DiffFinger: Advancing Synthetic Fingerprint Generation through Denoising Diffusion Probabilistic Models

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Grabovski, Freddie, Yasur, Lior, Hacmon, Yaniv, Nisimov, Lior, Nimrod, Stav
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866913344633438208
author Grabovski, Freddie
Yasur, Lior
Hacmon, Yaniv
Nisimov, Lior
Nimrod, Stav
author_facet Grabovski, Freddie
Yasur, Lior
Hacmon, Yaniv
Nisimov, Lior
Nimrod, Stav
contents This study explores the generation of synthesized fingerprint images using Denoising Diffusion Probabilistic Models (DDPMs). The significant obstacles in collecting real biometric data, such as privacy concerns and the demand for diverse datasets, underscore the imperative for synthetic biometric alternatives that are both realistic and varied. Despite the strides made with Generative Adversarial Networks (GANs) in producing realistic fingerprint images, their limitations prompt us to propose DDPMs as a promising alternative. DDPMs are capable of generating images with increasing clarity and realism while maintaining diversity. Our results reveal that DiffFinger not only competes with authentic training set data in quality but also provides a richer set of biometric data, reflecting true-to-life variability. These findings mark a promising stride in biometric synthesis, showcasing the potential of DDPMs to advance the landscape of fingerprint identification and authentication systems.
format Preprint
id arxiv_https___arxiv_org_abs_2405_04538
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle DiffFinger: Advancing Synthetic Fingerprint Generation through Denoising Diffusion Probabilistic Models
Grabovski, Freddie
Yasur, Lior
Hacmon, Yaniv
Nisimov, Lior
Nimrod, Stav
Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
This study explores the generation of synthesized fingerprint images using Denoising Diffusion Probabilistic Models (DDPMs). The significant obstacles in collecting real biometric data, such as privacy concerns and the demand for diverse datasets, underscore the imperative for synthetic biometric alternatives that are both realistic and varied. Despite the strides made with Generative Adversarial Networks (GANs) in producing realistic fingerprint images, their limitations prompt us to propose DDPMs as a promising alternative. DDPMs are capable of generating images with increasing clarity and realism while maintaining diversity. Our results reveal that DiffFinger not only competes with authentic training set data in quality but also provides a richer set of biometric data, reflecting true-to-life variability. These findings mark a promising stride in biometric synthesis, showcasing the potential of DDPMs to advance the landscape of fingerprint identification and authentication systems.
title DiffFinger: Advancing Synthetic Fingerprint Generation through Denoising Diffusion Probabilistic Models
topic Computer Vision and Pattern Recognition
Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2405.04538