Content-Based Image Retrieval Based on Affine Noisy Invariant Color Region

Journal Title: International Research Journal of Applied and Basic Sciences - Year 2013, Vol 6, Issue 5

Abstract

The content-based image retrieval methods retrieve images by image features. In this paper, color and gray affine noisy invariant regions are extracted from a query and database images to help accurate retrieval on different attacks. Also a number of color statistical properties of the color region are computed and color feature vectors establishes for this region. Besides, for the gray region, only a 64 ? 1 feature vector is obtained applying vector quantization and codebook generation based on the Linde-Buzo-Gray algorithm, which reduces retrieval feature comparison calculations. Finally combination of both gray and color affine noisy invariant regions improves the retrieval system efficiency. In order to optimize weighting combination coefficients of the color feature vectors with the gray feature vector, the particle swarm optimization algorithm is applied. The experimental results show a real-time content-based image retrieval system with higher accuracy and acceptable retrieval time.

Authors and Affiliations

Amin Abdullahzadeh| Department of Electrical & Computer Engineering, University of Sistan and Baluchestan, Farahnaz Mohanna| Department of Electrical & Computer Engineering, University of Sistan and Baluchestan, email: F_mohanna@ece.usb.ac.ir

Keywords

Related Articles

A Critical Survey of Contrastive Analysis Hypothesis in a Multilingual(Persian & Turkish and English Context) Community

Contrastive Analysis Hypothesis emerged on the basis of structural linguistic and behavioral psychology. To define merits and demerits of CAH, three different versions of it had been proposed by various scholars since 19...

The effect of information and relations technologies on increasing labor outcome

The aim of present study is inventing the relation between applying information and relations technologies and analyzing its role in increasing labor outcome in Melat bank of Borojerd city. The statistic society of this...

Needs Assessment Of Kerman’s Emergency Medical Staff In The Context Of Communal Sports And Introduce Appropriate Solutions

The Main Objective of This Study Was to Indentify and Prioritize the Communal Sports Needs of Emergency Medical staff of Kerman Province. The Research Method Was Descriptive And The Statistical Community Was Considered T...

Comparison of biometric

In today's developing world which is moving fast towards using new techniques, using techniques like biometric in different fields can have a wonderful contribution in the development of security systems. To use any tech...

The shear strength analyses of soil with various compactions under vertical load in direct shear test

One of the oldest tests to determine the shear strength of soil is direct shear test. With regard to this test, the stresses on a surface which failure occurred are controlled during the test directly. The purpose of com...

Download PDF file
  • EP ID EP6172
  • DOI -
  • Views 363
  • Downloads 8

How To Cite

Amin Abdullahzadeh, Farahnaz Mohanna (2013). Content-Based Image Retrieval Based on Affine Noisy Invariant Color Region. International Research Journal of Applied and Basic Sciences, 6(5), 598-606. https://europub.co.uk/articles/-A-6172