Hybrid Swarm Intelligence Technique for CBIR Systems

Literature has proved the individual performance of ABC and PSO while solving various optimization problems. However, as PSO searches the solution by updating the particles and the ABC searches by bees’ wandering behavior, there are drawbacks persist in the individual performance. Hence in our previous work, we have proposed a hybrid swarm optimization technique to outperform the individual performance of ABC and PSO. The experimentation was done using standard benchmark test function models and the comparisons were made against the individual performance of PSO and ABC. This work is an extension of our previous in which we take an image processing problem called Content-Based Image Retrieval (CBIR) to evaluate the performance of the proposed hybrid algorithm. CBIR systems are the most popular image processing system in which relevant images are retrieved from a huge database when a query image is given. In such CBIR systems, multiple features are used to determine the relevance of retrieved images and query images. In this scenario, it is essential to minimize all the features distances that are determined between the query image and the database images. To perform the retrieval stage efficiently, an effective search algorithm is required. Hence, in this paper we exploit the proposed hybrid algorithm in the retrieval stage of a CBIR system to ensure the retrieval performance. The technique will be implemented in the working platform of MATLAB and the retrieval accuracy will be compared with the conventional methods.