Paper Info
Title
Cooperative Orientation Generative Adversarial Network for Latent Fingerprint Enhancement
Abstract
Robust fingerprint enhancement algorithm is crucial to latent fingerprint recognition. In this paper, a latent fingerprint enhancement model named cooperative orientation generative adversarial network (COOGAN) is proposed. We formulate fingerprint enhancement as an image-to-image translation problem with deep generative adversarial network (GAN) and introduce orientation constraints to it. The deep architecture provides a powerful representation for the translation between latent fingerprint space and enhanced fingerprint space. While the orientation supervision can guide the deep feature learning to focus more on the ridge flows. To further boost the performance, a quality estimation module is proposed to remove the unrecoverable regions while enhancement. Experimental results show that COOGAN achieves state-of-the-art performance on NIST SD27 latent fingerprint database.
Year
DOI
Venue
2019
10.1109/ICB45273.2019.8987356
2019 International Conference on Biometrics (ICB)
Keywords
Field
DocType
robust fingerprint enhancement algorithm,latent fingerprint recognition,latent fingerprint enhancement model,image-to-image translation problem,deep generative adversarial network,orientation constraints,latent fingerprint space,enhanced fingerprint space,NIST SD27 latent fingerprint database,cooperative orientation generative adversarial network,COOGAN,quality estimation module
Computer vision,Generative adversarial network,Pattern recognition,Fingerprint recognition,Computer science,Fingerprint,NIST,Artificial intelligence,Fingerprint database,Feature learning
Conference
ISSN
ISBN
Citations 
2376-4201
978-1-7281-3641-7
0
PageRank 
References 
Authors
0.34
0
4
Name
Order
Citations
PageRank
Yuhang Liu110.68
Yao Tang2144.72
Ruilin Li3167.90
Jufu Feng458642.31