Fingerphoto spoofing in mobile devices: A preliminary study
01 Sep 2016-pp 1-7
TL;DR: This research is aimed at understanding the effect of spoofing on fingerphoto spoofing, and creating a large spoofed fingerphoto database and making it publicly available for research.
Abstract: Biometric-based authentication for smart handheld devices promises to provide a reliable and alternate security mechanism compared to traditional methods such as pins, patterns, and passwords. Although fingerprints are a viable source for authentication, they generally require installation of an additional hardware such as optical and swipe sensors on mobile devices, and are only available in expensive, high-end smartphones. Alternatively, fingerphoto images captured using the smartphone camera for authentication is one of the promising biometric approaches. However, using fingerphotos for authentication brings along a major challenge of fingerphoto spoofing. This research is aimed at understanding the effect of spoofing on fingerphotos. There are three major contributions of this research: (i) create a large spoofed fingerphoto database and make it publicly available for research, (ii) to establish the effect of print attack and photo attack in fingerphoto spoofing, and (iii) understand the performance of existing spoofing detection algorithms on fingerphoto spoofing.
Citations
More filters
01 Jan 2023
TL;DR: The COLFISPOOF database as mentioned in this paper is a dataset of 7,200 samples of 72 PAI species and was acquired using a contactless fingerprint recognition system utilizing a smartphone as capturing device.
Abstract: Contactless fingerprint recognition is known for its high user comfort and low hygienic concerns. However, contact-less fingerprint recognition, especially in mobile and un-supervised scenarios, is vulnerable to presentation attacks. Presentation Attack Detection (PAD) in biometric systems like contactless fingerprint recognition is more challenging compared with contact-based modalities because many de-tection mechanisms rely on direct contact between the finger and the surface of the capture device. Hence, in contactless scenarios it is generally possible to present more Presentation Attack Instruments (PAIs) like printout or replay arte-facts. In this work, we introduce COLFISPOOF, a new database for contactless fingerprint PAD. The database is acquired using a contactless fingerprint recognition system utilizing a smartphone as capturing device. It comprises 7,200 samples of 72 different PAI species and was captured with two different smartphone models. The database is publicly available for research purposes such that interested researchers can download and use it to develop new PAD algorithms. Moreover, we define evaluation protocols for training and testing of machine learning algorithms such that future PAD algorithms can be benchmarked on this database in a comparable and reproducible way.
3 citations
01 Jan 2019
TL;DR: Experimental results show that despite multiple challenges present in the UNFIT database, the segmentation algorithm can segment and perform authentication using finger-selfies.
Abstract: In the last one decade, the usage and capabilities of smartphones have increased multifold. To keep data and devices secure, fingerprint and face recognition-based unlocking are gaining popularity. However, the additional cost of installing fingerprint sensors on smartphones questions the use of fingerprints. Alternatively, finger-selfie, an image of a person’s finger acquired using a built-in smartphone camera, can act as a cost-effective solution. Unlike capturing face selfies, capturing good-quality finger-selfies may not be a trivial task. The captured finger-selfie might incorporate several challenges such as illumination, in- and out-of-plane rotations, blur, and occlusion. Users may even present multiple fingers together in the same frame. In this chapter, we propose authentication using finger-selfies taken in an unconstrained environment. The research contributions include the UNconstrained FIngerphoTo (UNFIT) database which is captured under challenging unconstrained conditions. The database also contains the manual annotation of identities and location of the fingers. We further present a segmentation algorithm to segment finger regions and, finally, perform feature extraction and matching using CompCode and ResNet50. Experimental results show that despite multiple challenges present in the UNFIT database, the segmentation algorithm can segment and perform authentication using finger-selfies.
2 citations
TL;DR: This work presents an approach for presentation attack detection that enables a palm-vein sensor to provide effective countermeasures against these attacks, based on analysis of noise residual computed from the acquired image.
Abstract: Abstract. Widespread deployment of biometric systems has made researchers focus on its vulnerability to even the simplest attempts to breach security through presentation attacks, which involve presenting an artefact (fake sample) to the biometric sensor. We present an approach for presentation attack detection that enables a palm-vein sensor to provide effective countermeasures against these attacks. Our method is based on analysis of noise residual computed from the acquired image. The palm-vein image acquired by the sensor is denoised through median filtering, a well-known nonlinear technique for noise reduction. Subsequently, a noise residual image is obtained by subtracting the denoised image from the acquired image. The local texture features extracted from the noise residual image are then used to detect the presentation attack by means of a trained binary support vector machine classifier. We have performed evaluations on a publicly available palm-vein dataset consisting of 4000 bona fide and fake images collected from 50 subjects in two different sessions. Our approach consistently achieves a perfect average classification error rate of 0.0%. The results also suggest that the proposed approach is more effective than state-of-the-art methods in palm-vein antispoofing.
