Similarity matrix compression for efficient signature quadratic form distance computation

Determining similarities among multimedia objects is a fundamental task in many content-based retrieval, analysis, mining, and exploration applications. Among state-of-the-art similarity measures, the Signature Quadratic Form Distance has shown good applicability and high quality in comparing flexible feature representations. In order to improve the efficiency of the Signature Quadratic Form Distance, we propose the similarity matrix compression approach which aims at compressing the distance's inherent similarity matrix. We theoretically show how to reduce the complexity of distance computations and benchmark computation time improvements. As a result, we improve the efficiency of a single distance computation by a factor up to 9. Categories and Subject Descriptors H.2.4 [Systems]: Multimedia databases, Query processing; H.3.3 [Information Search and Retrieval]: Retrieval models, Search process General Terms Theory, Experimentation, Performance Keywords Signature Quadratic Form ...

• Type: Journal
• Year: 2010
• Where: SISAP
• Authors: Christian Beecks, Merih Seran Uysal, Thomas Seidl
• Keywords: Data Mining, Quadratic Form Distance, Signature Quadratic Form, Similarity Matrix Compression, SISAP 2010