Iris-GAN: Learning to Generate Realistic Iris Images Using Convolutional GAN

by   Shervin Minaee, et al.

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.


page 1

page 3

page 4


Palm-GAN: Generating Realistic Palmprint Images Using Total-Variation Regularized GAN

Generating realistic palmprint (more generally biometric) images has alw...

Finger-GAN: Generating Realistic Fingerprint Images Using Connectivity Imposed GAN

Generating realistic biometric images has been an interesting and, at th...

iWarpGAN: Disentangling Identity and Style to Generate Synthetic Iris Images

Generative Adversarial Networks (GANs) have shown success in approximati...

Deep GAN-Based Cross-Spectral Cross-Resolution Iris Recognition

In recent years, cross-spectral iris recognition has emerged as a promis...

Robust Iris Segmentation Based on Fully Convolutional Networks and Generative Adversarial Networks

The iris can be considered as one of the most important biometric traits...

Alcohol Consumption Detection from Periocular NIR Images Using Capsule Network

This research proposes a method to detect alcohol consumption from Near-...

Please sign up or login with your details

Forgot password? Click here to reset