university of florida department of electrical and
TRANSCRIPT
UniversityofFlorida
DepartmentofElectricalandComputerEngineering
EEL6825,Section026A
PatternRecognitionandIntelligentSystems
Spring 2021
CourseDescription
Thisisa3-creditcourse.
Theobjectiveofthiscourseistoimpartaworkingknowledgeofseveralimportantandwidelyusedpatternrecognitiontopicstothestudentsthroughamixtureofmotivationalapplicationsandtheory.
CoursePrerequisites
• EEL3135(Discrete-TimeSignalsandSystems)orundergraduate-levelsignalsandsystems
• EEL4516(NoiseinDevicesandcommunicationSystems)orundergraduate-levelprobabilitytheory/stochasticprocesses
• SomeexposuretoMATLABandCprogramminglanguage• Knowledgeofbasicmatrixtheory(linearalgebra)wouldbehelpful,butnot
necessary
RequiredTextbook
• Richard O. Duda, Peter E. Hart, David G. Stork, ``Pattern Classification,'' 2nd Edition, Wiley-Interscience, October 2000. ISBN-10: 0471056693 | ISBN-13: 978-0471056690.
RecommendedReadings
• DavidG.Stork,EladYom-Tov,``ComputerManualinMATLABtoaccompanyPatternClassification,"2ndEdition,Wiley-Interscience, April2004.ISBN:978-0-471-42977-7
• ChristopherM.Bishop,“PatternRecognitionandMachineLearning”,1stEdition,Springer,October1,2007.ISBN-10:0387310738|ISBN-13:978-0387310732.
• TrevorHastie,RobertTibshirani,JeromeFriedman,"TheElementsofStatisticalLearning:DataMining,Inference,andPrediction,"SecondEdition,Springer,February9,2009.ISBN-10:0387848576|ISBN-13:978-0387848570.
• KevinPatrickMurphy,"MachineLearning:aProbabilisticPerspective,"theMITPress,August24,2012.ISBN-10:0262018020|ISBN-13:978-0262018029.
• EugeneCharniak,"IntroductiontoDeepLearning,"theMITPress,January2019.ISBN:9780262039512(Thisbookisaproject-basedguidetothebasicsofdeeplearning)
Instructor:
Dr.DapengWuOffice:NEB431Email:[email protected]
TA:
1)HengQiaoEmail:[email protected]
2)HaotianJiangEmail:[email protected]
3)XiyaoMa
Email:[email protected]
4)YanlinZhou
Email:[email protected]
Coursewebsite:http://www.wu.ece.ufl.edu/courses/eel6825s21
MeetingTime
Monday,Wednesday,Friday,period8(3:00pm-3:50pm)
MeetingRoom
Online
OfficeHours
• Dr.Wu:Monday,Wednesday,period9(4:05pm-4:55pm),and by appointment via email.
StructureoftheCourse
The course consists of lectures, 4 homework assignments, and 1 project.
Thiscourseisprimarilyalecturecourse.Icoverallimportantmaterialinlectures.SinceEEL3135andEEL4516areprerequisites,IassumesomepreviousknowledgeaboutDSP,probabilitytheoryandstochasticprocesses,andhenceIwillcoversomematerialveryquickly.Thus,dependingonwhatandhowmuchyourecallfromearlierstudy,varyingamountsofreadinginintroductorybooksonDSP,probabilitytheoryandstochasticprocesses(otherthanthecoursetextbook)maybenecessary;thesereadingsareuptothestudent.Iwillonlygivereadingassignmentsfromthecoursetextbook.
AttendinglectureisquiteimportantasImaycovermaterialnotavailableinanybookeasilyaccessibletoyou.IusePowerpointpresentationduringlecture.Lecturenoteswillbepostedonthecoursewebsitebeforetheclass.Thelectureistoengagethestudentsinindependentthinking,criticalthinking,andcreativethinking,helpthestudentsorganizetheknowledgearoundessentialconceptsandfundamentalprinciples,anddevelopconditionalizedknowledgewhichtellsthemwhen,whereandwhyacertainmethodisapplicabletosolvingtheproblemtheyencounter.
