Back to articles
Articles
Volume: 3 | Article ID: art00054
Image
Content And Metadata Based Image Retrieval System For Art Images
Kingsly Stephen
Jency Moses
  DOI :  10.2352/CGIV.2006.3.1.art00054  Published Online :  January 2006
Abstract

In this paper a new approach for image retrieval is analyzed using image content and metadata. Conventional content-based image retrieval systems are already in use but they are useful for some specific domains. This system provides an integrated approach with content and metadata. Pyramid wavelet transform is used for image decomposition and Daubechies family of filters is used for noise removal and filtering operations. The Euclidean distance classifier is used for finding the similarity measures between the query image and the images in the database. The same will also be used for sub-image matching. Calculating the low frequency band for the image has many advantages to reduce memory space, because all other higher frequency bands are eliminated. Clustered metadata is stored in various categories, which is used to form a query-by-text and to retrieve images. This clustered metadata is used to reduce searching time. All these methods are integrated to get higher performance. This image retrieval system is analyzed and simulated to show the performance analysis of the new approach

Journal Title : Conference on Colour in Graphics, Imaging, and Vision
Publisher Name : Society of Imaging Science and Technology
Publisher Location : 7003 Kilworth Lane, Springfield, VA 22151, USA
Subject Areas :
Views 10
Downloads 0
 DOI 10.2352/CGIV.2006.3.1.art00054
 articleview.views 10
 articleview.downloads 0
  Cite this article 

Kingsly Stephen, Jency Moses, "Content And Metadata Based Image Retrieval System For Art Images"  in Proc. IS&T CGIV 2006 3rd European Conf. on Colour in Graphics, Imaging, and Vision,  2006,  pp 271 - 272,  https://doi.org/10.2352/CGIV.2006.3.1.art00054

 Copy citation
  Copyright statement 
Copyright © Society for Imaging Science and Technology 2006
72010351
Conference on Colour in Graphics, Imaging, and Vision
conf colour graph imag vis
2158-6330
Society of Imaging Science and Technology
7003 Kilworth Lane, Springfield, VA 22151, USA
2158-6330(20060101)2006:1L.271;1-
cgiv_v2006n1/splitsection54.xml
/ist/cgiv/2006/00002006/00000001/art00054
Articles
Content And Metadata Based Image Retrieval System For Art Images
StephenKingsly
MosesJency
01012006
2006
1
271
272
2006
In this paper a new approach for image retrieval is analyzed using image content and metadata. Conventional content-based image retrieval systems are already in use but they are useful for some specific domains. This system provides an integrated approach with content and metadata. Pyramid wavelet transform is used for image decomposition and Daubechies family of filters is used for noise removal and filtering operations. The Euclidean distance classifier is used for finding the similarity measures between the query image and the images in the database. The same will also be used for sub-image matching. Calculating the low frequency band for the image has many advantages to reduce memory space, because all other higher frequency bands are eliminated. Clustered metadata is stored in various categories, which is used to form a query-by-text and to retrieve images. This clustered metadata is used to reduce searching time. All these methods are integrated to get higher performance. This image retrieval system is analyzed and simulated to show the performance analysis of the new approach