Presentation Attack Detection for Iris Recognition System Using NIR Camera Sensor.

Dat Nguyen,Kang Park,Na Baek,Tuyen Pham

doi:10.3390/s18051315

Abstract

Among biometric recognition systems such as fingerprint, finger-vein, or face, the iris recognition system has proven to be effective for achieving a high recognition accuracy and security level. However, several recent studies have indicated that an iris recognition system can be fooled by using presentation attack images that are recaptured using high-quality printed images or by contact lenses with printed iris patterns. As a result, this potential threat can reduce the security level of an iris recognition system. In this study, we propose a new presentation attack detection (PAD) method for an iris recognition system (iPAD) using a near infrared light (NIR) camera image. To detect presentation attack images, we first localized the iris region of the input iris image using circular edge detection (CED). Based on the result of iris localization, we extracted the image features using deep learning-based and handcrafted-based methods. The input iris images were then classified into real and presentation attack categories using support vector machines (SVM). Through extensive experiments with two public datasets, we show that our proposed method effectively solves the iris recognition presentation attack detection problem and produces detection accuracy superior to previous studies.

Highlights

Over recent decades, biometric technology has gained much attention and is widely used in various applications to enhance user convenience and the security level of recognition systems compared to traditional recognition methods [1,2,3,4,5,6,7,8,9]
We proposed a new presentation attack detection (PAD) method for enhancing the security level of iris recognition systems
The main contribution of our proposed method is that we reduced the limitation of the deep learning-based method by using a combination of handcrafted image features and deep features

Summary

Introduction

Biometric technology has gained much attention and is widely used in various applications to enhance user convenience and the security level of recognition systems compared to traditional recognition methods [1,2,3,4,5,6,7,8,9]. Presentation attack detection methods are required to protect a biometric recognition system from attackers and enhance its security level. Several studies have indicated that a fake iris pattern can be made by recapturing a real iris pattern or by printing an iris pattern on a contact lens to fool iris recognition systems. To address this problem, we propose a new presentation attack detection method for an iris recognition system by using hybrid image features and offer a classification method to overcome the limitations of previous research. Our proposed method is novel in five ways compared to previous research

Methods

Results

Discussion

Conclusion