IdonotintendfortheWWWmaterialtobeasubstituteforattendinglecturesinceengagingthestudentsinactivethinking,makinglogicalconnectionsbetweentheoldknowledgeandthenewknowledge,andprovidinginsightsaretheobjectivesofmylecture.Thelecturenotesarepostedonthewebsothatyoucanmissanoccasionallectureandstillcatchup,anditmakestakingnoteseasier.Torewardthosewhoattendregularly,therewillbesomelecture-basedmaterialintheexamwhichisnotavailableviatheweb.
Theclassprojectisdescribedhere.
Course Outline
• Bayesiandecisiontheory• Parametricestimationandsupervisedlearning• Nonparametricmethods• Lineardiscriminantfunctions• Unsupervisedlearningandclustering• Nonmetricmethods• Featureextractionandfeatureselection• Applications
CourseObjectives
Uponthecompletionofthecourse,thestudentshouldbeableto
• usethefundamentaltechniquesforpatternrecognition• understandthebasicsofstatisticallearningtheory• acquirethebasicskillofdesigningmachinelearningalgorithmsandsystems
Handouts
Pleasefindhandoutshere.
CoursePolicies
• Attendance:o Perfectclassattendanceisnotrequired,butregularattendanceisexpected.o Itisthestudent'sresponsibilitytoindependentlyobtainanymissedmaterial
(includinghandouts)fromlecture.• Duringlecture,cellphonesshouldbeturnedoff.• Nolatesubmissionsofyourhomeworksolution,andproject
proposal/report,areallowedunlessU.F.approvedreasonsaresuppliedandadvancepermissionisgrantedbytheinstructor.Excusedlatesubmissionsareconsistentwithuniversitypoliciesintheundergraduatecatalog(https://catalog.ufl.edu/ugrad/current/regulations/info/attendance.aspx)andrequireappropriatedocumentation.
• Software useo All faculty, staff and student of the University are required and expected to obey
the laws and legal agreements governing software use. Failure to do so can lead
to monetary damages and/or criminal penalties for the individual violator. Because such violations are also against University policies and rules, disciplinary action will be taken as appropriate. We, the members of the University of Florida community, pledge to uphold ourselves and our peers to the highest standards of honesty and integrity.
• Announcements:o Allstudentsareresponsibleforannouncementsmadeinlecture,onthe
studentaccesswebsite,orviatheclassemaillist.o Itisexpectedthatyouwillcheckyouremailseveraltimesperweekfor
possiblecourseannouncements.• Studentswithdisabilities:
o StudentswithdisabilitiesrequestingaccommodationsshouldfirstregisterwiththeDisabilityResourceCenter(352-392-8565,https://www.dso.ufl.edu/drc)byprovidingappropriatedocumentation.Onceregistered,studentswillreceiveanaccommodationletterwhichmustbepresentedtotheinstructorwhenrequestingaccommodation.Studentswithdisabilitiesshouldfollowthisprocedureasearlyaspossibleinthesemester.
