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

Wenny Ramadha Putri, Shen Hsuan Liu, Muhammad Saqlain Aslam, Yung Hui Li, Chin Chen Chang, Jia Ching Wang

研究成果: 雜誌貢獻期刊論文同行評審

2 引文 斯高帕斯(Scopus)


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.

期刊Sensors (Switzerland)
出版狀態已出版 - 1 3月 2022


深入研究「Self-Supervised Learning Framework toward State-of-the-Art Iris Image Segmentation」主題。共同形成了獨特的指紋。