Web-based beowulf-class parallel computing on image database indexing and retrieval system

摘要

Content-Based Image Retrieval (CBIR) techniques will be served as the next generation of search engine. However, even with a suitable retrieval method, real-time image retrieval from a large image database still requires extremely high computational power. In this paper, a web-based image database indexing and retrieval system is described. It uses fast CBIR with Beowulf-Class parallel computing engine (Super Abacus) to efficiently and effectively shorten the retrieval time. The contentbased image retrieval with several parallel algorithms for images query from different color spaces and the compressed-domain of images are developed to achieve higher efficiency. Besides, the text-based query is also supported for images query using the conventional annotation approach.