International Journal of Advanced Computing and Communication Systems

Content Based Image Retrieval Based on Global and Region Content of an Image

Kavitha H, Dept. of ISE Siddaganga Institute of Technology, Tumkur, Karnataka, India.

Sudhamani M V, RNS Institute of Technology, Benguluru, Karnataka, India.

International Journal of Advanced Computing and Communication Systems

ISSN (Online) : 2347 - 9299

ISSN (Print) : 2347 - 9280

Received On :

Revised On :

Accepted On :

Published On :

Volume 01, Issue 03

Page No : 014-018

Abstract

In this paper we present efficient content based image retrieval system based on the visual features like based on color features and the other is retrieval based on combined features. When the retrieval based on color fails, texture and color. In our work the first step is the the user uses the other alternative which is the combined extraction of the texture features by using the Gabor filters form the whole image or for region formed after segmentation. Gabor filter (or Gabor wavelet) is widely adopted in image retrieval systems to extract texture retrieval. Since the texture features are extracted globally from the image, they are not an accurate description of the image in some cases which degrades the system performance. The drawback of the global feature is overcome by features from images and has been efficient. Therefore, we use the Gabor shown to be very filter to extract the region based approach. In the region based approach the image is decomposed into regions by segmentation. global texture features from the image. In order to speed up retrieval the HSV color features are retrieved for both the entire image and the segmented regions. The experiments were carried out with COIL-100 and Wang’s image dataset. Region based approach does better since the region perception is nearer to human visual system. The well known region based retrieval systems are the Blobworld system [4] and the Natra system [5]. These two methods are based on The experimental results show that the current work is the comparison of the individual regions in an image. For significantly better than the existing systems.

Keywords

Content based image retrieval, Region based features, Global based features, Texture, Color, Gabor filter.

Cite this Article

Kavitha H and Sudhamani M V, “Content Based Image Retrieval Based on Global and Region Content of an Image,” International Journal of Advanced Computing and Communication Systems, pp. 014-018, November, 2014.

Copyright

© 2014 Kavitha H and Sudhamani M V. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.