Detecting Textured Contact Lens in Uncontrolled Environment Using DensePAD
16 Jun 2019-pp 2336-2344
TL;DR: A new Unconstrained Multi-sensor Iris Presentation Attack (UnMIPA) database is created and a novel algorithm, DensePAD, which utilizes DenseNet based convolutional neural network architecture for iris presentation attack detection is presented.
Abstract: The ubiquitous use of smartphones has spurred the research in mobile iris devices. Due to their convenience, these mobile devices are also utilized in unconstrained outdoor conditions. This scenario has necessitated the development of reliable iris recognition algorithms for such an uncontrolled environment. Additionally, iris presentation attacks such as textured contact lens pose a major challenge to current iris recognition systems. Motivated by these, this paper presents two key contributions. First, a new Unconstrained Multi-sensor Iris Presentation Attack (UnMIPA) database is created. It consists of more than 18,000 iris images of subjects wearing textured contact lens and without wearing contact lenses captured in both indoor and outdoor environment using multiple iris sensors. The second contribution of this paper is a novel algorithm, DensePAD, which utilizes DenseNet based convolutional neural network architecture for iris presentation attack detection. In-depth experimental evaluation of this algorithm reveals its superior performance in detecting iris presentation attack images on multiple databases. The performance of the proposed DensePAD algorithm is also evaluated in real-world scenarios of open-set iris presentation attacks which highlights the challenging nature of detecting iris presentation attack images from unseen distributions.
Citations
More filters
TL;DR: Zhang et al. as discussed by the authors proposed an attention-based deep pixel-wise bi-nary supervision (A-PBS) method to detect iris presentation attack detection.
Abstract: Iris presentation attack detection (PAD) plays a vital role in iris recognition systems. Most existing CNN-based iris PAD solutions 1) perform only binary label supervision during the training of CNNs, serving global information learning but weakening the capture of local discriminative features, 2) prefer the stacked deeper convolutions or expert-designed networks, raising the risk of overfitting, 3) fuse multiple PAD systems or various types of features, increasing difficulty for deployment on mobile devices. Hence, we propose a novel attention-based deep pixel-wise bi-nary supervision (A-PBS) method. Pixel-wise supervision is first able to capture the fine-grained pixel/patch-level cues. Then, the attention mechanism guides the network to automatically find regions that most contribute to an accurate PAD decision. Extensive experiments are performed on LivDet-Iris 2017 and three other publicly available databases to show the effectiveness and robustness of proposed A-PBS methods. For instance, the A-PBS model achieves an HTER of 6.50% on the IIITD-WVU database outperforming state-of-the-art methods.
26 citations
Posted Content•
TL;DR: This work proposes an effective and robust iris PA detector called D-NetPAD based on the DenseNet convolutional neural network architecture that demonstrates generalizability across PA artifacts, sensors and datasets.
Abstract: An iris recognition system is vulnerable to presentation attacks, or PAs, where an adversary presents artifacts such as printed eyes, plastic eyes, or cosmetic contact lenses to circumvent the system. In this work, we propose an effective and robust iris PA detector called D-NetPAD based on the DenseNet convolutional neural network architecture. It demonstrates generalizability across PA artifacts, sensors and datasets. Experiments conducted on a proprietary dataset and a publicly available dataset (LivDet-2017) substantiate the effectiveness of the proposed method for iris PA detection. The proposed method results in a true detection rate of 98.58\% at a false detection rate of 0.2\% on the proprietary dataset and outperfoms state-of-the-art methods on the LivDet-2017 dataset. We visualize intermediate feature distributions and fixation heatmaps using t-SNE plots and Grad-CAM, respectively, in order to explain the performance of D-NetPAD. Further, we conduct a frequency analysis to explain the nature of features being extracted by the network. The source code and trained model are available at this https URL.
20 citations
Cites background or methods from "Detecting Textured Contact Lens in ..."
...[38] also utilize the DenseNet architecture to detect cosmetic contact PA images captured by various mobile iris sensors....
[...]
...The features of different categories are sufficiently discriminated at the end of Dense Block 4, which justifies the use of four Dense blocks in the architecture as opposed to three in [38]....
[...]
...The work in [38] exploits the DenseNet architecture of depth 22 with three densely connected blocks....
[...]
06 Jul 2020
TL;DR: This work proposes an iris PAD solution based on multi-layer fusion, which performs better than the best single layer feature extractor in most cases and achieves similar or better results than the state-of-the-art algorithms on the Notre Dame and IIITD-WVU databases.
Abstract: Iris presentation attack detection (PAD) algorithms are developed to address the vulnerability of iris recognition systems to presentation attacks. Taking into account that the deep features successfully improved computer vision performance in various fields including iris recognition, it is natural to use features extracted from deep neural networks for iris PAD. Each layer in a deep learning network carries features of different level of abstraction. The features extracted from the first layer to the higher layers become more complex and more abstract. This might point our complementary information in these features that can collaborate towards an accurate PAD decision. Therefore, we propose an iris PAD solution based on multi-layer fusion. The information extracted from the last several convolutional layers are fused on two levels, feature-level and score-level. We demonstrated experiments on both, off-the-shelf pre-trained network and network trained from scratch. An extensive experiment also explores the complementary between different layer combinations of deep features. Our experimental results show that feature-level based multi-layer fusion method performs better than the best single layer feature extractor in most cases. In addition, our fusion results achieve similar or better results than the state-of-the-art algorithms on the Notre Dame and IIITD-WVU databases of the Iris Liveness Detection Competition 2017 (LivDet-Iris 2017).