• University Honesty Policy
UF students are bound by The Honor Pledge which states, “We, the members of the University of Florida community, pledge to hold ourselves and our peers to the highest standards of honor and integrity by abiding by the Honor Code. On all work submitted for credit by students at the University of Florida, the following pledge is either required or implied: “On my honor, I have neither given nor received unauthorized aid in doing this assignment.” The Honor Code (https://www.dso.ufl.edu/sccr/process/student-conduct-honor-code/) specifies a number of behaviors that are in violation of this code and the possible sanctions. Furthermore, you are obligated to report any condition that facilitates academic misconduct to appropriate personnel. If you have any questions or concerns, please consult with the instructor or TAs in this class.Students are encouraged to discuss class material in order to better understand concepts. All homework answers must be the author's own work. However, students are encouraged to discuss homework to promote better understanding. What this means in practice is that students are welcome to discuss problems and solution approaches, and in fact can communally work solutions at a board. However, the material handed in must be prepared starting with a clean sheet of paper (and the author's recollection of any solution session), but not refer to any written notes or existing code from other students during the writing of the solution. In other words, writing the homework report shall be an exercise in demonstrating the student understands the materials on his/her own, whether or not help was provided in attaining that understanding. Allworksubmittedinthiscoursemustbeyourownandproducedexclusivelyforthiscourse. The use of sources (ideas, quotations, paraphrases) must be properlyacknowledgedanddocumented.ForthecopyoftheUFHonorCodeandconsequencesof academic dishonesty, please refer to
http://www.dso.ufl.edu/sccr/honorcodes/honorcode.php. Violations will be takenseriouslyandarenotedonstudentdisciplinaryrecords.Ifyouareindoubtregardingthe requirements, please consult with the instructor before you complete anyrequirementofthecourse.
Course Evaluation Students are expected to provide feedback on the quality of instruction in this course by completing online evaluations at https://evaluations.ufl.edu/evals. Evaluations are typically open during the last two or three weeks of the semester, but students will be given specific times when they are open. Summary results of these assessments are available to students at https://evaluations.ufl.edu/results/.
SoftwareUse
Allfaculty,staff,andstudentsoftheUniversityarerequiredandexpectedtoobeythelawsandlegalagreementsgoverningsoftwareuse.Failuretodosocanleadtomonetarydamagesand/orcriminalpenaltiesfortheindividualviolator.BecausesuchviolationsarealsoagainstUniversitypoliciesandrules,disciplinaryactionwillbetakenasappropriate.We,themembersoftheUniversityofFloridacommunity,pledgetoupholdourselvesandourpeerstothehigheststandardsofhonestyandintegrity.
StudentPrivacy
Therearefederallawsprotectingyourprivacywithregardstogradesearnedincoursesandonindividualassignments.Formoreinformation,pleasesee:http://registrar.ufl.edu/catalog0910/policies/regulationferpa.html
OnlineCourseRecording
Ourclasssessionsmaybeaudiovisuallyrecordedforstudentsintheclasstoreferbackandforenrolledstudentswhoareunabletoattendlive.Studentswhoparticipatewiththeircameraengagedorutilizeaprofileimageareagreeingtohavetheirvideoorimagerecorded.Ifyouareunwillingtoconsenttohaveyourprofileorvideoimagerecorded,besuretokeepyourcameraoffanddonotuseaprofileimage.Likewise,studentswhoun-muteduringclassandparticipateorallyareagreeingtohavetheirvoicesrecorded.Ifyouarenotwillingtoconsenttohaveyourvoicerecordedduringclass,youwillneedtokeepyourmutebuttonactivatedandcommunicateexclusivelyusingthe"chat"feature,whichallowsstudentstotypequestionsandcommentslive.Thechatwillnotberecordedorshared.Asinallcourses,unauthorizedrecordingandunauthorizedsharingofrecordedmaterialsisprohibited.
AttendancePolicy,ClassExpectations,andMake-UpPolicy
ThisclasswillbepresentedonlineusingZoomandrequiresaccesstoaworkingwebcamandstableinternetconnection.
ExcusedabsencesmustbeincompliancewithuniversitypoliciesintheGraduateCatalog(http://gradcatalog.ufl.edu/content.php?catoid=10&navoid=2020#attendance)andrequireappropriatedocumentation.
Campus Resources:
HealthandWellness
UMatter,WeCare:
Ifyouorafriendisindistress,pleasecontactumatter@ufl.eduor352392-1575sothatateammembercanreachouttothestudent.
