Efficient image retrieval using a network with complex neurons

We describe a self-organizing framework for the generation of a network useful in content-based retrieval of image databases. The system uses the theories of optimal projection for optimal feature selection and a hierarchical network structure of the image database for rapid retrieval rates. We demonstrate the query technique on a large database of widely varying real-world objects in natural settings, and show the applicability of the approach even for large variability within a particular object class