Self-Supervised Learning Framework toward State-of-the-Art Iris Image Segmentation

Abstract

Iris segmentation plays a pivotal role in the iris recognition system. The deep learning technique developed in recent years has gradually been applied to iris recognition techniques. As we all know, applying deep learning techniques requires a large number of data sets with high-quality manual labels. The larger the amount of data, the better the algorithm performs. In this paper, we propose a self-supervised framework utilizing the pix2pix conditional adversarial network for generating unlimited diversified iris images. Then, the generated iris images are used to train the iris segmentation network to achieve state-of-the-art performance. We also propose an algorithm to generate iris masks based on 11 tunable parameters, which can be generated randomly. Such a framework can generate an unlimited amount of photo-realistic training data for down-stream tasks. Experimental results demonstrate that the proposed framework achieved promising results in all commonly used metrics. The proposed framework can be easily generalized to any object segmentation task with a simple fine-tuning of the mask generation algorithm.

Towards More Accurate and Complete Heterogeneous Iris Segmentation Using a Hybrid Deep Learning Approach

“…Although data augmentation techniques (e.g., scaling, flipping, cropping) have been successful in image classification tasks, these techniques are ineffective in the field of iris segmentation. To this end, Putri et al [21] utilized generative adversarial networks to generate different types of iris images. The model generates a large number of iris images by using predefined iris masks and periocular masks.…”