Iris-GAN: Learning to Generate Realistic Iris Images Using Convolutional GAN
This work addresses the challenge of realistic iris image generation for biometric applications, but it is incremental as it applies an existing GAN method to a specific domain.
The authors tackled the problem of generating realistic iris images by proposing a GAN-based framework, which successfully produced diverse and realistic iris images that closely matched the distribution of two popular iris databases.
Generating iris images which look realistic is both an interesting and challenging problem. Most of the classical statistical models are not powerful enough to capture the complicated texture representation in iris images, and therefore fail to generate iris images which look realistic. In this work, we present a machine learning framework based on generative adversarial network (GAN), which is able to generate iris images sampled from a prior distribution (learned from a set of training images). We apply this framework to two popular iris databases, and generate images which look very realistic, and similar to the image distribution in those databases. Through experimental results, we show that the generated iris images have a good diversity, and are able to capture different part of the prior distribution.