Intermediate Annotationless Dynamical Object-Index-Based Query in Large Image Archives with Holographic Representation

Abstract

This paper presents a new parallel and distributed associative network-based technique for content-based image retrieval (CBIR) with dynamic indices. Unlike any prior artificial associative networks (AAM), this new associative search network has the unique ability to explicitly focus on any subset of pixels in the image. It can also provide a feedback meta-quantity on the quality of outgoing information. The network is founded on a bi-modal representation of information elements which in addition to basic information also includes meta-states. Its computational model has been derived from optical holography. These unique capabilities coupled with usual advantages of associative computing (adaptability, efficiency, ability to cope with imprecision, parallel and distributed mode of computation) now for the first time make it possible to realize a CBIR technique based on associative computing. This new CBIR strategy provides an inquirer greater flexibility to independently and dynamically construct object-indices without depending on the fixed, predefined ad hoc indices used by traditional CBIR approaches. The paper presents the mechanism, architecture, and performance of an image archival and retrieval system realized with this new network.