PDQ & TMK + PDQF -- A Test Drive of Facebook's Perceptual Hashing Algorithms
Janis Dalins, Campbell Wilson, Douglas Boudry

TL;DR
This paper evaluates Facebook's open-sourced PDQ and TMK + PDQF algorithms for detecting modified images and videos, highlighting their effectiveness in real-world law enforcement scenarios and providing a reference implementation.
Contribution
It offers a performance review of Facebook's perceptual hashing algorithms on real-world data and demonstrates their integration potential in law enforcement workflows.
Findings
High accuracy in detecting common image transformations
Effective video similarity measurement in real-world cases
Practical reference implementation provided
Abstract
Efficient and reliable automated detection of modified image and multimedia files has long been a challenge for law enforcement, compounded by the harm caused by repeated exposure to psychologically harmful materials. In August 2019 Facebook open-sourced their PDQ and TMK + PDQF algorithms for image and video similarity measurement, respectively. In this report, we review the algorithms' performance on detecting commonly encountered transformations on real-world case data, sourced from contemporary investigations. We also provide a reference implementation to demonstrate the potential application and integration of such algorithms within existing law enforcement systems.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsDigital Media Forensic Detection · Anomaly Detection Techniques and Applications · Video Surveillance and Tracking Methods
