AN INTELLECTUAL BASED RE-RANKING FOR IMAGE SEARCH IN WEB

S.Aiswarya; B.Gayatri; S.Gayathri; M.Archana Devi

Article Information

Published In Volume 2, Issue 3 (2016)
Publication Date July 27, 2026
Manuscript ID IJCRCST-MARCH16-08
Article Type Research Paper
Pages 517 - 519
6 Views 0 Downloads

Abstract

Image search is a specialized data search used to find images. Due to the lack of visual information and context of information, the searching results are unsatisfactory at most of the times. Therefore, image re-ranking which incorporates visual features of images to improve text based image searching is introduced. In this paper, we propose to exploit semantic attributes for image search re-ranking. i.e. The is image represented by an attribute feature. Then we propose a visual-attribute joint hyper graph learning approach to simultaneously explore two information sources. A hypergraph is constructed to model the relationship of all images. We conduct experiments on more than 1,000 queries in MSRA-MMV2.0 data set. The experimental results demonstrate the effectiveness of our approach.

Keywords

Image Search Feature Extraction ranking factors

Authors

S.Aiswarya

B.Gayatri

S.Gayathri

M.Archana Devi

How to Cite this Article

S.Aiswarya, B.Gayatri, S.Gayathri, M.Archana Devi (2016). "AN INTELLECTUAL BASED RE-RANKING FOR IMAGE SEARCH IN WEB". International Journal of Contemporary Research in Computer Science and Technology, 2(3), pp. 517-519.