Fusing Contextual Metadata and Visual Similarity in Mobile Media Location-Based Classification
A Bamidele, Fred W. M. Stentiford · UCL Discovery (University College London) · 2005
This paper describes a new approach to the automatic identification of the location of mobile images. New methods for determining image similarity are combined with analysis of automatically acquired contextual metadata to produce location information. Results are reported on a database of 1209 real images collected on Nokia 7610 camera phones by different users in 12 different locations across multiple mobile carrier cell identities.