A Region-Similarity-Based Image Retrieval System
Jean-François Omhover, Marcin Detyniecki, Bernadette Bouchon‐Meunier, Lip Pole Ia · 2004
In this document, we present an image retrieval system that is based on a segmented representation of the visual content. This representation leads to a comparison of the image content that is more ”semantic” than a classical global comparison. The system compares regions using fuzzy similarity measures that have been show to be psychologically intuitive and easy to aggregate. We then exploit the aggregation between regional similarity measures to let the user build four different types of original visual requests. Our system can handle these requests easily, thanks to its open architecture that let the expert user modify its parameters and compose new aggregation operators on them.