Palmprint De-Identification Using Diffusion Model for High-Quality and Diverse Synthesis
This addresses the risk of misuse of publicly available palmprint images for malicious activities, offering a novel solution in an underexplored area, though it is incremental as it builds on existing diffusion models.
The paper tackles the problem of palmprint de-identification by proposing a training-free framework using pre-trained diffusion models to generate diverse, high-quality images that conceal identity features, achieving a balance between de-identification and retaining non-identity information with significant diversity across samples.
Palmprint recognition techniques have advanced significantly in recent years, enabling reliable recognition even when palmprints are captured in uncontrolled or challenging environments. However, this strength also introduces new risks, as publicly available palmprint images can be misused by adversaries for malicious activities. Despite this growing concern, research on methods to obscure or anonymize palmprints remains largely unexplored. Thus, it is essential to develop a palmprint de-identification technique capable of removing identity-revealing features while retaining the image's utility and preserving non-sensitive information. In this paper, we propose a training-free framework that utilizes pre-trained diffusion models to generate diverse, high-quality palmprint images that conceal identity features for de-identification purposes. To ensure greater stability and controllability in the synthesis process, we incorporate a semantic-guided embedding fusion alongside a prior interpolation mechanism. We further propose the de-identification ratio, a novel metric for intuitive de-identification assessment. Extensive experiments across multiple palmprint datasets and recognition methods demonstrate that our method effectively conceals identity-related traits with significant diversity across de-identified samples. The de-identified samples preserve high visual fidelity and maintain excellent usability, achieving a balance between de-identification and retaining non-identity information.