Computer vision technology for food quality evaluation, second edition sun - The complete ebook vers

Page 1


https://ebookmass.com/product/computer-vision-technology-

Instant digital products (PDF, ePub, MOBI) ready for you

Download now and discover formats that fit your needs...

Probabilistic graphical models for computer vision Ji Q

https://ebookmass.com/product/probabilistic-graphical-models-forcomputer-vision-ji-q/

ebookmass.com

Feature extraction and image processing for computer vision Fourth Edition Aguado

https://ebookmass.com/product/feature-extraction-and-image-processingfor-computer-vision-fourth-edition-aguado/

ebookmass.com

Computer vision: theory, algorithms, practicalities Fifth Edition Davies

https://ebookmass.com/product/computer-vision-theory-algorithmspracticalities-fifth-edition-davies/

ebookmass.com

(eTextbook PDF) for Horngren’s Financial & Managerial Accounting 6th Edition

https://ebookmass.com/product/etextbook-pdf-for-horngrens-financialmanagerial-accounting-6th-edition/

ebookmass.com

AcademicPressisanimprintofElsevier

125LondonWall,LondonEC2Y5AS,UK

525BStreet,Suite1800,SanDiego,CA92101-4495,USA

50HampshireStreet,5thFloor,Cambridge,MA02139,USA

TheBoulevard,LangfordLane,Kidlington,OxfordOX51GB,UK

Copyright © 2016,2008ElsevierInc.Allrightsreserved.

Nopartofthispublicationmaybereproducedortransmittedinanyformorbyanymeans,electronicor mechanical,Includingphotocopying,recording,oranyinformationstorageandretrievalsystem,without permissioninwritingfromthepublisher.Detailsonhowtoseekpermission,furtherinformationaboutthe Publisher’spermissionspoliciesandourarrangementswithorganizationssuchastheCopyrightClearance CenterandtheCopyrightLicensingAgency,canbefoundatourwebsite: www.elsevier.com/permissions.

ThisbookandtheindividualcontributionscontainedinitareprotectedundercopyrightbythePublisher (otherthanasmaybenotedherein).

Notices

Knowledgeandbestpracticeinthisfieldareconstantlychanging.Asnewresearchandexperiencebroaden ourunderstanding,changesinresearchmethods,professionalpractices,ormedicaltreatmentmaybecome necessary.

Practitionersandresearchersmustalwaysrelyontheirownexperienceandknowledgeinevaluatingandusing anyinformation,methods,compounds,orexperimentsdescribedherein.Inusingsuchinformationormethods theyshouldbemindfuloftheirownsafetyandthesafetyofothers,includingpartiesforwhomtheyhavea professionalresponsibility.

Tothefullestextentofthelaw,neitherthePublishernortheauthors,contributors,oreditors,assumeany liabilityforanyinjuryand/ordamagetopersonsorpropertyasamatterofproductsliability,negligenceor otherwise,orfromanyuseoroperationofanymethods,products,instructions,orideascontainedinthe materialherein.

BritishLibraryCataloguing-in-PublicationData

AcataloguerecordforthisbookisavailablefromtheBritishLibrary

LibraryofCongressCataloging-in-PublicationData

AcatalogrecordforthisbookisavailablefromtheLibraryofCongress

ISBN:978-0-12-802232-0

ForinformationonallAcademicPresspublications visitourwebsiteat https://www.elsevier.com/

Publisher: NikkiLevy

AcquisitionEditor: PatriciaOsborn

EditorialProjectManager: KarenMiller

ProductionProjectManager: NickyCarter

Designer: MariaIne ˆ sCruz

TypesetbyTNQBooksandJournals

Part2QualityEvaluationofMeat,PoultryandSeafood

Chapter7:QualityEvaluationofMeatCuts....................................................175

N.A.Valous,L.Zheng,D.-W.Sun,J.Tan

7.1Introduction........................................................................................................175

7.2QualityEvaluationUsingComputerVision.....................................................177

