Since current machine-learning approaches give promising results in image searches to find a matching place in a photograph, the current study examines approaches to make this end-to-end system better support government and law enforcement requirements.
This study has relevance to sex trafficking investigations that sometimes have access to photographs of victims in hotel rooms. These images directly link such victims to places which can assist in verifying where victims have been trafficked or where traffickers might operate in the future. The procedure described in this article improves performance, visualization approaches that explain what parts of the image led to a match, and infrastructure that supports exporting the results of a query. (publisher abstract modified)