2 citations
09 Mar 2023
TL;DR: In this paper , the authors developed a presentation attack detection (PAD) dataset of more than 7500 four-finger images and more than 14,000 manually segmented single-fingertip images, and 10,000 synthetic fingertips (deepfakes).
Abstract: Touch-based fingerprint biometrics is one of the most popular biometric modalities with applications in several fields. Problems associated with touch-based techniques such as the presence of latent fingerprints and hygiene issues due to many people touching the same surface motivated the community to look for non-contact-based solutions. For the last few years, contactless fingerprint systems are on the rise and in demand because of the ability to turn any device with a camera into a fingerprint reader. Yet, before we can fully utilize the benefit of noncontact-based methods, the biometric community needs to resolve a few concerns such as the resiliency of the system against presentation attacks. One of the major obstacles is the limited publicly available data sets with inadequate spoof and live data. In this publication, we have developed a Presentation attack detection (PAD) dataset of more than 7500 four-finger images and more than 14,000 manually segmented single-fingertip images, and 10,000 synthetic fingertips (deepfakes). The PAD dataset was collected from six different Presentation Attack Instruments (PAI) of three different difficulty levels according to FIDO protocols, with five different types of PAI materials, and different smartphone cameras with manual focusing. We have utilized DenseNet-121 and NasNetMobile models and our proposed dataset to develop PAD algorithms and achieved PAD accuracy of Attack presentation classification error rate (APCER) 0.14% and Bonafide presentation classification error rate (BPCER) 0.18%. We have also reported the test results of the models against unseen spoof types to replicate uncertain real-world testing scenarios.
2 citations
TL;DR: In this paper , a comparative study on the generalizability of seven different pre-trained Convolutional Neural Networks (CNN) and a Vision Transformer (ViT) to reliably detect presentation attacks is presented.
Abstract: The rapid evolution of high-end smartphones with advanced high-resolution cameras has resulted in contactless capture of fingerprint biometrics that are more reliable and suitable for verification. Similar to other biometric systems, contactless fingerprint-verification systems are vulnerable to presentation attacks. In this paper, we present a comparative study on the generalizability of seven different pre-trained Convolutional Neural Networks (CNN) and a Vision Transformer (ViT) to reliably detect presentation attacks. Extensive experiments were carried out on publicly available smartphone-based presentation attack datasets using four different Presentation Attack Instruments (PAI). The detection performance of the eighth deep feature technique was evaluated using the leave-one-out protocol to benchmark the generalization performance for unseen PAI. The obtained results indicated the best generalization performance with the ResNet50 CNN.
References
More filters
[...]
TL;DR: Internal estimates monitor error, strength, and correlation and these are used to show the response to increasing the number of features used in the forest, and are also applicable to regression.
Abstract: Random forests are a combination of tree predictors such that each tree depends on the values of a random vector sampled independently and with the same distribution for all trees in the forest. The generalization error for forests converges a.s. to a limit as the number of trees in the forest becomes large. The generalization error of a forest of tree classifiers depends on the strength of the individual trees in the forest and the correlation between them. Using a random selection of features to split each node yields error rates that compare favorably to Adaboost (Y. Freund & R. Schapire, Machine Learning: Proceedings of the Thirteenth International conference, aaa, 148–156), but are more robust with respect to noise. Internal estimates monitor error, strength, and correlation and these are used to show the response to increasing the number of features used in the splitting. Internal estimates are also used to measure variable importance. These ideas are also applicable to regression.
79,257 citations
"Fingerphoto spoofing in mobile devi..." refers methods in this paper
...Three different matching approaches are adopted: (i) L2 distance based matching, (ii) Neural Network (NN), and (iii) Random Decision Forest (RDF) [6]....
[...]
...We see that the photo attack with iPad-Nokia has the least TAR for ScatNet+NN and ScatNet+RDF matching algorithms, and it is in accordance with Table 3 which provides the highest EER for iPad-Nokia....
[...]
...ScatNet + RDF yields the best results for both spoofed and nonspoofed images; the EERs are in the range of 0.48% to 2.53%....
[...]
TL;DR: Issues such as solving SVM optimization problems theoretical convergence multiclass classification probability estimates and parameter selection are discussed in detail.
Abstract: LIBSVM is a library for Support Vector Machines (SVMs). We have been actively developing this package since the year 2000. The goal is to help users to easily apply SVM to their applications. LIBSVM has gained wide popularity in machine learning and many other areas. In this article, we present all implementation details of LIBSVM. Issues such as solving SVM optimization problems theoretical convergence multiclass classification probability estimates and parameter selection are discussed in detail.
40,826 citations
"Fingerphoto spoofing in mobile devi..." refers methods in this paper
...In general, those images that are not correctly matched with the matching algorithm are easily distinguished as spoof images by the SVM classifier, which is in accordance with the basic understanding of the problem....
