Gradient-Guided Exploration of Generative Model's Latent Space for Controlled Iris Image Augmentations

TL;DR

This paper presents a gradient-guided latent space traversal method for generative models to produce diverse, attribute-controlled iris image augmentations while preserving identity, aiding iris recognition and attack detection.

Contribution

It introduces a novel approach to manipulate iris image attributes via gradient-guided latent space traversal, applicable to both GAN-generated and real images.

Findings

Effective control over iris image attributes like sharpness and pupil size.

Preserves identity during attribute manipulation.

Applicable to both synthetic and real iris images.

Abstract

Developing reliable iris recognition and presentation attack detection methods requires diverse datasets that capture realistic variations in iris features and a wide spectrum of anomalies. Because of the rich texture of iris images, which spans a wide range of spatial frequencies, synthesizing same-identity iris images while controlling specific attributes remains challenging. In this work, we introduce a new iris image augmentation strategy by traversing a generative model's latent space toward latent codes that represent same-identity samples but with some desired iris image properties manipulated. The latent space traversal is guided by a gradient of specific geometrical, textural, or quality-related iris image features (e.g., sharpness, pupil size, iris size, or pupil-to-iris ratio) and preserves the identity represented by the image being manipulated. The proposed approach can be easily extended to manipulate any attribute for which a differentiable loss term can be formulated. Additionally, our approach can use either randomly generated images using either a pre-train GAN model or real-world iris images. We can utilize GAN inversion to project any given iris image into the latent space and obtain its corresponding latent code.