A Latent Feature Space Transformation For Identity-Aware Controllable De-Identification
Md Shopon, Marina L. Gavrilova · 2024
Soft biometric de-identification is an emerging field in biometrics, offering a balance between privacy protection and recognition accuracy. In this work, we present a novel identity-preserving soft biometric obfuscation method that uses the latent feature space of a trained generator and employs deep neural networks. The proposed method aims at preserving the identity of individuals while de-identifying their soft biometric attributes. Specifically, a novel feature space transformation network is designed to preserve identity while modifying facial attributes while minimizing the disclosure of identity. The proposed feature transformation network is the first of its kind developed specifically for controllable adaptive de-identification. Furthermore, we implemented an identity preservation mechanism, utilizing the FaceNet architecture to compute embedding vectors for both the original and deidentified images. Through extensive validation on benchmark datasets such as VGGFace2 and CelebA, we have demonstrated the effectiveness and robustness of our method.