Demo of the SICOS tool for Social Image Cluster-based Organization and Search

摘要

This paper briefly describes and evaluates SICOS, a tool for Social Image Cluster-based Organization and Search, allowing to group together images sharing similar semantic and visual features, to simplify their organization and querying following user preferences. The system consists of modular components for: i) feature extraction and representation (low-level and high-level), ii) partitional image clustering (initial clustering phase executed when the user first connects to the system), iii) incremental clustering (updating clusters produces in the previous phase by processing newly published images), iv) fast image querying (using features of cluster representatives), and v) personalized images and search results visualization (using various user-chosen cluster display techniques). Experiments highlight the efficiency of the tool.