Finger-GAN: Generating Realistic Fingerprint Images Using Connectivity Imposed GAN
This work addresses the challenge of generating realistic biometric images for fingerprint analysis, but it is incremental as it builds on existing GAN methods with a specific regularization.
The authors tackled the problem of generating realistic fingerprint images by proposing a GAN-based framework with a connectivity regularization term, achieving good diversity and quantitative performance as measured by FID scores.
Generating realistic biometric images has been an interesting and, at the same time, challenging problem. Classical statistical models fail to generate realistic-looking fingerprint images, as they are not powerful enough to capture the complicated texture representation in fingerprint images. In this work, we present a machine learning framework based on generative adversarial networks (GAN), which is able to generate fingerprint images sampled from a prior distribution (learned from a set of training images). We also add a suitable regularization term to the loss function, to impose the connectivity of generated fingerprint images. This is highly desirable for fingerprints, as the lines in each finger are usually connected. We apply this framework to two popular fingerprint databases, and generate images which look very realistic, and similar to the samples in those databases. Through experimental results, we show that the generated fingerprint images have a good diversity, and are able to capture different parts of the prior distribution. We also evaluate the Frechet Inception distance (FID) of our proposed model, and show that our model is able to achieve good quantitative performance in terms of this score.