Effective Relevance Feedback for Content Based Image Retrieval Using Mining Navigation Pattern and SEO Tools

Abstract

with a rapid increase of images that are available in social blog and media, image annotation has evolved as an important thing due to its application in image toning and retrieval. Most studies cast image annotation into a multi label classification problem. Images with complete annotations in order to learn a reliable model for tag prediction. We address this limitation by developing a novel approach that combines the strength of tag ranking with the power of matrix recovery. Instead of having to make a decision for each tag, our approach ranks tags in the descending order of their relevance to the given image, significantly simplifying the problem. In addition, the proposed method aggregates the prediction models for different tags into a matrix, and casts tag ranking into a matrix recovery problem, so that a reliable prediction model can be learned for tag ranking even when the tag space is large and the number of training images is limited. Experiments on multiple well-known image data sets demonstrate the effectiveness of the proposed framework for tag ranking compared with the state-of-the-art approaches for image annotation and tag ranking.

Authors and Affiliations

M. Sridharan, N. Bala Sundara Ganapathy, M. Jerome Felix, S. Sivakumar

Keywords

Related Articles

Industrial Conflict: Conflict Necessary For Creativity

In today’s business scenario organizations are facing a major issue in the form of Conflict which requires attention. Conflict can be functional or dysfunctional. Functional conflict is for improvement whereas Dysfuncti...

Comparative Study of Slosh Suppression Devices and Techniques for Liquid and Hybrid Rocket Propellant Tanks

The present study reviews and discusses about the undesirable phenomenon of propellant sloshing in propellant tanks of liquid and hybrid rocket engines. The occurrence of unexpected sloshing in propellant tanks usually...

Survey Paper for Result Alert System

Students have to search the internet each time to know about any news updates like payments, result etc. in the college website. In our project, we will implement E-mail & SMS technology for the fast and reliable procur...

Contribution of Foreign Direct Investment in India: Its Growth and Issues

Foreign Direct Investment acts as a bridge to fulfill the gap between investment and saving. In the process of economic development foreign capital helps to cover the domestic saving constraint and provide access to the...

Structural Health Monitoring Of RCC Slab Using PZT Material: An Overview

In order to study the damage detection or structural health monitoring of RCC slab by the using of PZT smart material. During the process of monitoring or analyzing the damage, simply PZT patches are attached to the sur...

Download PDF file
  • EP ID EP21969
  • DOI -
  • Views 174
  • Downloads 3

How To Cite

M. Sridharan, N. Bala Sundara Ganapathy, M. Jerome Felix, S. Sivakumar (2016). Effective Relevance Feedback for Content Based Image Retrieval Using Mining Navigation Pattern and SEO Tools. International Journal for Research in Applied Science and Engineering Technology (IJRASET), 4(4), -. https://europub.co.uk/articles/-A-21969