Re-Ranking Of Web Images Using Semantic Signature and Parallel SVM

Abstract

Image re-ranking has been adopted by current commercial search engines to improve the results of web-based image search. In image re-ranking, for a given a query keyword, first a pool of images are retrieved by the search engine and the user is asked to select a query image from the pool. The remaining images are re-ranked based on their visual similarities with the query image. But there are difficulties in understanding users’ search intention and in learning a universal visual semantic space to characterize the web images. An image re-ranking framework is proposed which automatically offline learns different visual semantic spaces for different query keywords through keyword expansions. The visual features of images are projected into their related visual semantic spaces to get semantic signatures. At the online stage, images are re-ranked by comparing their semantic signatures obtained from the visual semantic space specified by the query keyword. An image can have a single semantic signature or multiple semantic signatures for a specific keyword. Computing multiple semantic signatures for an image has higher precision and re-ranking accuracy than using single semantic signature. But the lengthy combined semantic signatures results in more time consumption. Hence a number of SVMs (Support Vector Machines) can be used in parallel at the online stage which compares multiple semantic signatures at the same time and results are merged at the later stages. Thus images are re-ranked in faster manner while preserving the accuracy

Authors and Affiliations

Nisha Abdul, Kiran V K

Keywords

Related Articles

slugSimulation and Design Analysis of Integrated Receiver System for Millimeter Wave Applications

This paper presents the simulation and design analysis of fully integrated receiver system for millimeter and microwave applications. A beauty thought of new design of CMOS LNA, filter and microstrip antenna are largely...

3-Dimensional Sterling Conception for System Security

Apart from being liable to social engineering attacks, text primarily based secrets are either weak-and-memorable or secure-but-difficult-to-remember If the password is machine generated it's mostly sophisticated for us...

slugCalculating Transmission Coefficient of Double Triangular Quantum Well under Electric Field for Different Structural Parameters

Transmission coefficient of double quantum well triple barrier structure is numerically computed for triangular geometries. Propagation matrix method (PMM) is used for computation purpose over GaAs/Al...

Speed Control of Induction Motor Drive Using Universal Bridge (MATLAB)

When connected to 1- Phase or 3- phase supply connect motor runs, however there are many industrial and domestic application where speed variation is required, many techniques are used for speed variation like voltage c...

Isolation and Screening of Melanin Producing Microorganism

Melanin is negatively charge compound composed of multi-functional polymers and polyphenolic compounds that are produced by various microorganisms by fermentation oxidation. Melanins are frequently used in medicines, ph...

Download PDF file
  • EP ID EP21028
  • DOI -
  • Views 257
  • Downloads 6

How To Cite

Nisha Abdul, Kiran V K (2015). Re-Ranking Of Web Images Using Semantic Signature and Parallel SVM. International Journal for Research in Applied Science and Engineering Technology (IJRASET), 3(6), -. https://europub.co.uk/articles/-A-21028