Abstract
Generating fingerprint images for biometric purposes is both necessary and challenging. In this study, we presented a fingerprint generation approach based on generative adversarial network. To ensure GAN training stability, we have introduced conditional loss doping that allows a continuous flow of gradients. Our study utilizes a careful combination of a residual network and spectral normalization to generate fingerprints. The proposed average residual connection shows more immunity against vanishing gradients than a simple residual connection. Spectral normalization allows our network to enjoy reduced variance in weight generation, which further stabilizes the training. Proposed scheme uses spectral bounding only in the input and the fully connected layers. Our network synthesized fingerprints up to 256 by 256 in size. We used the multi-scale structural similarity (MS-SSIM) metric for measuring the diversity of the generated samples. Our model has achieved 0.23 MS-SSIM scores for the generated fingerprints. The MS-SSIM score indicates that the proposed scheme is more likely to produce more diverse images and less likely to face mode collapse.
Highlights
A master fingerprint is capable of bypassing a small-scale biometric security system such as those used on smartphones
Their study has shown that a master fingerprint can be obtained by manipulation of original images or through synthesis using the hill-climbing scheme
Many schemes have been proposed, and all of them are based on the idea of the deep convolutional generative adversarial network (DCGAN) [15]
Summary
Despite introducing an enormous number of possibilities, the GAN framework has challenges, such as mode collapse, training stability, and a large computational budget To mitigate these challenges, many schemes have been proposed, and all of them are based on the idea of the deep convolutional generative adversarial network (DCGAN) [15]. Instead of dealing with a cost function, some research suggests looking at the differences in the number of networks [24]–[27] They proposed that multiple generators or discriminators can improve GAN stability. These studies [25], [26] employ more than two discriminators to produce gradients with low variance, improves the generator We present our result analysis, which is followed by the conclusion
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
