Distributed Web Service Architecture for Scalable Content Analysis: Semi-Automatic Annotation of User Generated Content
This paper describes distributed web service architecture to allow web level scalability for multimedia content analysis. The authors introduce service component architecture that allows for orchestration and composition of services as content analysis units to enrich multimedia metadata using common data model built upon MPEG-7 content description standard. They report experiments with automatic load balancing and introduce an end user application that facilitates annotation of people in images and video. Image and video sharing services have become one of the most popular service types in the Internet due to increasing creative use and communication through web and multimedia.