[...]
...Hence, spoof detection is formulated as a binary classification problem using an SVM [7] to learn these texture patterns from a spoofed image....
[...]
...To study the behavior of high definition display devices such as retina display, gradient based DSIFT [10] features and LUCID descriptor [17] are also independently used to learn an SVM. LUCID descriptors are recently found to provide successful performance in the domain of mobile biometric liveness detection [5]....
[...]
...While using the complete test set, LBP + SVM gives the best spoofed fingerphoto detection performance with 3.71% EER when the complete spoofed dataset is considered....
[...]
...We evaluate the performance of different features such as Local Binary Patterns (LBP), Dense Scale Invariant Feature Transform (DSIFT), and Locally Uniform Comparison Image Descriptor (LUCID) features along with Support Vector Machine (SVM) based fingerphoto spoofing detection algorithm to distinguish between spoofed and non-spoofed images....
[...]
20 Sep 1999
TL;DR: Experimental results show that robust object recognition can be achieved in cluttered partially occluded images with a computation time of under 2 seconds.
Abstract: An object recognition system has been developed that uses a new class of local image features. The features are invariant to image scaling, translation, and rotation, and partially invariant to illumination changes and affine or 3D projection. These features share similar properties with neurons in inferior temporal cortex that are used for object recognition in primate vision. Features are efficiently detected through a staged filtering approach that identifies stable points in scale space. Image keys are created that allow for local geometric deformations by representing blurred image gradients in multiple orientation planes and at multiple scales. The keys are used as input to a nearest neighbor indexing method that identifies candidate object matches. Final verification of each match is achieved by finding a low residual least squares solution for the unknown model parameters. Experimental results show that robust object recognition can be achieved in cluttered partially occluded images with a computation time of under 2 seconds.
16,989 citations
"Fingerphoto spoofing in mobile devi..." refers methods in this paper
...To study the behavior of high definition display devices such as retina display, gradient based DSIFT [10] features and LUCID descriptor [17] are also independently used to learn an SVM. LUCID descriptors are recently found to provide successful performance in the domain of mobile biometric liveness detection [5]....
[...]
...To study the behavior of high definition display devices such as retina display, gradient based DSIFT [10] features and LUCID descriptor [17] are also independently used to learn an SVM....
[...]
...We evaluate the performance of different features such as Local Binary Patterns (LBP), Dense Scale Invariant Feature Transform (DSIFT), and Locally Uniform Comparison Image Descriptor (LUCID) features along with Support Vector Machine (SVM) based fingerphoto spoofing detection algorithm to distinguish between spoofed and non-spoofed images....
[...]
...The results using both LBP, DSIFT, and LUCID descriptors are presented in Table 5 and Table 6 and the ROC curves are shown in Figure 5....
[...]
...Further, we evaluated different features such as LBP, DSIFT, and LUCID combined with a learning algorithm to classify spoofed and original images....
[...]
TL;DR: This paper presents a novel and efficient facial image representation based on local binary pattern (LBP) texture features that is assessed in the face recognition problem under different challenges.
Abstract: This paper presents a novel and efficient facial image representation based on local binary pattern (LBP) texture features. The face image is divided into several regions from which the LBP feature distributions are extracted and concatenated into an enhanced feature vector to be used as a face descriptor. The performance of the proposed method is assessed in the face recognition problem under different challenges. Other applications and several extensions are also discussed
5,563 citations
"Fingerphoto spoofing in mobile devi..." refers methods in this paper
...The texture patterns are extracted using LBP features [3, 8, 11]....
[...]
TL;DR: This work presents a novel approach based on analyzing facial image textures for detecting whether there is a live person in front of the camera or a face print, and analyzes the texture of the facial images using multi-scale local binary patterns (LBP).
Abstract: Current face biometric systems are vulnerable to spoofing attacks. A spoofing attack occurs when a person tries to masquerade as someone else by falsifying data and thereby gaining illegitimate access. Inspired by image quality assessment, characterization of printing artifacts, and differences in light reflection, we propose to approach the problem of spoofing detection from texture analysis point of view. Indeed, face prints usually contain printing quality defects that can be well detected using texture features. Hence, we present a novel approach based on analyzing facial image textures for detecting whether there is a live person in front of the camera or a face print. The proposed approach analyzes the texture of the facial images using multi-scale local binary patterns (LBP). Compared to many previous works, our proposed approach is robust, computationally fast and does not require user-cooperation. In addition, the texture features that are used for spoofing detection can also be used for face recognition. This provides a unique feature space for coupling spoofing detection and face recognition. Extensive experimental analysis on a publicly available database showed excellent results compared to existing works.
628 citations
"Fingerphoto spoofing in mobile devi..." refers methods in this paper
...The texture patterns are extracted using LBP features [3, 8, 11]....
[...]