Image and multimedia processing using computational intelligence

Abstract

This project investigates two applications in image and multimedia processing, namely: (i) blind image deconvolution, and (ii) content-based image retrieval (CBIR). Computational intelligence, which offers instrumental mathematical modeling of artificial intelligence, is employed in this project due to their effectiveness. The main principles of the proposed algorithms can be described concisely as: identification of useful a priori information, integration of extracted knowledge into the schemes, and development of appropriate computational techniques to optimize the cost function. The requirements for systematic signal identification, intelligent information integration, and robust optimization point to computational intelligence techniques. Two categories of computational intelligence, namely neural networks and fuzzy systems are employed in our work.