CounselingandWellnessCenter:http://www.counseling.ufl.edu/cwc,and392-1575;andtheUniversityPoliceDepartment:392-1111or9-1-1foremergencies.
SexualAssaultRecoveryServices(SARS)
StudentHealthCareCenter,392-1161.
UniversityPoliceDepartmentat392-1111(or9-1-1foremergencies),orhttp://www.police.ufl.edu/.
AcademicResources
E-learningtechnicalsupport,352-392-4357(selectoption2)[email protected]://lss.at.ufl.edu/help.shtml.
CareerResourceCenter,ReitzUnion,392-1601.Careerassistanceandcounseling.https://www.crc.ufl.edu/.
LibrarySupport,http://cms.uflib.ufl.edu/ask.Variouswaystoreceiveassistancewithrespecttousingthelibrariesorfindingresources.
TeachingCenter,BrowardHall,392-2010or392-6420.Generalstudyskillsandtutoring.https://teachingcenter.ufl.edu/.
WritingStudio,302TigertHall,846-1138.Helpbrainstorming,formatting,andwritingpapers.https://writing.ufl.edu/writing-studio/.
StudentComplaintsCampus:https://www.dso.ufl.edu/documents/UF_Complaints_policy.pdf.
On-LineStudentsComplaints:http://www.distance.ufl.edu/student-complaint-process.
Grading:
Grades Percentage Dates
Homework 30% see calendar
Project proposal 10% 4pm, March 12
Project report 60% 4pm, April 28
Theprojectreportconsistsof
1. (50%) A written report for your project2. (25%) Computer programs that you develop for your project3. (10%) Powerpoint file of your presentation4. (15%) Your presentation/demo video on YouTube
Gradingscale:
Top25%studentswillreceiveA.AveragescorewillbeatleastB+.
MoreinformationonUFgradingpolicymaybefoundat:https://catalog.ufl.edu/ugrad/current/regulations/info/grades.aspx
Homework:
• Due dates of assignments are specified in the course calendar. • No late submissions are allowed unless U.F. approved reasons are supplied and advance
permission is granted by the instructor. • If you wish to dispute a homework grade, you must return the assignment along with a
succinct written argument within one week after the graded materials have been returned to the class. Simple arithmetic errors in adding up grade totals are an exception, and can normally be handled verbally on-the-spot during office hours of the TA. For all other disputes, the entire homework may be (non-maliciously) re-graded, which may result in increase or decrease of points.
ClassProject:
Theclassprojectwillbedoneindividually.Eachprojectrequiresaproposalandafinalreport.Thefinalreportisexpectedtobeintheformatofaconferencepaperpluscomputerprograms,aPowerpointfile,andavideo. On March 12, the project proposal (up to 2 pages) is due. On April 28, the final report (up to 10 pages) is due. For details about the project, please read here.
Suggestedtopicsforprojectsarelistedhere.
Coursecalendarcanbefoundhere.
Usefullinks
• Anaconda:AnacondaistheleadingopendatascienceplatformpoweredbyPython.• Theano:TheanoisaPythonlibrarythatletsyoutodefine,optimize,andevaluate
mathematicalexpressions,especiallyoneswithmulti-dimensionalarrays(numpy.ndarray).
• TensorFlow:TensorFlowisanopensourcesoftwarelibraryfornumericalcomputationusingdataflowgraphs.Nodesinthegraphrepresentmathematicaloperations,whilethegraphedgesrepresentthemultidimensionaldataarrays(tensors)communicatedbetweenthem.TheflexiblearchitectureallowsyoutodeploycomputationtooneormoreCPUsorGPUsinadesktop,server,ormobiledevicewithasingleAPI.
• Keras:Kerasisaminimalist,highlymodularneuralnetworkslibrary,writteninPythonandcapableofrunningontopofeitherTensorFloworTheano.Itwasdevelopedwithafocusonenablingfastexperimentation.Beingabletogofromideatoresultwiththeleastpossibledelayiskeytodoinggoodresearch.