7.2.1BeefQuality,YieldGrade,Composition,andTenderness...........................177

7.2.2PorkColor,Marbling,Grade,andComposition...........................................178

7.2.3PoultryInspection,ContaminantDetection,andComposition....................179

7.2.4LambYieldGradeandTenderness...............................................................179

7.3QualityEvaluationUsingHyperspectralImaging............................................180

7.3.1BeefTenderness,MicrobialSpoilage,andComposition.............................180

7.3.2PorkGrading,Composition,andMicrobialSpoilage..................................181

7.3.3PoultryClassification,ContaminantDetection,andComposition...............183

7.3.4LambClassification,Composition,andTenderness.....................................185

7.4FutureWork.......................................................................................................185

8.1Introduction........................................................................................................195

12.3.2DetectionofCitrusCanker........................................................................318

12.3.3DetectionofOtherSkinDefects...............................................................319

12.4InternalQualityInspection..............................................................................319 References.................................................................................................................321

Chapter13:QualityEvaluationofStrawberry.................................................327 J.-H.Cheng,D.-W.Sun,M.Nagata,J.G.Tallada

13.1Introduction......................................................................................................327

13.1.1OverviewofStrawberries..........................................................................327

13.1.2NecessityofQualityMeasurement...........................................................327

13.1.3ComputerVisionTechnologiesforQualityMeasurement.......................328

13.2GradingofSize,Shape,andRipeness............................................................329

13.2.1StandardsforQualityGrades....................................................................329

13.2.2PreliminaryStudyforSizeandShapeJudgment.....................................330

13.2.3AdvanceTechniquesforSizeandShapeJudgment.................................332

13.2.4GradingofRipeness..................................................................................336

13.3DetectionofBruisesandFecalContamination..............................................337

13.3.1ImportanceofDetectingBruises...............................................................337

13.3.2ColorImagingforBruiseDetection.........................................................338

13.3.3NIRImagingforBruiseDetection............................................................338

13.4.1ImportanceofMeasurementofInternalQuality......................................343

13.4.2MeasurementofFirmness..........................................................................343

13.4.3MeasurementofSolubleSolidsContent...................................................346 13.4.4EstimationofAnthocyaninDistribution...................................................347

Chapter22:QualityEvaluationandControlofPotatoChips.............................591

22.1Introduction......................................................................................................591

22.2ComputerVision..............................................................................................592

22.3ImageFeatures.................................................................................................595

22.4Applications......................................................................................................599

22.5FriedPotatoSorting.........................................................................................604

22.5.1BrowningSortingUsingArtificialNeuralNetworks(ANN) byCARAH(Centrepourl’agronomieetl’agro-industriedela ProvinceeHainaut,Belgium)...................................................................604

22.5.2BrowningSortingWithoutANN(WalloonAgricultural ResearchCenter,Belgium)........................................................................607

22.5.3BrowningSortingandAcrylamideEstimationUsingANN byCARAH.................................................................................................610

Thispageintentionallyleftblank

AbouttheEditor

BorninsouthernChina,ProfessorDa-WenSunisaglobal authorityinfoodengineeringresearchandeducation.Heisa MemberoftheRoyalIrishAcademy,thehighestacademichonor inIreland;aMemberofAcademiaEuropaea(TheAcademyof Europe),oneofthemostprestigiousacademiesintheworld;anda FellowoftheInternationalAcademyofFoodScienceand Technology.Hehassignificantlycontributedtothefieldoffood engineeringasaresearcher,asanacademicauthority,andasan educator.

