DISTRIBUTED MPEG-7 IMAGE INDEXING USING SMALL WORLD USER AGENTS (MP-L2)

Author(s) : Panagiotis Androutsos (University of Toronto, Canada) Azadeh Kushki (University of Toronto, Canada) Dimitrios Androutsos (Ryerson Polytechnic University, Canada) Kostantinos Plataniotis (University of Toronto, Canada) Anastasios Venetsanopoulos (University of Toronto, Canada)

Abstract : A distributed indexing system for the indexing and retrieval of MPEG-7 described images is proposed. The system employs a sociological model of human acquaintance networks (small world theory) and concepts derived from the nature of the World Wide Web. Retrieval is performed using agents and a node hopping algorithm exploiting node referrals established from similarity values maintained locally at each node. A general framework for this Small World Image Mine (SWIM) is presented along with a realization using MPEG-7 Color Structure descriptor data for 2400 images. Results related to search agent path length and network node indegree are presented.

Menu