ebook img

Computer-Aided Intelligent Recognition Techniques and Applications PDF

519 Pages·2005·10.28 MB·English
Save to my drive
Quick download
Download
Most books are stored in the elastic cloud where traffic is expensive. For this reason, we have a limit on daily download.

Preview Computer-Aided Intelligent Recognition Techniques and Applications

COMPUTER-AIDED INTELLIGENT RECOGNITION TECHNIQUES AND APPLICATIONS Edited by Muhammad Sarfraz KingFahdUniversityofPetroleumandMinerals,KingdomofSaudiArabia COMPUTER-AIDED INTELLIGENT RECOGNITION TECHNIQUES AND APPLICATIONS COMPUTER-AIDED INTELLIGENT RECOGNITION TECHNIQUES AND APPLICATIONS Edited by Muhammad Sarfraz KingFahdUniversityofPetroleumandMinerals,KingdomofSaudiArabia Copyright©2005 JohnWiley&SonsLtd,TheAtrium,SouthernGate,Chichester, WestSussexPO198SQ,England Telephone (+44)1243779777 Email(forordersandcustomerserviceenquiries):[email protected] VisitourHomePageonwww.wiley.com AllRightsReserved.Nopartofthispublicationmaybereproduced,storedinaretrievalsystemor transmittedinanyformorbyanymeans,electronic,mechanical,photocopying,recording, scanningorotherwise,exceptunderthetermsoftheCopyright,DesignsandPatentsAct1988or underthetermsofalicenceissuedbytheCopyrightLicensingAgencyLtd,90TottenhamCourt Road,LondonW1T4LP,UK,withoutthepermissioninwritingofthePublisher.Requeststothe PublishershouldbeaddressedtothePermissionsDepartment,JohnWiley&SonsLtd,TheAtrium, SouthernGate,Chichester,WestSussexPO198SQ,England,[email protected], orfaxedto(cid:1)+44(cid:2)1243770620. Designationsusedbycompaniestodistinguishtheirproductsareoftenclaimedastrademarks. Allbrandnamesandproductnamesusedinthisbookaretradenames,servicemarks,trademarksor registeredtrademarksoftheirrespectiveowners.ThePublisherisnotassociatedwithany productorvendormentionedinthisbook. Thispublicationisdesignedtoprovideaccurateandauthoritativeinformationinregardtothesubject mattercovered.ItissoldontheunderstandingthatthePublisherisnotengagedinrendering professionalservices.Ifprofessionaladviceorotherexpertassistanceisrequired,theservicesofa competentprofessionalshouldbesought. OtherWileyEditorialOffices JohnWiley&SonsInc.,111RiverStreet,Hoboken,NJ07030,USA Jossey-Bass,989MarketStreet,SanFrancisco,CA94103-1741,USA Wiley-VCHVerlagGmbH,Boschstr.12,D-69469Weinheim,Germany JohnWiley&SonsAustraliaLtd,33ParkRoad,Milton,Queensland4064,Australia JohnWiley&Sons(Asia)PteLtd,2ClementiLoop#02-01,JinXingDistripark,Singapore129809 JohnWiley&SonsCanadaLtd,22WorcesterRoad,Etobicoke,Ontario,CanadaM9W1L1 Wileyalsopublishesitsbooksinavarietyofelectronicformats.Somecontentthatappears inprintmaynotbeavailableinelectronicbooks. LibraryofCongressCataloging-in-PublicationData Sarfraz,Muhammad. Computer-aidedintelligentrecognitiontechniquesandapplications/MuhammadSarfraz. p. cm. IncludesbibliographicalreferencesandIndex. ISBN-13978-0-470-09414-3(cloth) ISBN-100-470-09414-1(cloth) 1. Logiccircuits—Computer-aideddesign. 