High Impact Factor : 4.396 icon | Submit Manuscript Online icon |

Web Image Re-Ranking using Semantic Signature

Author(s):

Pawan Kamte , NBN Sinhgad School of Engineering,Pune; Rohoni Sanap, NBN Sinhgad School of Engineering,Pune; Ruchi Thigle, NBN Sinhgad School of Engineering,Pune; Pournima Temkar, NBN Sinhgad School of Engineering,Pune; Rahul Samant, NBN Sinhgad School of Engineering,Pune

Keywords:

Image re-ranking, query image, query keyword, image search, semantic signature

Abstract

Image re-ranking is effective way to improve the result of web-based image search has been adopted by current commercial search engine. A query keyword, a pool of images first retrieved by the search engine based on the information which is given by user in the form of text. Asking the user to select a query image from the set the minus images are re-ranked based on their visual similarities with the query image. Query and Image based recommendation sorted by the method of re-ranking provides an accurate output of images based on the visual semantic signature of the query image. In query based recommendation, expansion of keywords provides better result whereas in image recommendation, re-ranking based on priority of images accessed by other users provides more accurate results. At the online stage, image is re-ranked by comparing their semantic signature obtained from the visual specified by the query keyword.

Other Details

Paper ID: IJSRDV3I1126
Published in: Volume : 3, Issue : 1
Publication Date: 01/04/2015
Page(s): 214-216

Article Preview

Download Article