EDBT/ICDT 2009 Joint Conference

Electronic Conference Proceedings

• Welcome
• Full Program
• ICDT Sessions
• ICDT Papers
• EDBT Sessions
  • Invited Talks
  • Research Track
    • System Architectures
    • Spatio-Temporal
    • Database Summarization
    • Query Processing
    • XML, XPath, XQuery
    • Graph Techniques
    • Privacy & Security
    • Data Models
    • Stream Processing
    • XML, XPath, XQuery
    • Database Summarization
    • Query Processing
    • Top-K Techniques
    • Graph Techniques
    • Data Mining
    • Heterogeneous & Distributed
    • System Architectures
    • Privacy & Security
    • Uncertainty
    • Workflow Techniques
    • Multi-Dimensional
    • Caching Techniques
    • Information Retrieval
    • Query Processing
    • Top-K Techniques
    • Potpourri
    • Provenance
    • Spatio-Temporal
    • Skylines
    • Transaction Processing
  • Industrial Track
  • Demo Track
  • Tutorials
• EDBT Papers
• Author Index
• Workshops

Caching Content-based Queries for Robust and Efficient Image Retrieval

Authors

• Fabrizio Falchi (ISTI-CNR, Italy)
• Claudio Lucchese (ISTI-CNR, Italy)
• Salvatore Orlando (Università di Venezia, Italy)
• Raffaele Perego (ISTI-CNR, Italy)
• Fausto Rabitti (ISTI-CNR, Italy)

Abstract

In order to become an effective complement to traditional Web-scale text-based image retrieval solutions, content-based image retrieval must address scalability and effciency issues. In this paper we investigate the possibility of caching the answers of content-based image retrieval queries in metric space, with the aim of reducing the average cost of query processing, and boosting the overall system throughput. Our proposal exploits the similarity between the query object and the cache content, and allows the cache to return approximate answers with acceptable quality guarantee even if the query processed has never been encountered in the past. Moreover, since popular images that are likely to be used as query have several near-duplicate versions, we show that our caching algorithm is robust, and does not suffer of cache pollution problems due to near-duplicate query objects. We report on very promising results conducted on a collection of one million high-quality digital photos. We show that it is worth pursuing caching strategies also in similarity search systems, since the proposed caching techniques can have a significant impact on performance, like caching on text queries has been proven effective for traditional Web search engines.

Session

EDBT Research Session 22: Caching Techniques (Thursday, March 26, 11:00—12:30)