2. Patternperception. I. Title. TK7868.L6S2572005 006.3—dc22 2004030987 BritishLibraryCataloguinginPublicationData AcataloguerecordforthisbookisavailablefromtheBritishLibrary ISBN-13978-0-470-09414-3(HB) ISBN-100-470-09414-1(HB) Typesetin9/11ptTimesbyIntegraSoftwareServicesPvt.Ltd,Pondicherry,India PrintedandboundinGreatBritainbyAntonyRoweLtd,Chippenham,Wiltshire Thisbookisprintedonacid-freepaperresponsiblymanufacturedfromsustainableforestry inwhichatleasttwotreesareplantedforeachoneusedforpaperproduction. Contents Preface xvii ListofContributors xix 1. OnOfflineArabicCharacterRecognition 1 MuhammadSarfraz,AbdulmalekZidouriandSyedNazimNawaz (KingdomofSaudiArabia) 1. Introduction 1 2. StructureoftheProposedOCRSystem 4 3. Preprocessing 6 4. Segmentation 7 4.1 LineSegmentationandZoning 8 4.2 WordSegmentation 8 4.3 SegmentationofWordsintoIndividualCharacters 9 5. FeatureExtraction 10 6. RecognitionStrategy 11 6.1 RecognitionUsingtheSyntacticApproach 12 6.2 RecognitionUsingtheNeuralNetworkApproach 13 7. ExperimentalResultsandAnalysis 15 7.1 SystemTraining 15 7.2 ExperimentalSet-up 15 7.3 ResultsAchieved 15 8. Conclusion 17 Acknowledgement 17 References 17 2. LicensePlateRecognitionSystem:SaudiArabianCase 19 MuhammadSarfrazandMohammedJameelAhmed(KingdomofSaudiArabia) 1. Introduction 19 2. StructureofaTypicalLPRSystem 20 3. ImageAcquisition 21 4. LicensePlateExtraction 21 4.1 VerticalEdgeDetection 23 4.2 Filtering 23 4.3 VerticalEdgeMatching 24 4.4 BlacktoWhiteRatioandPlateExtraction 26 5. LicensePlateSegmentation 26 vi Contents 6. CharacterRecognition 26 6.1 Normalization 26 6.2 TemplateMatching 27 7. ExperimentalAnalysisandResults 27 8. Conclusion 32 References 32 3. AlgorithmsforExtractingTextualCharactersinColorVideo 33 EdwardK.WongandMinyaChen(USA) 1. Introduction 33 2. PriorandRelatedWork 34 3. OurNewTextExtractionAlgorithm 35 3.1 Step1:IdentifyPotentialTextLineSegments 36 3.2 Step2:TextBlockDetection 38 3.3 Step3:TextBlockFiltering 38 3.4 Step4:BoundaryAdjustments 38 3.5 Step5:BicolorClustering 38 3.6 Step6:ArtifactFiltering 39 3.7 Step7:ContourSmoothing 39 4. ExperimentalResultsandPerformance 40 5. UsingMultiframeEdgeInformationtoImprovePrecision 47 5.1 Step3(b):TextBlockFilteringBasedonMultiframeEdgeStrength 47 6. DiscussionandConcludingRemarks 47 References 48 4. SeparationofHandwrittenTouchingDigits:AMultiagentsApproach 51 AshrafElnagar(UAE)andRedaAl-Hajj(Canada) 1. Introduction 51 2. PreviousWork 52 3. DigitizingandProcessing 56 4. SegmentationAlgorithm 56 4.1 ExtractionofFeaturePoints 56 4.2 TheEmployedAgents 57 5. ExperimentalResults 61 6. ConclusionsandFutureWork 65 References 65 5. Prototype-basedHandwritingRecognitionUsingShapeandExecutionPrototypes 67 MiguelL.Bote-Lorenzo,EduardoGómez-SánchezandYannisA.Dimitriadis(Spain) 1. Introduction 67 2. AHandwritingGenerationProcessModel 68 3. TheFirstStagesoftheHandwritingRecognitionSystem 70 3.1 CharacterSegmentation 70 3.2 FeatureExtraction 71 4. TheExecutionofthePrototypeExtractionMethod 73 4.1 GroupingTrainingSamples 74 4.2 RefinementofthePrototypes 75 4.3 ExperimentalEvaluationofthePrototypeExtractionMethod 76 5. Prototype-basedClassification 82 5.1 ThePrototype-basedClassifierArchitecture 82 5.2 ExperimentalEvaluationofthePrototypeInitialization 83 Contents vii 5.3 PrototypePruningtoIncreaseKnowledgeCondensation 84 5.4 DiscussionandComparisontoRelatedWork 85 6. Conclusions 87 Acknowledgement 87 References 87 6. LogoDetectioninDocumentImageswithComplexBackgrounds 89 TuanD.PhamandJinsongYang(Australia) 1. Introduction 89 2. DetectionofPotentialLogos 90 3. VerificationofPotentialLogos 91 