Color –Based Image Retrieval in Image Database System
Gunja Varshney1, Uma Soni2
1Gunja Varshney, Computer Science & Engineering, Sobhasaria Engineering College, Sikar, Rajsthan, India.
2Uma Soni, Computer Science & Engineering, Sobhasaria Engineering College, Sikar, Rajsthan, India.
Manuscript received on October 03, 2011. | Revised Manuscript received on October 14, 2011. | Manuscript published on November 05, 2011. | PP: 31-35 | Volume-1 Issue-5, November 2011. | Retrieval Number: E0140081511/2011©BEIESP
Open Access | Ethics and Policies | Cite
© The Authors. Published By: Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Image Databases (IDBs) are a special kind of Spatial Databases where a large number of images are stored and queried. IDBs find a plethora of applications in modern life, e.g. in Medical, Multimedia, Educational Applications, etc. Data in an IDB may be stored in raster or vector format. Each of these data formats has certain properties and, in several cases, the choice between them is a challenge. Raster data lead to fast computing of several operations and they are well suited to remote sensing. On the other hand, they have a fixed resolution, leading to limited detail. In this article, we focus on raster data. We present the design and architecture of an Image Database System where several query types are supported. These include: queries about the additional properties (descriptive information) that have been recorded for each image (e.g. which images have been used as covers of children’s books), queries about the color characteristics (color features) of the images (e.g. find the images that depict vivid blue), queries by example, or sketch (e.g. a sample image is chosen, or drawn by the user and images color-similar to this sample are sought). Color retrieval is achieved by utilizing color histograms. The development of our system is based on non-specialized tools: a relational database, Visual Basic and the computer’s file system. The user interface of the system aims at increased ease of use. It permits the management of the collection of images and the effective querying of the images by all the above query types and their combinations.
Keywords: Image Databases, Color Information, Query Processing, Color-Based Retrieval, Spatial Databases, Image Retrieval.