Abstract. In large content-based image database applications, e cient information retrieval depends heavily on good indexing structures of the extracted features. While indexing techniques for text retrieval are well understood, e cient and robust indexing methodology for image retrieval is still in its infancy. In this paper, we present a non-hierarchical clustering scheme for index generation using the Rival Penalized C o m p etitive Learning (RPCL) algorithm. RPCL is a stochastic heuristic clustering method which p r o vides good cluster center approximation and is computationally e cient. Using synthetic data as well as real data, we demonstrate the recall and precision performance measurement o f nearest-neighbor feature retrieval based on the indexing structure generated by R P C L .
Abstract. The fashion, textile, and clothing industry is a main constituent in Hong Kong. In this industry, handling a large amount o f images is an important task in various phases, for example, the designing, sourcing, and merchandising phase. We d e v elop an image database system called, Montage for managing and retrieving these visual information e ciently and e ectively. M o n tage is an image database supporting content-based retrieval by color histogram, sketch, texture, a n d shape. One important feature of Montage is the Open Architecture design which makes the system extensible, customizible, and exible. There are two aspects of this open architecture design: (1) Open DataBase Connectivity (ODBC) and (2) plug-in framework which w e will discuss in more details. Moreover, we describe an experimental Java system enabling internet access to Montage. In the paper, we also present a n e x p e r i m e n t t o e v aluate the performance of several query methods.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.