Abstract

Hotel recognition is a sub-domain of scene recognition that involves determining what hotel is seen in a photograph taken in a hotel. The hotel recognition task is a challenging computer vision task due to the properties of hotel rooms, including low visual similarity between rooms in the same hotel and high visual similarity between rooms in different hotels, particularly those from the same chain. Building accurate approaches for hotel recognition is important to investigations of human trafficking. Images of human trafficking victims are often shared by traffickers among criminal networks and posted in online advertisements. These images are often taken in hotels. Using hotel recognition approaches to determine the hotel a victim was photographed in can assist in investigations and prosecutions of human traffickers.

In this dissertation, I present an application for the ongoing capture of hotel imagery by the public, a large-scale curated dataset of hotel room imagery, deep learning approaches to hotel recognition based on this imagery, a visualization approach that provides insight into what networks trained on image similarity are learning, and an approach to image search focused on specific objects in scenes. Taken together, these contributions have resulted in a first in the world system that offers a solution to answering the question, `What hotel was this photograph taken in?' at a global scale.

Committee Chair

Sanmay Robert . Das Pless

Committee Members

Tao Ju, Ayan Chakrabarti, Alvitta Ottley, Richard Souvenir,

Comments

Permanent URL: https://doi.org/10.7936/6xsj-ys38

Degree

Doctor of Philosophy (PhD)

Author's Department

Computer Science & Engineering

Author's School

McKelvey School of Engineering

Document Type

Dissertation

Date of Award

Winter 12-15-2018

Language

English (en)

Author's ORCID

http://orcid.org/0000-0002-4387-028X

Download

Share

COinS