SUMMARY GENERATION FOR LECTURING VIDEOS

International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056

Volume: 09 Issue: 07 | July 2022 www.irjet.net p-ISSN: 2395-0072

SUMMARY GENERATION FOR LECTURING VIDEOS

R Anish1 , Shashank P3 , Suraiya Anjum3 , Sushma K4 , Prof. Puneeth P5

*1,2,3,4,5 Department of Information Science and Engineering, Maharaja Institute of Technology, Mysore, Karnataka, India ***

ABSTRACT

Onlinelecturesandonlinecoursessharethesamemassconceptualcontentallstoredintoonelargevideo.Astheworldis progressingtowardsadvancementinthetechnologysoistheproductionofhighvolume,highdensitydata.Manyuniversities adaptedtoe learningduetothepandemicandnotallwillaccessthesevideosmultipletimestounderstandtheconceptsasthey arelong.Thustheextractionofimportantandusefultopicsfromthelecturingvideosistheareawhichhasn'tbeenexploredin greatyet.Particularareaishavingahugepotentialofresearchandimplementationasfarastherealapplicationsareconcerned. Videohighlightsorsynopsisistheabstractionofthemaineventsinvideoorimagecollection.Itisusedinordertohighlightthe entirevideotoeasilyinterpretwhatitisbeingtriedtoconclude.Withthishighlightingprocesswecaneasilyunderstandand reviseonconceptsthatareimportantandpartsofvideoscontaininginterest.highlightvideosofimportantconceptswhichwill easetheprocessofrevisionandlearning.Contenthighlightsfacilitatesusinsimplifyingthelearningprocess.Oneofourmain objectivesistosavetimeandaccesstheimportanttopicswhichisrequiredbytheviewerasfastaspossible.

Keywords: Yake,EasyOCR,frameselection,textdetection

I. INTRODUCTION

Theinternetisfloodedwithanenormousamountofvideosandtextscanquicklyscanthetextandseeifthereisanycontent inthevideo.Summaryversionsofthevideoswillbealifesavingasset.Recordedvideosoflecturesaregainingpopularityasa basictoolfordistanceeducationaswellasa supplementarytoolforface to faceeducation.Studentsgetinformationfrom videos,butthetimecostofgoingthroughthesevideosespeciallyforlonglecturevideoswillbehigh,sotosolvethis,weneedto automatically capture the gist and essential topics in the videos, the video summary meets this requirement. Video summarizationisdefinedastheprocessofgeneratingasummaryofalongvideobyselectingthemostinformativefortheuser. ThisthesisemphasizesthesurveyforgeneratinglecturesummarieswhereweuseCV2forvideotoimageconversion,easyOCR fortextdetection,mergingandgeneratingvideosummarywithtextgeneration.

II. LITERATURE REVIEW

[1] Inthispaperaframeworkforautomaticsummarizationofvideos.TheSumBotframeworkisspeciallydesignedfor scenarioswherethesummarizationprocessfollowsasemi structurededitingtemplate.

[2] Inthispapertheanchor basedDSNetapproachformulatesthevideosummaryasafocusdetectionproblemandthe importancescoreandpositionfromthegeneratedinterestsuggestions

[3] Inthispaperanincrementalframeworkforsubsetselection.Ateachpoint,itupdatesthesetofrepresentativeswith thepreviouslyselectedsetofrepresentativesandthenew datastack.

[4] InthispaperAPCDLframeworkforvideosummarizationtasksthatgeneratevideosummariesusingaduallearning frameworkandconstraintsonsummarizationproperties.

[5] InthispaperAnovelapproachtoadeepvideosummarycalledADSumisused togeneratethesummary.

[6] Inthis paper,automaticcricketvideohighlights will be generated byconsideringsome ofthecriteria like scores, audiencevoiceandchangeinthescore.

[7] InthispaperThe staticandmotionsimilarityscoresofclipswiththeappropriateadaptationthresholdsareusedto mergeconsistentclips.Uselocalstaticandmotionsimilaritiestoadjusttheboundariesbetweenclips

[8] InthispaperAscenechangedetectionalgorithmbasedonpositionanalysishasbeenproposedforframerateup conversion.Theproposedalgorithmcalculatesstatisticsaftergeneratinga2Dhistogramtoextracttheshapeofthe histogram.

