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：10
页码：15920
DOI：10.15680/IJIRCCE.2017.0510046
出版社：S&S Publications
摘要：Consider objects that are tagged with keywords and are embedded in a vector space. The presence ofkeywords in feature space allows for the development of new tools to query and explore these multi-dimensionaldatasets. We propose a method called Projection and Multi Scale Hashing that uses random projection and hash-basedindex structures, and achieves high scalability and speedup. In multi-dimensional spaces, it is difficult for users toprovide meaningful coordinates, and our work deals with another type of queries where users can only providekeywords as input. Images are represented using color feature vectors, and usually have descriptive text information(e.g., tags or keywords) associated with them. Our system is based on real datasets shows that we can show the efficientsearching of keywords in multidimensional datasets..