19 citations
TL;DR: An in-depth experimental evaluation of this framework reveals a superior performance in three databases compared with state-of-the-art (SoTA) algorithms and baselines, and minimizes the confusion between textured and transparent presentations in comparison to SoTA methods.
16 citations
TL;DR: In this paper, the authors present an overview of the most important advances in the area of iris presentation attack detection published in the recent two years and discuss the possible directions for future research.
15 citations
References
More filters
21 Jul 2017
TL;DR: DenseNet as mentioned in this paper proposes to connect each layer to every other layer in a feed-forward fashion, which can alleviate the vanishing gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters.
Abstract: Recent work has shown that convolutional networks can be substantially deeper, more accurate, and efficient to train if they contain shorter connections between layers close to the input and those close to the output. In this paper, we embrace this observation and introduce the Dense Convolutional Network (DenseNet), which connects each layer to every other layer in a feed-forward fashion. Whereas traditional convolutional networks with L layers have L connections—one between each layer and its subsequent layer—our network has L(L+1)/2 direct connections. For each layer, the feature-maps of all preceding layers are used as inputs, and its own feature-maps are used as inputs into all subsequent layers. DenseNets have several compelling advantages: they alleviate the vanishing-gradient problem, strengthen feature propagation, encourage feature reuse, and substantially reduce the number of parameters. We evaluate our proposed architecture on four highly competitive object recognition benchmark tasks (CIFAR-10, CIFAR-100, SVHN, and ImageNet). DenseNets obtain significant improvements over the state-of-the-art on most of them, whilst requiring less memory and computation to achieve high performance. Code and pre-trained models are available at https://github.com/liuzhuang13/DenseNet.
27,821 citations
TL;DR: This paper presents a novel lens detection algorithm that can be used to reduce the effect of contact lenses and outperforms other lens detection algorithms on the two databases and shows improved iris recognition performance.
Abstract: The presence of a contact lens, particularly a textured cosmetic lens, poses a challenge to iris recognition as it obfuscates the natural iris patterns. The main contribution of this paper is to present an in-depth analysis of the effect of contact lenses on iris recognition. Two databases, namely, the IIIT-D Iris Contact Lens database and the ND-Contact Lens database, are prepared to analyze the variations caused due to contact lenses. We also present a novel lens detection algorithm that can be used to reduce the effect of contact lenses. The proposed approach outperforms other lens detection algorithms on the two databases and shows improved iris recognition performance.
149 citations
"Detecting Textured Contact Lens in ..." refers background in this paper
...Literature has demonstrated that textured contact lenses can be utilized for identity impersonation as well as obfuscation [19, 20, 23]....
[...]
...ND-Contact-Lens-2015 [4] 326 7,300 IIIT-Delhi Contact Lens Iris Database [19] 101 6,570...
[...]
[...]
TL;DR: A path forward is proposed to advance the research on ocular recognition by improving the sensing technology, heterogeneous recognition for addressing interoperability, utilizing advanced machine learning algorithms for better representation and classification, and developing algorithms for ocular Recognition at a distance.
138 citations
"Detecting Textured Contact Lens in ..." refers background in this paper
...Due to the reliable nature of iris biometrics [13], iris sensors and recognition systems are being made available in the new generation mobile devices [14]....
[...]
06 Aug 2012
TL;DR: The novel anti-spoofing technique is tested on a database comprising over 1,600 real and fake iris samples proving to have a very high potential as an effective protection scheme against direct attacks.
Abstract: A new liveness detection scheme for iris based on quality related measures is presented. The novel antispoofing technique is tested on a database comprising over 1,600 real and fake (high quality printed images) iris samples proving to have a very high potential as an effective protection scheme against direct attacks. Furthermore, the liveness detection method presented has the added advantage over previously studied techniques of needing just one iris image (the same used for verification) to decide whether it comes from a real or fake eye.
129 citations
Additional excerpts
...ATVS-FIr [6] 50 1,600 LivDet-Iris-2013-Warsaw [23] 284 1,667...
[...]
23 Aug 2010
TL;DR: A novel fake iris detection algorithm based on improved LBP and statistical features is proposed, which achieves state-of-the-art performance in contact lens spoof detection.
Abstract: Spoof detection is a critical function for iris recognition because it reduces the risk of iris recognition systems being forged. Despite various counterfeit artifacts, cosmetic contact lens is one of the most common and difficult to detect. In this paper, we proposed a novel fake iris detection algorithm based on improved LBP and statistical features. Firstly, a simplified SIFT descriptor is extracted at each pixel of the image. Secondly, the SIFT descriptor is used to rank the LBP encoding sequence. Then, statistical features are extracted from the weighted LBP map. Lastly, SVM classifier is employed to classify the genuine and counterfeit iris images. Extensive experiments are conducted on a database containing more than 5000 fake iris images by wearing 70 kinds of contact lens, and captured by four iris devices. Experimental results show that the proposed method achieves state-of-the-art performance in contact lens spoof detection.
120 citations
"Detecting Textured Contact Lens in ..." refers methods in this paper
...It achieves at least 3% lower total error as compared to LBP, WLBP, and DESIST....
[...]
...Comparative analysis of the proposed DensePAD algorithm is also performed with existing iris PAD algorithms: LBP [7], WLBP [25], and DESIST framework [11]....
[...]
...Comparative analysis is performed with existing iris PAD algorithms: Local Binary Patterns (LBP) [7], Weighted Local Binary Patterns (WLBP) [25], and DEtection of iriS spoofIng using Structural and Textural feature (DESIST) [11]....
[...]