© 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page2216

International Research Journal of Engineering and Technology (IRJET) e ISSN: 2395 0056

Volume: 09 Issue: 07 | July 2022 www.irjet.net p ISSN: 2395 0072

III. SURVEY FINDINGS

Generatingshortsummariesorhighlightsofrecordedvideocontentisanessentialtasknotonlyforpublishingcontent on videosharingplatforms,butalsoforvideoassetmanagement.Thealgorithmsusedareavideosummarycreatedwithunpaired dataandadeeplearningframeworkwithunpaireddata.Videosummariesareintendedtocreateaconcisesummarytoextract the most useful parts of the video. This is essential for humans to effectively and efficiently search and understand large amounts of video data in a user friendly way. This is usually formulated as a supervised learning problem that learns a spatiotemporalmappingfunctionforselectingkeyframesorsubframesfromavideosequence.

IV. METHODOLOGY

Ouralgorithmusesthetextualinformationforextractionmethod.Thetextualinformationwhichisextractedfromeach frame.FirstitrecognizesthetitleintheslideandconvertthetextofthetitleintoasentencebasedonthealgorithmslikeOCR andCNN.Whentextualinformationisavailable,titledifferencesarerecognizedandinformationabouttopicsthathavechanged foreachtopicisprovided.Thisformsthebasisfordetectingchangesinthescene.Thiscapturestheframeswherethescene changesoccurandcombinesthemtocreatehighlights.OCR(Opticalcharacterrecognition)convertsthedigitalimageintoa machine codedtextelectronically.Here,thedigitalimageisgenerallyanimageincludingaregionsimilartothecharactersofthe language.OCRcanbeusedinartificialintelligence,patternrecognitionandcomputervision.ThisisbecausethenewOCRis trainedbyprovidingsampledatathatisexecutedviamachinelearningalgorithms.Thistechniqueofextractingtextfroman imageisusuallydoneinaworkenvironmentwhereyouarecertainthattheimagecontainstextdata.

Figure 1: SystemArchitecture

International Research Journal of Engineering and Technology (IRJET) e ISSN: 2395 0056

Volume: 09 Issue: 07 | July 2022 www.irjet.net p ISSN: 2395 0072

Figure 2 : VideoSnapshot

Figure 3 : VideoSnapshot

International Research Journal of Engineering and Technology (IRJET) e ISSN: 2395 0056

V. DATA FLOW DIAGRAMS

Figure 4: Dataflowdiagramtonovelapproachofsummarygenerationoflecturingvideos

Volume: 09 Issue: 07 | July 2022 www.irjet.net p ISSN: 2395 0072 © 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal |

International Research Journal of Engineering and Technology (IRJET) e ISSN: 2395 0056

Volume: 09 Issue: 07 | July 2022 www.irjet.net p ISSN: 2395 0072

VI.USE CASE MODEL

Figure 5: UseCaseModel

VII. RESULTS AND DISCUSSION

HerewetriedtogeneratethesummaryforPowerPoint basedlecturingvideoswhichisverymuchbeneficialforstudents. Wheretheuserneedstouploadalecturingvideousingtheuserinterfaceprovided,oncethevideoisuploadedsuccessfully,a summaryvideowithtextisgenerated.Oncethevideoisgeneratedtheusershouldcopythelinkandpasteitintothebrowserto downloadthesummarizedvideo.

Figure 3: UserInterface

2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified

International Research Journal of Engineering and Technology (IRJET) e ISSN: 2395 0056

Volume: 09 Issue: 07 | July 2022 www.irjet.net p ISSN: 2395 0072

Figure 4: SummaryVideowithTextGeneration

Figure 5: AccuracyAnalysisbetweennon educationalandeducationalvideos

VII. CONCLUSION

ThemainaimofthisprojectisasummarygenerationforlecturingvideosVideoSummarizationorsynopsisistheabstraction ofthemaineventsinvideoorimagecollection.itisusedtosummarizetheentirelecturingvideoandprovideonlytheimportant conceptsthatisbeingcoveredinthatsession.Withthissummarizationprocess,wecaneasilyunderstandandreviseconcepts that are important and parts of videos containing interest. The proposed system will generate highlights of PowerPoint presentationvideosandblackboardtaughtvideosbyextractingthetextfromtheimages/framesofthevideosandidentifying thechangeintextualinformationbetweenframes.Someimportantconceptsmayormaynotbeidentifiedproperlyinthecaseof poorvideo/imagequality.

