RETRIEVAL OF TEXTUAL AND NON-TEXTUAL INFORMATION IN CLOUD

Anbarasi M S, Divya R, Buvaneswari P, Illakkiya M

Abstract: With the advent of the Internet there is an exponential growth in multimedia content in various databases, which has a major issue in effective access and retrieval of both textual and non-textual resources. To resolve this problem information is stored in the cloud environment. From Internet the large and complex data cannot be stored and processed using traditional data processing applications. The idea in this proposed method involves parsing of the web page for the extraction of textual data and images. Textual retrieval is done through keyword extraction whereas feature extraction technique is done for the image retrieval. K-means algorithm is used to perform clustering. Based on ranking both the textual data and non-textual data are retrieved together.

Keywords: Retrieval, Feature Extraction, K- means Clustering, Cloud

DOI: https://doi.org/10.15623/ijret.2014.0319092