FDeblur-GAN: Fingerprint Deblurring using Generative Adversarial Network

06/21/2021
by   Amol S. Joshi, et al.
0

While working with fingerprint images acquired from crime scenes, mobile cameras, or low-quality sensors, it becomes difficult for automated identification systems to verify the identity due to image blur and distortion. We propose a fingerprint deblurring model FDeblur-GAN, based on the conditional Generative Adversarial Networks (cGANs) and multi-stage framework of the stack GAN. Additionally, we integrate two auxiliary sub-networks into the model for the deblurring task. The first sub-network is a ridge extractor model. It is added to generate ridge maps to ensure that fingerprint information and minutiae are preserved in the deblurring process and prevent the model from generating erroneous minutiae. The second sub-network is a verifier that helps the generator to preserve the ID information during the generation process. Using a database of blurred fingerprints and corresponding ridge maps, the deep network learns to deblur from the input blurry samples. We evaluate the proposed method in combination with two different fingerprint matching algorithms. We achieved an accuracy of 95.18 the task of matching deblurred and ground truth fingerprints.

READ FULL TEXT

page 1

page 4

page 6

research
07/31/2018

ID Preserving Generative Adversarial Network for Partial Latent Fingerprint Reconstruction

Performing recognition tasks using latent fingerprint samples is often c...
research
05/02/2018

Altered Fingerprints: Detection and Localization

Fingerprint alteration, also referred to as obfuscation presentation att...
research
12/10/2020

Super-resolution Guided Pore Detection for Fingerprint Recognition

Performance of fingerprint recognition algorithms substantially rely on ...
research
05/29/2023

NaturalFinger: Generating Natural Fingerprint with Generative Adversarial Networks

Deep neural network (DNN) models have become a critical asset of the mod...
research
04/13/2020

Dense Registration and Mosaicking of Fingerprints by Training an End-to-End Network

Dense registration of fingerprints is a challenging task due to elastic ...
research
01/03/2018

Fingerprint Distortion Rectification using Deep Convolutional Neural Networks

Elastic distortion of fingerprints has a negative effect on the performa...
research
09/16/2020

Characteristic and Necessary Minutiae in Fingerprints

Fingerprints feature a ridge pattern with moderately varying ridge frequ...

Please sign up or login with your details

Forgot password? Click here to reset