20.500.12556/RUL-156192 Generating bimodal privacy-preserving data for face recognition The performance of state-of-the-art face recognition systems depends crucially on the availability of large-scale training datasets. However, increasing privacy concerns nowadays accompany the collection and distribution of biometric data, which has already resulted in the retraction of valuable face recognition datasets. The use of synthetic data represents a potential solution, however, the generation of privacy-preserving facial images useful for training recognition models is still an open problem. Generative methods also remain bound to the visible spectrum, despite the benefits that multispectral data can provide. To address these issues, we present a novel identity-conditioned generative framework capable of producing large-scale recognition datasets of visible and near-infrared privacy-preserving face images. The framework relies on a novel identity-conditioned dual-branch style-based generative adversarial network to enable the synthesis of aligned high-quality samples of identities determined by features of a pretrained recognition model. In addition, the framework incorporates a novel filter to prevent samples of privacy-breaching identities from reaching the generated datasets and improve both identity separability and intra-identity diversity. Extensive experiments on six publicly available datasets reveal that our framework achieves competitive synthesis capabilities while preserving the privacy of real-world subjects. The synthesized datasets also facilitate training more powerful recognition models than datasets generated by competing methods or even small-scale real-world datasets. Employing both visible and near-infrared data for training also results in higher recognition accuracy on real-world visible spectrum benchmarks. Therefore, training with multispectral data could potentially improve existing recognition systems that utilize only the visible spectrum, without the need for additional sensors. image synthesis face-based biometrics privacy-preserving data multispectral recognition generative adversarial networks sinteza slik biometrija na podlagi obraza zasebni podatki večspektralno razpoznavanje generativne nasprotniške mreže true false true Angleški jezik Slovenski jezik Članek v reviji 2024-05-13 12:44:50 2024-05-13 12:44:51 2024-05-22 08:43:13 0000-00-00 00:00:00 2024 0 0 25 str. pt. E, art. 108495 Vol. 133 Jul. 2024 0000-00-00 Zaloznikova Objavljeno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 004.93:57.087.1 0952-1976 10.1016/j.engappai.2024.108495 194774275 RAZ_Tomasevic_Darian_2024.pdf RAZ_Tomasevic_Darian_2024.pdf 1 E97D16A87A993C8CB4D62862FB68848E 0354031e6cd2e632a45c27b6a0d31d6e4c58ae53632a40ebedff77ca31497de1 893f7ad8-1116-11ef-adc7-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=183508 https://www.sciencedirect.com/science/article/pii/S0952197624006535 1 d44459fe-1115-11ef-adc7-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=183507 Fakulteta za računalništvo in informatiko Fakulteta za elektrotehniko 0 0 0