IX. FUTURE WORK

InourproposedsystemweareimplementingitonlyforthePowerPoint basedlecturingvideos.Inviewoffutureenhancement, wetrytoimplementthevideosummarizationtechniqueforchalkandboardlecturingvideosinwhichthemachineneedstobe trainedinaveryefficientmannertoprovidetheexpectedoutput.

International Research Journal of Engineering and Technology (IRJET) e ISSN: 2395 0056

X. REFERENCES

[1] “SumBot:SummarizeVideosLikeaHuman”byHongxiangGu,StefanoPetrangeliandViswanathanSwaminathanin 2020.

[2]“DSNet:AFlexibleDetect to SummarizeNetworkforVideoSummarization”byWenchengZhu,JiwenLu,JiahaoLiand JieZhouin2021

[3] “OnlineSummarizationviaSubmodularandConvexOptimization”byEhsanElhamifarandM.ClaraDePaolisKaluzain 2017

[4]“Property ConstrainedDualLearningforVideoSummarization“byBinZhao,XuelongLiandXiaoqiangLuin2019.

[5] “DeepAttentiveVideoSummarizationWithDistributionConsistencyLearning”byZhongJi,YuxiaoZhao,YanweiPang, XiLiandJungongHanin2020.

[6] “AMultimodalapproachforautomaticcricketvideosummarization”byAmanBhalla,ArpitAhuja,PradeepPantand AnkushMittalin2019.

[7] “UnsupervisedVideoSummarizationbasedonconsistentclipgeneration”ByXinAi,YanSong,ZechaoLiin2018.

[8] “Positionalanalysis basedscenechangedetectionalgorithm”bySuk Ju Kangin2015.

[9]“VideoSummarizationbylearningfromunpaireddata“byMrigankRochanandYangWangin2020.

[10] “VideoSummarizationbylearningdeepsidesemanticembedding”ByYitianyuan,TaoMei,PengcuiandWenwuZhu in2017.

[11] “UnsupervisedVideoSummarizationFrameworkusingKey FrameExtractionandVideoSkimming”byShrutiFadon andMahmoodJasimin2020.

[12] “ANewApproachtoExtractingSportsHighlights”byPichetSuksaiandParujRatanworabhanin2016

[13] “AnEfficientFrameworkforAutomaticHighlightsGenerationfromSportVideos”byAliJaveed,KhalidBhasirBajura, HafizMalik,AunIrtazain2016.

[14] “VideoSummarizationviaActionRanking“byMohammedElfekandAliBajin2019.

[15] “Cloud AssistedMulti ViewVideoSummarizationUsingCNNandBi LSTM”byTanvirHussain,KhanMohammed, AminUllah,ZehongCao,SungwookBaikandVictorHugoDeAlborquerquein2019.SummaryGenerationforLecturing Videos2021 22DepartmentofISE,MITMysore23.

[16] “AutomaticTourVideoSummarizationFocusingonSceneChangeforAdvanceTouristicExperience”byeYukiKanaya, ShogoKawanaka,HirohikoSuwaYutakaArakawaandKeiichiYasumotoin2019.

[17] “HybridApproachforVideoCompressionBasedonSceneChangeDetection”byAnkitaP.Chauhan,RohitR.Parmar, ShankarK.Parmar,ShahidaG.Chauhanin2013.

[18] “ANovelKey framesSelectionFrameworkforComprehensiveVideoSummarization”byChengHuangandHongmei Wangin2018.

[19] “User RankingVideoSummarizationwithMulti StageSpatio TemporalRepresentation”bySiyuHuang,XiLi,Zhongfei Zhang,FeiWu,andJunweiHanin2018.

[20] “MetaLearningforTask DrivenVideoSummarization”byXuelongLi,Fellow,IEEE,HongliLi,andYongshengDongin 2019

Volume: 09 Issue: 07 | July 2022 www.irjet.net p ISSN: 2395 0072 © 2022, IRJET | Impact Factor value: 7.529 | ISO 9001:2008 Certified Journal | Page2222