. In this paper, a method combining band radio image with improved three-phase level set segmentation algorithm (ITPLSSM) is proposed to achieve high accuracy, rapid, and non-destructive detection of skin defects of loquats. Principal component analysis (PCA) was used to find the characteristic wavelength and PC images to distinguish between four types of skin defects. Determine the best band ratio image based on characteristic wavelength. The band ratio image (Q782/944) based on PC2 image is the best segmented image. Based on Pseudo-color image enhancement, morphological processing, and local clustering criteria, the band ratio image (Q782/944) has better contrast between defective area and normal area in loquat. Finally, the ITPLSSM was used to segment the processing band ratio image (Q782/944), with the accuracy is 95.28 %. The proposed ITPLSSM method is effective in distinguishing with four types of skin defects. Meanwhile, it also effectively segments the images with intensity inhomogeneities.

查看原文本刊更多论文

结合波段无线电和改进的三相水平集分割方法的高光谱成像枇杷皮肤缺陷检测

果皮缺陷是枇杷采收后分级和加工中出现的主要问题之一。表皮有缺陷的枇杷在运输和储存过程中容易被破坏，从而造成其他枇杷被感染的风险，影响枇杷的销售价格。本文提出了一种将波段无线电图像与改进的三相水平集分割算法(ITPLSSM)相结合的方法，实现了枇杷皮肤缺陷的高精度、快速、无损检测。采用主成分分析(PCA)寻找特征波长和PC图像来区分四种类型的皮肤缺陷。根据特征波长确定最佳带比图像。基于PC2图像的带比图像(Q782/944)是分割效果最好的图像。基于伪彩色图像增强、形态学处理和局部聚类准则，Q782/944带比图像对枇杷缺陷区和正常区具有较好的对比度。最后，利用ITPLSSM对处理带比图像(Q782/944)进行分割，准确率为95.28%。所提出的ITPLSSM方法可以有效地区分四种类型的皮肤缺陷。同时，它还能有效地分割出具有强度不均匀性的图像。

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 Quality and Safety FOOD SCIENCE & TECHNOLOGY-

CiteScore

7.20

自引率

1.80%

发文量

审稿时长

5 weeks

期刊介绍： Food quality and safety are the main targets of investigation in food production. Therefore, reliable paths to detect, identify, quantify, characterize and monitor quality and safety issues occurring in food are of great interest. Food Quality and Safety is an open access, international, peer-reviewed journal providing a platform to highlight emerging and innovative science and technology in the agro-food field, publishing up-to-date research in the areas of food quality and safety, food nutrition and human health. It promotes food and health equity which will consequently promote public health and combat diseases. The journal is an effective channel of communication between food scientists, nutritionists, public health professionals, food producers, food marketers, policy makers, governmental and non-governmental agencies, and others concerned with the food safety, nutrition and public health dimensions. The journal accepts original research articles, review papers, technical reports, case studies, conference reports, and book reviews articles.