Web Image Search Reranking Using CBIR

Abstract

The existing image retrieval process is based on text-based approach where the input to the search engine is given as the text. Typically, in the development of an image requisition system, semantic image retrieval relies heavily on the related captions, e.g., file-names, categories, annotated keywords, and other manual descriptions. Unfortunately, this kind of textual-based image retrieval always suffers from two problems: high-priced manual annotation and inappropriate automated annotation. To overcome this drawback the proposed work is defined based on CBIR system. The mission of this work is to present an image conceptually, with a set of low-level visual features such as color, texture, and shape and retrieve similar kind of images from the database based on features extracted from the query image. Input to the search engine is given as “Image” itself and this method serves to visually represent the query. Subsequently based on the multi-feature image extraction, Rerankers are constructed which are used to rank the top N output based on the query image. This ensures high accuracy and reliability with less noise in the displayed result.

Authors and Affiliations

V. Vinitha , Dr. J. Jagadeesan , R. Augustian Isaac

Keywords

Related Articles

Spectral Subtraction for Speech Enhancement and Compression Using LPC 

Pre-Processing of Speech Signal is very crucial in the applications where silence or background noise is completely undesirable. The degradation of speech due to the presence of noise causes severe difficulties in variou...

Security against attacks in TOR networks

TOR( The Onion Router) network is a system that provide anonymity for its client by routing the client packets via various volunteering networks, such routing conceals the clients location & activity thus making traf...

A Study for Finding Location of Nodes in Wireless Sensor Networks

The popularity of Wireless Sensor Network (WSN) has increased tremendously in recent times. WSN has the potential to connect the physical world with the virtual world by forming a network of sensor nodes. Sensor nodes tr...

Peer to Peer Cooperation for Caching in Wireless Networks

Some recent studies have shown that cooperative cache can improve the system performance in wireless P2P networks such as ad hoc networks and mesh networks. All these studies are at a very high level, leaving many design...

TUMOR VOLUME CALCULATION OF BRAIN FROM MRI SLICES

The main objective of this paper is to calculate volumes of brain tumors from sagittal, axial and coronal orientations. Brain tumor detection is a most important area in medical image processing. Brain cancer is a diseas...

Download PDF file
  • EP ID EP162759
  • DOI -
  • Views 112
  • Downloads 0

How To Cite

V. Vinitha, Dr. J. Jagadeesan, R. Augustian Isaac (2014). Web Image Search Reranking Using CBIR. International Journal of Computer Science & Engineering Technology, 5(4), 348-360. https://europub.co.uk./articles/-A-162759