| Popis: |
The paper presents a method for content-based image retrieval based on an evolutionary algorithm. Stochastic approaches have been applied with success in several optimization problems thanks to their capability to explore the solution space, in particular in complex, multidimensional spaces, avoiding local maxima of the target function. Here, we show how a Particle Swarm Optimization algorithm appropriately designed to exploit the user feedback in CBIR may outperform traditional Relevance Feedback approaches, showing a much higher precision/recall thanks to the capability of navigating the feature space and to move the swarm towards the most appropriate image cluster. |
