Cancelable iris template based on slicing

Qianrong Zheng, Jianwen Xiang, Changtian Song, Rivalino Matias, Rui Hao, Songsong Liao, Xue-Min Zhang, Meng Zhao, Dongdong Zhao

Abstract: With the widespread adoption of iris authentication technology and its use in different applications, the potential risks associated with iris template leakage have become a major concern. Hence, a secure template protection scheme becomes an important requirement for biometric systems. However, most of the current template protection schemes based on cancelable templates fail to meet the balance between security and performance. To address this challenge, we propose a method called cancelable iris template based on slicing (Iris-Slice). The scheme generates segments by segmenting the original iris data to a specific length, and subsequently compares these segments with their opposite sequences and retains the smaller segments. Next, the retained segments are randomly expanded, where the expanded sequences are half the inverse of the original iris data. Ultimately, the expanded sequences are saved in a collection for iris data protection. Experimental results on well-known iris datasets (CASIA-IrisV3-Interval, CASIA-IrisV4-Lamp, MMU-V1, IITD) show that the accuracy of the Iris-Slice method decreases only slightly by 0.63%. We also analyze the irreversibility, revocability, and unlinkability of our proposed scheme, both theoretically and experimentally. The results show that our scheme satisfies all these requirements with high performance.