Impact of PSO on Retrieval Performance in QBIC System

Abstract

The aim of this chapter is to propose an efficient retrieval method that can retrieve appropriate information from the gigantic collections of images utilized in heterogeneous applications which has a pronounced impact on retrieval performance when compared to standard and customary Gabor filter methods. In recent times, there is a magnificent technical progression in the research area related to image retrieval, in specific the Query By Image Content (QBIC) system. Retrieval of information has become a very challenging area of research in various applications like databases related to multimedia, Google retrieval and digital libraries. The study developed a hybrid QBIC retrieval system that depicts the impact of PSO on retrieval performance in QBIC system by retrieving color features, texture features and shape features of the images in three consecutive stages. In the suggested technique, color features are initially extracted using a color histogram. In the following step, Log Gabor filters are tuned using Particle Swarm Optimization (PSO), retrieving the texture characteristics. The extraction of shape features is completed by using a polygonal fitting technique. When compared to the current standard systems, the suggested method shows a superior retrieval rate in terms of mean recall and mean precision. The novelty is that it can exploit global minima features that result in high accuracy without affecting the computation.