Inverted Index Compression for Scalable Image Matching
2010pp. 525–525
Citations Over TimeTop 10% of 2010 papers
David M. Chen, Sam S. Tsai, Vijay Chandrasekhar, Gabriel Takacs, Ramakrishna Vedantham, Radek Grzeszczuk, Bernd Girod
Abstract
In this paper, they address a key challenge for scaling image search up to larger databases: the amount of memory consumed by the inverted index. In a VT-based image retrieval system, the most memory-intensive structure is the inverted index. For example, in a database of one million images where each image contains hundreds of features, the inverted index consumes 2.5 GB of RAM. Such large memory usage limits the ability to run other concurrent processes on the same server, such as recognition systems for other databases. A memory-congested server can exhibit swapping between main and virtual memory, which significantly slows down all processes.
Related Papers
- → Hybrid compression of inverted lists for reordered document collections(2018)14 cited
- Inverted indexes: Types and techniques(2011)
- → Techniques for Inverted Index Compression(2020)12 cited
- → A new index model based on inverted index(2012)4 cited
- → The Research of Non-back Multi-words Matching Algorithm Based on Aggregate Address Inverted Index(2009)