an emphasized dual similarity measure integration for online image retrieval system using simrank

1
International Journal of Computing Algorithm, Vol 4(1), June 2015 ISSN(Print):2278-2397 Website: www.ijcoa.com An Emphasized Dual Similarity Measure Integration for Online Image Retrieval System Using SimRank R. Raj Kumar 1 , M.Krishnamurthy 2 1 PG Scholar, Department of CSE, KCG College of Technology, Chennai, Tamil Nadu, India 2 Professor & Head ME-CSEKCG College of Technology, Chennai, Tamil Nadu, India E-mail: [email protected], [email protected] Abstract In the real world scenario the use of image grows rapidly, the image rich network is the one that comprises of billions of images. The social media websites, such as Picasa, Flickr and Facebook comprises billions of end user posted images along with their annotations. Similarly the electronic commerce website such as Flipkart, Myntra and Amazon are also furnished with product related images. In this paper, we introduce how to perform efficient and optimum information retrieval in online image rich system. We propose a Mok-Sim Rank to compute link-based similarity and a dual similarity integration algorithm for both link and content based similarity. Experimental results on online electronic commerce site show that our approach is significantly better than traditional methods in terms of relevance.

Upload: international-journal-of-computing-algorithm

Post on 04-Dec-2015

214 views

Category:

Documents


1 download

DESCRIPTION

In the real world scenario the use of image grows rapidly, the image rich network is the onethat comprises of billions of images. The social media websites, such as Picasa, Flickr andFacebook comprises billions of end user posted images along with their annotations.Similarly the electronic commerce website such as Flipkart, Myntra and Amazon are alsofurnished with product related images. In this paper, we introduce how to perform efficientand optimum information retrieval in online image rich system. We propose a Mok-Sim Rankto compute link-based similarity and a dual similarity integration algorithm for both link andcontent based similarity. Experimental results on online electronic commerce site show thatour approach is significantly better than traditional methods in terms of relevance.

TRANSCRIPT

Page 1: An Emphasized Dual Similarity Measure Integration for Online Image Retrieval System Using SimRank

International Journal of Computing Algorithm, Vol 4(1), June 2015

ISSN(Print):2278-2397

Website: www.ijcoa.com

An Emphasized Dual Similarity Measure Integration for Online Image Retrieval System

Using SimRank

R. Raj Kumar1, M.Krishnamurthy2

1PG Scholar, Department of CSE, KCG College of Technology, Chennai, Tamil Nadu, India 2Professor & Head ME-CSEKCG College of Technology, Chennai, Tamil Nadu, India

E-mail: [email protected], [email protected]

Abstract In the real world scenario the use of image grows rapidly, the image rich network is the one that comprises of billions of images. The social media websites, such as Picasa, Flickr and Facebook comprises billions of end user posted images along with their annotations. Similarly the electronic commerce website such as Flipkart, Myntra and Amazon are also furnished with product related images. In this paper, we introduce how to perform efficient and optimum information retrieval in online image rich system. We propose a Mok-Sim Rank to compute link-based similarity and a dual similarity integration algorithm for both link and content based similarity. Experimental results on online electronic commerce site show that our approach is significantly better than traditional methods in terms of relevance.