PhD Defense: Image Geo-Localization and Its Application to Media Forensics
Bor-Chun Chen
Abstract
With the prevalence of social media platforms, media shared on the Internet can reach millions of people in a short time. Sheer amounts of media available on the Internet enable many different computer vision applications. However, at the same time, people can easily share a tampered media for malicious goals such as creating panic or distorting public opinions with little effort.
We first present an image geo-localization framework for extracting fine-grained location information (i.e. business venues) from images. Our framework utilizes the information available from social media websites such as Instagram and Yelp to extract a set of location-related concepts. Secondly, to make a robust system, we address the metadata tampering detection problem, detecting the discrepancy between the images and its associated metadata such as GPS and timestamp. Third, we present a generative model to generate realistic image compositing using adversarial learning, which can be used to further improve the image tampering detection model. Finally, we propose an object-based provenance approach to address the content manipulation problem in media forensics.
Examining Committee:
We first present an image geo-localization framework for extracting fine-grained location information (i.e. business venues) from images. Our framework utilizes the information available from social media websites such as Instagram and Yelp to extract a set of location-related concepts. Secondly, to make a robust system, we address the metadata tampering detection problem, detecting the discrepancy between the images and its associated metadata such as GPS and timestamp. Third, we present a generative model to generate realistic image compositing using adversarial learning, which can be used to further improve the image tampering detection model. Finally, we propose an object-based provenance approach to address the content manipulation problem in media forensics.
Examining Committee:
Chair: Dr. Larry Davis
Dean's rep: Dr. Rama Chellappa
Members: Dr. David Jacobs
Dr. Yaser Yacoob
Dr. Tom Goldstein
Dean's rep: Dr. Rama Chellappa
Members: Dr. David Jacobs
Dr. Yaser Yacoob
Dr. Tom Goldstein
Bio
Bor-Chun (Sirius) Chen is a Ph.D. candidate in computer science at University of Maryland - College Park, advised by Professor Larry S. Davis. He obtained her bachelor degree in 2010 and master degree in 2014 from National Taiwan University. His current research interests are computer vision and its applications to media forensics.
This talk is organized by Tom Hurst