• PyTorch:PyTorchisadeeplearningframeworkforfast,flexibleexperimentation.• Acuratedlistofresourcesdedicatedtorecurrentneuralnetworks
• SourcecodeinPythonforhandwrittendigitrecognition,usingdeepneuralnetworks
• SourcecodeinPyTorchforhandwrittendigitrecognition,usingdeepneuralnetworks
• SourcecodeinPythonforTF-mRNN:aTensorFlowlibraryforimagecaptioning• SourcecodeinPythonforthefollowingworkonimagecaptioning:
o OriolVinyals,AlexanderToshev,SamyBengio,DumitruErhan,ShowandTell:ANeuralImageCaptionGenerator,CVPR2015
§ Implementation• Imagecaptioning:
o ZheGan,et.al,SemanticCompositionalNetworksforVisualCaptioning,CVPR2017
§ ImplementationSourcecodeinPython(Theano)o Bottom-UpandTop-DownAttentionforImageCaptioningandVisual
QuestionAnswering:sourcecodes(Caffe)andsourcecodes(PyTorch)• MicrosoftCOCOdatasets• VisualQuestionAnswering:
o Bottom-UpandTop-DownAttentionforImageCaptioningandVisualQuestionAnswering:sourcecodes(Caffe)andVQAsourcecode(PyTorch)
• SemanticPropositionalImageCaptionEvaluation(SPICE)o SourcecodeinJAVAtocalculateSPICE
• Region-basedConvolutionalNeuralNetworks(R-CNN)o References:
§ Ren,Shaoqing,KaimingHe,RossGirshick,andJianSun."FasterR-CNN:Towardsreal-timeobjectdetectionwithregionproposalnetworks."InAdvancesinneuralinformationprocessingsystems,pp.91-99.2015.[pdf]
§ Dai,Jifeng,YiLi,KaimingHe,andJianSun."R-FCN:Objectdetectionviaregion-basedfullyconvolutionalnetworks."InAdvancesinneuralinformationprocessingsystems,pp.379-387.2016.[pdf][sourcecode]
§ Huang,Jonathan,VivekRathod,ChenSun,MenglongZhu,AnoopKorattikara,AlirezaFathi,IanFischeretal."Speed/accuracytrade-offsformodernconvolutionalobjectdetectors."arXivpreprintarXiv:1611.10012(2016).[pdf](E.g.,forInceptionV3,extractfeaturesfromthe“Mixed6e”layerwhosestridesizeis16pixels.Featuremapsarecroppedandresizedto17x17.)
o Sourcecodes:§ AFasterPytorchImplementationofFasterR-CNN(PyTorch)§ Bottom-UpandTop-DownAttentionforImageCaptioningandVisual
QuestionAnswering:sourcecodes(Caffe)• SourcecodeinPythonforend-to-endtrainingofLSTM
o Implementation• BidirectionalEncoderRepresentationsfromTransformers(BERT)
o ImplementationinTensorFlowo ImplementationinPyTorch
• SourcecodeinPythonforsequence-to-sequencelearning(languagetranslation,chatbot)
o TensorFlowseq2seqlibraryo Implementation1onTensorflowwithseparableencoderanddecodero Implementation2onKeras
• VisualStorytellingDataset(VIST)o Visualstorytellingalgorithms:
§ NoMetricsArePerfect:AdversarialREwardLearningforVisualStorytelling:sourcecodes(TensorFlow)
• VisualGenomeisadataset,aknowledgebase,anongoingefforttoconnectstructuredimageconceptstolanguage.
