Optimized Image Retrieval System in Oracle DBMS

Optimized Image Retrieval System in Oracle DBMS

Kaouther Zekri (ENIT, Tunis, Tunisia), Amel Grissa Touzi (FST, ENIT, Tunis, Tunisia), and Noureddine Ellouze (ENIT, Tunis, Tunisia)
DOI: 10.4018/IJSSMET.2017010101
OnDemand PDF Download:
No Current Special Offers


In this work, the authors are moving towards the creation of an effective image retrieval system in Oracle DBMS. Several DBMSs have been extensively used to manage the textual information stored with images and CBIR tasks usually rely on specific applications. The separation between the DBMSs and CBIR prevents the optimization of integrated search process based on the connection between the textual and visual content description of image. Moreover, the relevance of image retrieval depends directly on the choice of similarity criteria (color, texture, shape) that can give inaccurate results in case of non-trivial selection of these parameters. The purpose of the authors' approach is to build a CBIR system using advanced and integrated retrieval techniques defined in Oracle DBMS. This approach provides an assistance tool that can guide the user to the appropriate choice of search criteria. The authors present an experimental part that measures the performance of their system, which can help the user to correctly model his query by giving the appropriate retrieval criteria for a database with 800 images.
Article Preview

1. Introduction

The continued improvement in the quantity of multimedia data, especially images, led to a large mass of image databases which results two major challenges: storage and image processing.

Since 1990, scientific research focused on the development of a new way to retrieve images which can be automatic and effective (Singhai, 2010) (Walter, 2006). Among these systems we can quote: QBIC (Query By Image Content) (Pecenovic, 1998) of IBM, BlobWorld system (Pecenovic, 1998) of California University, the website img(Anaktisi) (Zagoris, 2009), MedFMI-SiR system (Daniel, 2011) and the ImageFinder (Payel, 2011).

The major problem related to the development of content based image retrieval system consists of the establishment of technical which can describe the visual content of image and take in consideration the needs of users and their different points of view regarding image interpretation (Park, 2002). Thus, the choice of search criteria shall be achieved based on all relevant information available on all the image data, so the contribution of the less significant features will be neglected.

Despite their usefulness and popularity, the systems we have mentioned have certain limitations, such as imprecise results, low interactivity, lack of semantic in query processing and functionalities to effectively model the query by selecting the appropriate search criteria.

In CBIR system, it is important to take account the semantic description of the image based on the metadata and the textual description stored with each image. The semantic description is the complementary part of the image visual content (Ahmad, 2015) which leads to an integrated retrieval engine that can execute optimized query by combining textual and content based image retrieval. Moreover, the choice of similarity criteria is empirical, and it is necessary to try to correctly model and control these parameters. If they are set improperly, the results of search will be irrelevant and unsatisfactory to the user needs. The selection of the appropriate criteria and the choice of their accurate weight depend of the type of image database, and the user need. Actually, in CBIR systems, the user randomly selects the search criteria which can produce a loss of precision in the result and force the user to repeat the selection of new coefficient with different weight several times so that it can find relevant search results.

Complete Article List

Search this Journal:
Volume 14: 1 Issue (2023)
Volume 13: 6 Issues (2022): 2 Released, 4 Forthcoming
Volume 12: 6 Issues (2021)
Volume 11: 4 Issues (2020)
Volume 10: 4 Issues (2019)
Volume 9: 4 Issues (2018)
Volume 8: 4 Issues (2017)
Volume 7: 4 Issues (2016)
Volume 6: 4 Issues (2015)
Volume 5: 4 Issues (2014)
Volume 4: 4 Issues (2013)
Volume 3: 4 Issues (2012)
Volume 2: 4 Issues (2011)
Volume 1: 4 Issues (2010)
View Complete Journal Contents Listing