Hismainresearchactivitiesincludecooling,drying,and refrigerationprocessesandsystems;qualityandsafetyoffood products;bioprocesssimulationandoptimization;andcomputer vision/imageprocessingandhyperspectralimagingtechnologies.Hismanyscholarlyworkshave becomestandardreferencematerialsforresearchersintheareasofcomputervision,computational fluiddynamicsmodeling,vacuumcooling,etc.Resultsofhisworkhavebeenpublishedinover800 papers,includingmorethan400peer-reviewedjournalpapers(WebofScienceh-index ¼ 71), amongthem,31papershavebeenselectedbyThomsonReuters’s EssentialScienceIndicatorsSM as highly-citedpapers,rankinghimNo.1intheworldinAgriculturalSciences(December2015). Hehasalsoedited14authoritativebooks.AccordingtoESI,basedondataderivedoveraperiodof 10yearsfromtheWebofScience,thereareabout4500scientistswhoareamongthetop1%ofthe mostcitedscientistsinthecategoryofAgricultureSciences,andProfessorSunhasconsistently beenrankedamongthetop50scientistsintheworld(hewasatthe20thpositioninDecember 2015),andhasrecentlybeennamedHighlyCitedResearcher2015byThomsonReuters.

HereceivedafirstclassBScHonorsandMScinMechanicalEngineeringandaPhDin ChemicalEngineeringinChinabeforeworkinginvariousuniversitiesinEurope.Hebecamethe firstChinesenationaltobepermanentlyemployedinanIrishUniversitywhenhewasappointed collegelecturerattheNationalUniversityofIreland,Dublin(UniversityCollegeDublin)in1995. Hewasthencontinuouslypromotedintheshortestpossibletimetoseniorlecturer,associate professor,andfullprofessor.Dr.SunisnowprofessorofFoodandBiosystemsEngineering,and directoroftheFoodRefrigerationandComputerizedFoodTechnologyResearchGroupat UniversityCollegeDublin(UCD).

Asaleadingeducatorinfoodengineering,ProfessorSunhassignificantlycontributedtothe fieldoffoodengineering.HehastrainedmanyPhDstudents,whohavemadetheirown contributionstotheindustryandacademia.Hehasalsogivenlecturesonadvancesinfood engineeringonaregularbasisinacademicinstitutionsinternationallyandhasdeliveredkeynote

Prefacetothe2ndEdition

Computervisionisatechnologythatemploysimageprocessingandanalysisforobjectrecognition andquantitativeinformationextraction.Drivenbysignificantincreasesincomputerpowerandrapid developmentsinimageprocessingtechniquesandsoftware,theapplicationofcomputervisionhas becomewidespread,inparticular,toprovideobjective,rapid,noncontact,andnondestructivequality inspection,classification,andevaluationforawiderangeoffoodandagriculturalproducts.

The1steditionof ComputerVisionTechnologyforFoodQualityEvaluation waspublishedin 2008,withthemainaimstopresentacomprehensivereviewofcomputervisionapplicationsforthe foodindustryandpinpointtheresearchanddevelopmenttrendsinthedevelopmentofthetechnology; toprovidetheengineerandtechnologistworkinginresearch,development,andoperationsinthefood industrywithcritical,comprehensive,andreadilyaccessibleinformationontheartandscienceof computervisiontechnology;andtoserveasanessentialreferencesourcetoundergraduateandpostgraduatestudentsandresearchersinuniversitiesandresearchinstitutions.Thiswillcontinuetobethe purposeofthis2ndedition.

Inthe2ndedition,besidesupdatingorrewritingindividualchapterswiththelatestdevelopmentsin eachtopicarea,twonewchaptersareadded.Hyperspectralimaginghasrapidlyemergedasand maturedintooneofthemostpowerfulandfastestgrowingnondestructivetoolsforfoodqualityanalysisandcontrol.Usinghyperspectralimagingtechniques,thespectrumassociatedwitheachpixelina foodimagecanbeusedasafingerprinttocharacterizethebiochemicalcompositionofthepixel,thus enablingthevisualizationoftheconstituentsofthefoodsampleatthepixellevel.Manychaptersin this2ndeditionhavethusbeenupdatedtoincludehyperspectralimagingapplicationsinrelevant areas.Ontheotherhand,Ramanchemicalimagingtechnologyisexpectedtobecomeoneofthe dominantimagingtechniquesinfoodresearch.ThereforetwonewchaptersareaddedinPartIto reflectthiscurrenttrendofdevelopmentsinfoodimagingtechnology.Inaddition,onechapteris removedfromPartVduetolackofdevelopmentinthetopicarea.