• MPIIMovie&Descriptiondatasetforautomaticvideodescription,videosummary,videostorytelling
• Bidirectionalrecurrentneuralnetworks(B-RNN):o Graves,Alan,NavdeepJaitly,andAbdel-rahmanMohamed."Hybridspeech
recognitionwithdeepbidirectionalLSTM."IEEEWorkshoponAutomaticSpeechRecognitionandUnderstanding(ASRU),2013.[pdf]
• Deepreinforcementlearningo References:
§ Mnih,Volodymyr,KorayKavukcuoglu,DavidSilver,AlexGraves,IoannisAntonoglou,DaanWierstra,andMartinRiedmiller."Playingatariwithdeepreinforcementlearning."arXivpreprintarXiv:1312.5602(2013).
§ Mnih,Volodymyr,KorayKavukcuoglu,DavidSilver,AndreiA.Rusu,JoelVeness,MarcG.Bellemare,AlexGravesetal."Human-levelcontrolthroughdeepreinforcementlearning."Nature518,no.7540(2015):529-533.[sourcecode]
§ HowtoStudyReinforcementLearningo Sourcecodes:
§ ImplementationofReinforcementLearningAlgorithms.Python,OpenAIGym,Tensorflow.ExercisesandSolutionstoaccompanySutton'sBookandDavidSilver'scourse.[link]
• GenerativeAdversarialNetwork(GAN)o References:
§ Goodfellow,Ian,JeanPouget-Abadie,MehdiMirza,BingXu,DavidWarde-Farley,SherjilOzair,AaronCourville,andYoshuaBengio."Generativeadversarialnets."InAdvancesinneuralinformationprocessingsystems,pp.2672-2680.2014.
§ Radford,Alec,LukeMetz,andSoumithChintala."Unsupervisedrepresentationlearningwithdeepconvolutionalgenerativeadversarialnetworks."arXivpreprintarXiv:1511.06434(2015).
§ Arjovsky,Martin,SoumithChintala,andLéonBottou."WassersteinGAN."arXivpreprintarXiv:1701.07875(2017).
o TypesofGAN1. VanillaGAN2. ConditionalGAN
3. InfoGAN4. WassersteinGAN5. ModeRegularizedGAN6. CoupledGAN7. AuxiliaryClassifierGAN8. LeastSquaresGAN9. BoundarySeekingGAN10. EnergyBasedGAN11. f-GAN12. GenerativeAdversarialParallelization13. DiscoGAN14. AdversarialFeatureLearning&AdversariallyLearnedInference15. BoundaryEquilibriumGAN16. ImprovedTrainingforWassersteinGAN17. DualGAN18. MAGAN:MarginAdaptationforGAN19. SoftmaxGAN
o Sourcecodes:§ ATensorflowImplementationof"DeepConvolutionalGenerative
AdversarialNetworks":pythoncode§ Collectionofgenerativemodels,e.g.GAN,VAEinPytorchand
Tensorflow:pythoncode• SequentialGenerativeAdversarialNetwork(GAN)
o References:§ Yu,Lantao,WeinanZhang,JunWang,andYongYu."SeqGAN:
SequenceGenerativeAdversarialNetswithPolicyGradient."InAAAI,pp.2852-2858.2017.
§ Mogren,Olof."C-RNN-GAN:Continuousrecurrentneuralnetworkswithadversarialtraining."arXivpreprintarXiv:1611.09904(2016).
§ Im,DanielJiwoong,ChrisDongjooKim,HuiJiang,andRolandMemisevic."Generatingimageswithrecurrentadversarialnetworks."arXivpreprintarXiv:1602.05110(2016).
§ Press,Ofir,AmirBar,BenBogin,JonathanBerant,andLiorWolf."LanguageGenerationwithRecurrentGenerativeAdversarialNetworkswithoutPre-training."arXivpreprintarXiv:1706.01399(2017).
o Sourcecodes:§ ImplementationofC-RNN-GAN§ TensorflowImplementationofGANmodelingforsequentialdata
• StanfordNLPParser:Anaturallanguageparserisaprogramthatworksoutthegrammaticalstructureofsentences.
