2015 16th IEEE/ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing (SNPD)
Download PDF

Abstract

Content based image retrieval techniques have been studied extensively in the past years due to the exponential growth of digital image information available in recent years with the widespread use of internet and declining cost of storage devices. Many techniques such as relevance feedback, multi query systems, etc. have been employed in CBIR systems to bridge the semantic gap between the low level features and high level semantics of the image. This paper proposes a multi query system using query replacement algorithm that utilizes the statistical features of the query image set to determine the similarity of the candidate images in the database for retrieval and ranking. Experimental results show the effectiveness of the algorithm computed in terms of average precision. It is seen that using the proposed algorithm, simply by using two images rather than one image as query improves the retrieval precision by 8% and continues to provide improved precision with every additional image added to the query image set.
Like what you’re reading?
Already a member?
Get this article FREE with a new membership!

Related Articles