LivDet iris 2017 — Iris liveness detection competition 2017

Yambay, David; Becker, Benedict; Kohli, Naman; Yadav, Daksha; Czajka, Adam; Bowyer, Kevin W.; Schuckers, Stephanie; Singh, Richa; Vatsa, Mayank; Noore, Afzel; Gragnaniello, Diego; Sansone, Carlo; Verdoliva, Luisa; He, Lingxiao; Ru, Yiwei; Li, Haiqing; Liu, Nianfeng; Sun, Zhenan; Tan, Tieniu

doi:10.1109/btas.2017.8272763

Cited by 99 publications

(96 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To evaluate the detection performance of our proposed iPAD method, we used two public datasets LivDet-Iris 2017-Warsaw [ 48 ] and Notre Dame Contact Lens Detection (NDCLD2015) [ 48 , 52 ]. For convenience, we refer to these datasets as Warsaw2017 and ND2015 in our study.…”

Section: Resultsmentioning

confidence: 99%

“…For convenience, we refer to these datasets as Warsaw2017 and ND2015 in our study. Although there are other presentation attack iris image datasets such as IIITD-WVU, Clarkson [ 48 ], and PAVID [ 53 ], they were unavailable to us via internet request. In addition, the datasets we chose have been used in previous iPAD studies (LivDet-Iris 2017 competition [ 48 ]).…”

Section: Resultsmentioning

confidence: 99%

“…Although there are other presentation attack iris image datasets such as IIITD-WVU, Clarkson [ 48 ], and PAVID [ 53 ], they were unavailable to us via internet request. In addition, the datasets we chose have been used in previous iPAD studies (LivDet-Iris 2017 competition [ 48 ]). The use of these datasets allowed us to compare the detection performance of our proposed method with those of previous studies.…”

Section: Resultsmentioning

confidence: 99%

“…Using the SVM method, we classified the input images into either the real or presentation attack class. To evaluate the performance of our proposed iPAD method and to compare it with previous studies, we used the standard criteria, called average classification error rate (ACER), to measure the detection performance [ 2 , 46 , 47 , 48 ]. By definition, the ACER is a measurement of the average error rate of the attack presentation classification error rate (APCER) and the bona-fide presentation classification error rate (BPCER).…”

Section: Proposed Pad Methods For Iris Recognition Systemmentioning

confidence: 99%

See 3 more Smart Citations

Presentation Attack Detection for Iris Recognition System Using NIR Camera Sensor

Nguyen

Baek

Pham

et al. 2018

Sensors

View full text Add to dashboard Cite

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.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Proposed Pad Methods For Iris Recognition Systemmentioning

confidence: 99%

See 2 more Smart Citations

Presentation Attack Detection for Iris Recognition System Using NIR Camera Sensor

Nguyen

Baek

Pham

et al. 2018

Sensors

View full text Add to dashboard Cite

show abstract

“…Each of them shares a common characteristic for benchmarks such as video based or images. For iris, spoofing attacks usually occur with printed iris images [7] or cosmetic contact lenses [8][9][10]. For faces, a digital video or photograph can be used for a spoof attack [11].…”

Section: Introductionmentioning

confidence: 99%

Auditory Perception Based Anti-Spoofing System for Human Age Verification

et al. 2019

View full text Add to dashboard Cite

Biometric systems are considered an efficient component for identification in the developing modern technologies. The aim of biometric systems is to verify or determine the identity of a user through his/her biological and behavioral characteristics. The threat of spoof attacks is always an important issue in biometric verification and authentication, which requires an updated and stronger protection system. In this article, we propose an anti-spoofing system based on auditory perception responses. To the best of our knowledge, this is the first time that an auditory perception based anti-spoofing system has been presented for age verification. The proposed auditory perception based anti-spoofing system was evaluated with 770 trials conducted by many subjects of each gender and age range (12–65 years of age). The results achieved are encouraging, as the auditory perception based system showed the lowest Equal Error Rate (EER) value of 5.5%.

show abstract