3.1 FeatureExtractionbyGeostatistics 91 3.2 NeuralNetwork-basedClassifier 93 4. ExperimentalResults 93 5. Conclusions 97 References 97 7. AnIntelligentOnlineSignatureVerificationSystem 99 BinLi(China)andDavidZhang(HongKong) 1. Introduction 99 1.1 ProcessandSystem 100 1.2 TheEvaluationofanOnlineSignatureVerificationSystem 101 2. LiteratureOverview 102 2.1 ConventionalMathematicalApproaches 102 2.2 DynamicProgrammingApproach 104 2.3 HiddenMarkovModel-BasedMethods 105 2.4 TheArtificialNeuralNetworksApproach 106 2.5 SignatureVerificationProductMarketSurvey 106 3. ATypicalOnlineSignatureVerificationSystem 107 3.1 DataAcquisition 107 3.2 FeatureExtraction 110 3.3 FeatureMatching 111 3.4 Verification 112 4. ProposedOnlineSignatureVerificationApplications 113 4.1 SystemPasswordAuthentication 113 4.2 InternetE-commerceApplication 114 5. Conclusions 116 References 116 8. HybridFingerprintRecognitionusingMinutiaeandShape 119 AskerBazen,RaymondVeldhuisandSabihGerez(TheNetherlands) 1. Introduction 119 2. ElasticDeformations 120 3. ElasticMinutiaeMatching 122 3.1 LocalMinutiaeMatching 122 3.2 GlobalMinutiaeMatching 123 4. ShapeMatching 126 5. Results 126 6. Conclusions 129 Acknowledgement 129 References 129 viii Contents 9. PersonalAuthenticationUsingtheFusionofMultiplePalm-printFeatures 131 Chin-ChuanHan(Taiwan,R.O.C.) 1. Introduction 131 2. Preprocessing 133 2.1 Step1:ImageThresholding 134 2.2 Step2:BorderTracing 134 2.3 Step3:Wavelet-basedSegmentation 135 2.4 Step4:RegionofInterest(ROI)Generation 135 3. FeatureExtraction 135 4. EnrollmentandVerificationProcesses 136 4.1 MultitemplateMatchingApproach 136 4.2 MultimodalAuthenticationwithPBF-basedFusion 137 4.3 AdaptiveThresholding 139 5. ExperimentalResults 140 5.1 ExperimentalEnvironment 140 5.2 VerificationUsingaTemplateMatchingAlgorithm 140 5.3 VerificationUsingPBF-basedFusion 141 6. Conclusions 142 References 142 10. IntelligentIrisRecognitionUsingNeuralNetworks 145 MuhammadSarfraz,MohamedDeriche,MuhammadMoinuddin andSyedSaadAzharAli(KingdomofSaudiArabia) 1. Introduction 145 2. LiteratureReview 147 3. SomeGroundbreakingTechniques 148 3.1 Daugman’sMethod 149 3.2 Boles’sMethod 150 3.3 MethodofDyadicWaveletTransformZeroCrossing 151 4. NeuralNetworks 154 4.1 MultilayerFeed-forwardNeuralNetworks(MFNNs) 154 4.2 RadialBasisFunctionNeuralNetworks(RBFNNs) 156 5. ProposedMethod 158 5.1 LocalizingtheIris 158 5.2 FindingtheContour 159 5.3 FeatureExtraction 159 5.4 IrisPatternRecognition 162 6. ExperimentalResults 162 6.1 ResultsforanMFNN 162 6.2 ResultsforanRBFNN 162 7. GraphicUserInterface(GUI) 164 8. ConcludingRemarks 166 References 166 11. Pose-invariantFaceRecognitionUsingSubspaceTechniques 169 MohamedDericheandMohammedAleemuddin(KingdomofSaudiArabia) 1. Introduction 169 1.1 Background 170 1.2 TheProblemofPose 171

Description:
Intelligent recognition methods have recently proven to be indispensable in a variety of modern industries, including computer vision, robotics, medical imaging, visualization and the media. Furthermore, they play a critical role in the traditional fields such as character recognition, natural langu
See more

The list of books you might like

Most books are stored in the elastic cloud where traffic is expensive. For this reason, we have a limit on daily download.