An efficient fast-response content-based image retrieval framework for big data. (August 2016)

• Record Type: Journal Article
• Authors: Sakr, Noha A.; ELdesouky, Ali.I.; Arafat, Hesham
• Is Part Of: Computers & electrical engineering. Volume 54(2016)
• Page Start: 522
• Page End: 538
• Publication Date: 2016-08
• Subjects: CBIR -- Feature Extraction -- BOVW -- Image indexing -- Hadoop -- MapReduce -- Clustering; Computer engineering -- Periodicals; Electrical engineering -- Periodicals; Electrical engineering -- Data processing -- Periodicals; Ordinateurs -- Conception et construction -- Périodiques; Électrotechnique -- Périodiques; Électrotechnique -- Informatique -- Périodiques; Computer engineering; Electrical engineering; Electrical engineering -- Data processing; Periodicals; Electronic journals; 621.302854
• DOI: 10.1016/j.compeleceng.2016.04.015
• Languages: English
• ISSNs: 0045-7906

Abstract

Abstract: In this paper, an efficient fast-response content-based image retrieval (CBIR) framework based on Hadoop MapReduce is proposed to operate stably with high performance targeting big data. It provides a novel bag of visual words (BOVW) technique based on a proposed chain-clustering binary search-tree (CC-BST) algorithm to build the visual statements for representing the image. As well, it introduces a proposed methodology for creating representatives for these visual statements as a solution for big-data' high-dimensionality. Further, those representatives are utilized to provide an indexing scheme for building one large file as an input for Hadoop. Moreover, an efficient-MapReduce technique is presented to exploit the created visual-representatives of the images to retrieve the top-relevant images for the input query. Empirical tests for the proposed techniques outperform the state-of-art compared techniques.