Feature set processing using multi-objective optimisation algorithm to improve content-based image retrieval system

We propose a framework of genetic algorithms to search for Pareto optimal solutions (i.e., non-dominated solutions) of multi-objective optimisation problems. Our approach differs from single-objective genetic algorithms in its selection procedure and elite presence strategy. The selection procedure in our genetic algorithms selects individuals for a crossover operation based on a sum of multiple objective functions. The characteristic feature of the selection procedure is that the weights attached to the multiple objective functions are not constant but randomly specified for each selection. This might most likely decry the classification accuracy and increase noise once it extracts type content type pictures. To avoid these drawbacks, a brand new technique is planned to induce retrieval performance. The implementation results show the effectiveness of projected optimisation technique in retrieving all pictures. Furthermore, the performance of the proposed technique is evaluated by comparing with the other optimised CBIR methods.