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. 1 Introduction The ability of computers to rapidly and successfully retrieve information from image databases based on the objects contained in the images has a direct impact on the progress of the revolution in communication precipitated with the increasing availability of digital video [4]. The complexity in the very nature of twodimensional image data gives rise to a host of problems that alphanumeric information systems were never designed to handle [1]. A central task of these m..