期刊名称：International Journal of Innovative Research in Computer and Communication Engineering
印刷版ISSN：2320-9798
电子版ISSN：2320-9801
出版年度：2015
卷号：3
期号：11
DOI：10.15680/IJIRCCE.2015.0311027
出版社：S&S Publications
摘要：The expanded accessibility of broadband associations has as of late prompted an increment in theutilization of Internet webcasting. Record lectures and positioning them on the Web for contact by understudies hasturned into a overall pattern at dissimilar colleges. Videos and Texts demonstrated in lecture are nearly identified withsubstance of the lecture, gives important source for recovering lecture videos and indexing. Text substance may beseparated, then analyse and deducted consequently by OCR (Optical Character Recognition) strategies. In this paper,for remedying lapses in the OCR Transcriptions, we investigated two separate systems connected just to unmatchedquestion words. In the first place strategy produces original set of n-gram strings to match the complete OCRTranscriptions. This n-gram incorporate string with an altered separation of 1 character and all conceivable n-gramsubstrings with no less than 3 characters. Second system for redressing OCR included the word reference of spellingadjustment strategy gave in MS Words. And second module of video summarization i.e. recent years, it has picked upan extensive passion of specialists and in scholastics from dissimilar regions. While distinguishing video occurrencehas been the subject of broad study activities as of late, significantly less existing system has considered multi-modeldata and issues related effectiveness. Start of soccer matches dissimilar uneasy circumstances develop that can't beadequately judged by the ref board of trustees. A framework that checks equitably picture courses of action wouldforestall not right understandings in view of a few mistakes, or high speed of the occasions. Bayesian networks give astructure for managing this uncertainty using a basic graphical structure also the probability calculus. We propose anefficient structure for analysing and summarization of soccer videos using object based features. The proposed workutilizes the t-cherry junction tree, an exceptionally recent advancement in probabilistic graphical models, to create acompact representation and great approximation intractable model for client’s relationships in an interpersonalorganization.
关键词：pervasive computing; lecture videos; automatic text indexing; OCR; lecture video; Summarization;finding; Bayesian network; Web intelligence.