• Performancemetricsforanaturallanguageparser• Precisionandrecall• mAP(meanAveragePrecision)forObjectDetection• Questionanswering
o References:
§ Seo,Minjoon,AniruddhaKembhavi,AliFarhadi,andHannanehHajishirzi."Bidirectionalattentionflowformachinecomprehension."arXivpreprintarXiv:1611.01603(2016).
o Sourcecodes:§ Bi-DirectionalAttentionFlow(BIDAF)
o Questionansweringdatasets:§ StanfordQuestionAnsweringDataset(SQuAD)§ NewsQA§ MSMARCO
• TheGeneralLanguageUnderstandingEvaluation(GLUE)benchmarkisacollectionofresourcesfortraining,evaluating,andanalyzingnaturallanguageunderstandingsystems.
• SemanticTextualSimilarity(STS)benchmarkevaluationdataset• Automatictextunderstandingandreasoning:
o FacebookbAbIprojecto Facebookdataseto Pythoncode
• NLTKsentimentanalysistool• OpinionLexicon(dictionaryofsentimentwords):PositiveandNegative• Humanactivityrecognition
o HMDB:alargehumanmotiondatabase§ Actionrecognitionalgorithms
o UCF101:ActionRecognitionDataSet§ Activityrecognitionalgorithms
• Coronavirusdataset• BatchNormalizationandWeightDecayNotes• MATLAB Tutorial• MATLAB Central• MatlabPrimer,MatlabManuals,ImageProcessingToolbox• Matlabimplementationofimage/videocompressionalgorithms• IntroductiontoMatarixAlgebra(freebookbyAutarKKaw,Professor,
UniversityofSouthFlorida).• MatrixReferenceManual• HIPR2:aWWW-basedImageProcessingTeachingMaterialswithJ• Learningbysimulations• OpenCV• OpenGL• ARecipeforTrainingNeuralNetworks(byAndrejKarpathy)• Downloadthefollowingfree(opensource)programtorecordvideowithscreen
capture:http://www.nchsoftware.com/capture/index.html?gclid=CNadwsW6-6wCFSVjTAodbjzTSg
Software:
• VirtualDub:VirtualDubisavideocapture/processingutilityfor32-bitWindowsplatforms(95/98/ME/NT4/2000/XP),licensedundertheGNUGeneralPublicLicense(GPL).
• XnView:isanefficientmultimediaviewer,browserandconverter.• ImageJ:ReadandwriteGIF,JPEG,andASCII.ReadBMP,DICOM,andFITS.[Open
Source,PublicDomain]• Opensourceforimageprocessing
tasks:http://octave.sourceforge.net/doc/image.html
JOURNALS
Elsevier
• ComputerVisionandImageUnderstanding• JournalofVisualCommunicationandImageRepresentation• Data&KnowledgeEngineering• ImageandVisionComputing• PatternRecognition• PatternRecognitionLetters
IEEE
• IEEETransactionsonCircuitsandSystemsforVideoTechnology• IEEETransactionsonMultimedia• IEEETransactionsonImageProcessing• IEEETransactionsonMedicalImaging• IEEETransactionsonPAMI
ComputerVision
• ComputerVisionHomepageatCMU• AnnotatedComputerVisionBibliographyfromUSCIRIS• CVonline:TheEvolving,Distributed,Non-Proprietary,On-LineCompendiumof
ComputerVision• 3-DforEveryone• Red-blueglassesoranaglyphfor3D
viewing:http://www.best3dglasses.com/anaglyph.html• Shutterglassesfor3Dviewing:http://www.stereo3d.com/shutter.htm• 3Dcameras:http://www.ptgrey.com/index.asp• 3Dphotosathttp://www.jessemazer.com/3Dphotos.html
• 3Dvideosequencescanbedownloadedat:http://research.microsoft.com/vision/InteractiveVisualMediaGroup/3DVideoDownload/
PublicDomainImageDatabases
CMUDatabase