Detecting Near-Duplicate Face Images

2024-08-14

IEEE Transactions on Biometrics Behavior and Identity Science

AI Summary

This work addresses the challenging problem of near-duplicate detection and provenance tracing for facial images, introducing a novel task: identifying the original image and inferring the temporal generation order among near-duplicates. Methodologically, we propose the first Image Pedigree Tree (IPT) and Image Pedigree Forest (IPF) modeling framework—pioneering the use of graph theory in facial near-duplicate provenance analysis—and integrate graph neural networks, invariant feature extraction, ensemble-based IPF construction, and cross-modal robust evaluation. Our approach demonstrates strong robustness under unknown generative models, complex geometric and photometric transformations, and diverse biometric perturbations. Evaluated on benchmark datasets, our IPF reconstruction accuracy improves by 42% over state-of-the-art methods. The framework significantly enhances both interpretability and practical applicability of facial image provenance analysis.

Technology Category

• Computer Vision: Image and Video Retrieval
• Data Mining & Knowledge Management: Representing, Reasoning, and Using Provenance, Trust
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Security and Privacy: Data transparency and provenance
• Web Mining and Content Analysis: Web data provenance, reliability, and authenticity

Abstract

Near-duplicate images are often generated when applying repeated photometric and geometric transformations that produce imperceptible variants of the original image. Consequently, a deluge of near-duplicates can be circulated online posing copyright infringement concerns. The concerns are more severe when biometric data is altered through such nuanced transformations. In this work, we address the challenge of near-duplicate detection in face images by, firstly, identifying the original image from a set of near-duplicates and, secondly, deducing the relationship between the original image and the near-duplicates. We construct a tree-like structure, called an Image Phylogeny Tree (IPT) using a graph-theoretic approach to estimate the relationship, i.e., determine the sequence in which they have been generated. We further extend our method to create an ensemble of IPTs known as Image Phylogeny Forests (IPFs). We rigorously evaluate our method to demonstrate robustness across other modalities, unseen transformations by latest generative models and IPT configurations, thereby significantly advancing the state-of-the-art performance by 42% on IPF reconstruction accuracy.

Problem

• Detect near-duplicate face images to address copyright infringement concerns
• Identify original image and deduce relationships among near-duplicates
• Construct Image Phylogeny Trees to determine generation sequence

Innovation

• Graph-theoretic Image Phylogeny Tree (IPT) construction
• Ensemble method creating Image Phylogeny Forests (IPFs)
• Robust detection across unseen generative transformations