A semantic classification and composite indexing approach to robust image retrieval

Abstract

This paper investigates the use of image content analysis and image clustering techniques to organize an image database and to determine low-level features and semantic meanings for indexing and retrieval. A robust image retrieval system consisting of semantic classification, composite indexing and interactive query is proposed under this framework. In this system, a large image collection with great varieties is categorized into different classes according to distinct characteristics. The semantics of feature descriptors and the relationship between feature descriptors and image contents are then explored. Finally, a composite indexing and interactive retrieval procedure using low-level features and high-level understanding is developed to achieve a robust image query performance.