SouthChinaUniversityofTechnology,Guangzhou,China; UniversityCollegeDublin(UCD),NationalUniversityofIreland,Dublin,Ireland

Thispageintentionallyleftblank

FundamentalsofComputer VisionTechnology

Thispageintentionallyleftblank

ImageAcquisitionSystems

SchoolofElectricalandElectronicEngineering,UniversitiSainsMalaysia,Penang,Malaysia

1.1Introduction

Inmakingaphysicalassessmentofagriculturalmaterialsandfoodstuff,imagesareundoubtedly thepreferredmethodinrepres entingconceptstothehumanbr ain.Manyofthequalityfactors affectingfoodstuffscanbedeterminedbyvisualinspectionandimageanalysis.Suchinspections determinemarketpriceand,tosomeextent,the“best-if-used-beforedate.”Traditionally,quality inspectionisperformedbytrainedhumaninspectorswhoapproachtheproblemofqualityassessmentintwoways:seeingandfeeling.Inadditiontobeingcostly,thismethodishighlyvariable, anddecisionsarenotalwaysconsistentbetweeninspectorsorfromdaytoday.Thisis,however, changingwiththeadventofelectronicimagingsy stemsandwiththerapiddeclineincostsofcomputers,peripheralsandotherdigitaldevices.Mo reover,theinspectionoffoodstuffsforvarious qualityfactorsisaveryrepetitive task,whichisalsoverysubjectiveinnature.Inthistypeofenvironment,machinevisionsystemsareideallysuite dforroutineinspectionandqualityassurance tasks.Backedbypowerfulartificialintelligencesy stemsandthestate-of-the -artelectronictechnologies,machinevisionprovidesa mechanisminwhichthehumanthinkingprocessissimulatedartificially.Todate,machinevisionhasextensivelybeenappliedtosolvevariousfoodengineering problems,rangingfromthesimplequalityevalua tionoffoodproductstocomplicatedrobotguidanceapplications(Abdullahetal.,2000;Pearson,1996;Taoetal.,1995).Despitethegeneral utilityofmachinevisionimagesasa first-lineinspectiontool,theircapabilitiesformorein-depth investigationarefundamentallylimited.Thisis duetothefactthatimagesproducedbyvision cameraareformedusinganarrowban dofradiation,extendingfrom10 4 to10 7 minwavelength.Duetothis,scientistsandengineershave inventedcamerasystemsthatallowpatternsof energyfromvirtuallyanypartoftheelectromagneticspectrumtobevisualized.Camerasystems suchasthecomputedtomography(CT),themag neticresonanceimaging(MRI),thenuclearmagneticresonance(NMR),thesingle-photonemissioncomputedtomography(SPECT),andthepositronemissiontomography(PET)operate atshorterwavelengths,rangingfrom10 8 to10 13 m. Ontheoppositesideoftheelectromagneticspect rum,thereareinfraredandradiocameras,which enablevisualizationtobeperform edatwavelengthsgreaterthan10 6 and10 4 m,respectively. Alltheseimagingmodalitiesrelyonacquisitionhar dwarefeaturinganarrayorringofdetectors, whichmeasurethestrengthofsomeformofradiation,eitherduetoreflectionorafterthesignal haspassedtransverselythroughtheobject.Perhapsonethingthatthesecamerasystemshavein commonistherequirementtoperformdigitalima geprocessingoftheresultingsignalsusing moderncomputingpower.Whiledigitalimageprocessingisusuallyassumedastheprocessof convertingradiantenergyinathree-dimensionalworldintoatwo-dimensionalradiantarrayof

Turn static files into dynamic content formats.

Create a flipbook
Issuu converts static files into: digital portfolios, online yearbooks, online catalogs, digital photo albums and more. Sign up and create your flipbook.