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：2017
卷号：5
期号：2
页码：1439
DOI：10.15680/IJIRCCE.2017.0502024
出版社：S&S Publications
摘要：In this paper, the semantic link network model is used for analyzing multimedia big data and performsimage recognition in social networks through collaborative filtering. A whole model for generating the associationrelation between multimedia resources using semantic link network model is proposed. The definitions, modules, andmethods of the semantic link network are used in the proposed method. The tags and the adjoining texts of multimediaresources are used to measure their semantic association. The modules of semantic link network model areimplemented to quantify association relations. A real data set including 100 thousand images with social tags fromFlickr is used in our experiments. Two evaluation methods, including clustering and retrieval, are performed, whichshows the proposed method can measure the semantic relatedness between Flickr images correctly and robustly. Facerecognition (FR) has been at the crux of more than a few novel breakthroughs over the past two decades and hasprogressively proffered several cross-domain applications that range from mainstream commercial software to criticallaw enforcement applications. Recent innovative developments in Big Data analysis, Cloud Computing, SocialNetworks and Machine learning have immensely transformed the conventional view of how several dreadful problemsin Computer Vision can be tackled. Hence in this paper, we will provide a thorough survey of the concepts of CloudComputing, Big Data, Social networks and Machine Learning from a recent outlook of FR, and proffer a framework fora novel FR approach based on the Extreme Learning Machines technique to perform the task of Face Tagging forSocial Networks operating on Big Data.
关键词：Big data; multimedia resources; semantic link network; Big data application; cluster; collaborative;filtering; FR.
