Detecting Changes in Crowdsourced Social Media Images

Abstract

We propose a novel service framework to detect changes in crowdsourced images. We use a service-oriented approach to model and represent crowdsourced images as image services. Non-functional attributes of an image service are leveraged to detect changes in an image. The changes are reported in form of a version tree. The version tree is constructed in a way that it reflects the extent of changes introduced in different versions. Afterwards, we find semantic differences in between different versions to determine the extent of changes introduced in a specific version. Preliminary experimental results demonstrate the effectiveness of the proposed approach.