Generation of Metadata Using Content-Based Image Retrieval System

Abstract

For efficient data management, we propose a system which generates metadata for image contents. This system is using Content-Based Image Retrieval System (CBIR) based on Mpeg-7 descriptors. First, low-level features are extracted from the query image without metadata and the images with similar low-level features are retrieved from the CBIR system. Metadata of the result images which are similar to the query image are extracted from the metadata database. From the resulting metadata, common keywords are extracted and proposed as the keywords for the query image.