Fingerprint Spoof Detection Using Contrast Enhancement and Convolutional Neural Networks

Jang, Han-Ul; Choi, Hak-Yeol; Kim, Dongkyu; Son, Ji‐Won; Lee, Heung-Kyu

doi:10.1007/978-981-10-4154-9_39

Cited by 28 publications

(20 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…In 2017, Jang et al proposed contrast enhancement and block-wise processing of the fingerprint to improve the state of the art results achieved with DL [25]. The blocks were then combined with a majority voting rule.…”

Section: B Deep Learning For Conventional Sensorsmentioning

confidence: 99%

Biometric Presentation Attack Detection: Beyond the Visible Spectrum

Tolosana

Gomez‐Barrero

Busch

et al. 2020

IEEE Trans.Inform.Forensic Secur.

View full text Add to dashboard Cite

The increased need for unattended authentication in multiple scenarios has motivated a wide deployment of biometric systems in the last few years. This has in turn led to the disclosure of security concerns specifically related to biometric systems. Among them, Presentation Attacks (PAs, i.e., attempts to log into the system with a fake biometric characteristic or presentation attack instrument) pose a severe threat to the security of the system: any person could eventually fabricate or order a gummy finger or face mask to impersonate someone else. The biometrics community has thus made a considerable effort to the development of automatic Presentation Attack Detection (PAD) mechanisms, for instance through the international LivDet competitions.In this context, we present a novel fingerprint PAD scheme based on i) a new capture device able to acquire images within the short wave infrared (SWIR) spectrum, and ii) an in-depth analysis of several state-of-the-art techniques based on both handcrafted and deep learning features. The approach is evaluated on a database comprising over 4700 samples, stemming from 562 different subjects and 35 different presentation attack instrument (PAI) species. The results show the soundness of the proposed approach with a detection equal error rate (D-EER) as low as 1.36% even in a realistic scenario where five different PAI species are considered only for testing purposes (i.e., unknown attacks).

show abstract

Section: B Deep Learning For Conventional Sensorsmentioning

confidence: 99%

Biometric Presentation Attack Detection: Beyond the Visible Spectrum

Tolosana

Gomez‐Barrero

Busch

et al. 2020

IEEE Trans.Inform.Forensic Secur.

View full text Add to dashboard Cite

show abstract

“…Histogram equalization is performed on each RGB channel in order to increase the contrast and improve the network performance. 41 Then the images are normalized to the [0, 1] range. Normalization is typically performed in neural networks because the nonlinear functions that are employed work better in this range.…”

Section: Data Preprocessingmentioning

confidence: 99%

Semantic segmentation on small datasets of satellite images using convolutional neural networks

Younis

Keedwell

2019

J. Appl. Rem. Sens.

View full text Add to dashboard Cite

Semantic segmentation is one of the most popular and challenging applications of deep learning. It refers to the process of dividing a digital image into semantically homogeneous areas with similar properties. We employ the use of deep learning techniques to perform semantic segmentation on high-resolution satellite images representing urban scenes to identify roads, vegetation, and buildings. A SegNet-based neural network with an encoder-decoder architecture is employed. Despite the small size of the dataset, the results are promising. We show that the network is able to accurately distinguish between these groups for different test images, when using a network with four convolutional layers.

show abstract

“…The new era of the image classification problem has started with the birth of Deep Convolutional Neural Networks (DCNN). DCNN have rapidly shown their effectiveness in fingerprint liveness detection [ 24 , 25 , 26 , 27 , 28 , 29 ]. There are two approaches to use convolutional neural networks in fake fingerprint detection.…”

Section: Literature Review On Presentation Attack Detectionmentioning

confidence: 99%

“…The final decision is made by the voting strategy, i.e., if the number of fake patches is greater than or equal to that of live patches, the fingerprint is fake. Wang et al [ 27 ], Jang et al [ 28 ] and Park et al [ 29 ] experimented with different network models and different patch sizes. Wang et al [ 27 ] divided a fingerprint image into non-overlapped patches of a size of

pixels and then used a four-layer CNN to classify each patch.…”

Section: Literature Review On Presentation Attack Detectionmentioning

confidence: 99%

“…Wang et al [ 27 ] divided a fingerprint image into non-overlapped patches of a size of

pixels and then used a four-layer CNN to classify each patch. Jang et al [ 28 ] used a network with four convolutional layers and two fully-connected layers, which was inspired by the architecture of the VGG network. The patch size in their work was

pixels.…”

Section: Literature Review On Presentation Attack Detectionmentioning

confidence: 99%

See 1 more Smart Citation

fPADnet: Small and Efficient Convolutional Neural Network for Presentation Attack Detection

Nguyen

Park

Cui

et al. 2018

Sensors

View full text Add to dashboard Cite

The rapid growth of fingerprint authentication-based applications makes presentation attack detection, which is the detection of fake fingerprints, become a crucial problem. There have been numerous attempts to deal with this problem; however, the existing algorithms have a significant trade-off between accuracy and computational complexity. This paper proposes a presentation attack detection method using Convolutional Neural Networks (CNN), named fPADnet (fingerprint Presentation Attack Detection network), which consists of Fire and Gram-K modules. Fire modules of fPADnet are designed following the structure of the SqueezeNet Fire module. Gram-K modules, which are derived from the Gram matrix, are used to extract texture information since texture can provide useful features in distinguishing between real and fake fingerprints. Combining Fire and Gram-K modules results in a compact and efficient network for fake fingerprint detection. Experimental results on three public databases, including LivDet 2011, 2013 and 2015, show that fPADnet can achieve an average detection error rate of 2.61%, which is comparable to the state-of-the-art accuracy, while the network size and processing time are significantly reduced.

show abstract

Fingerprint Spoof Detection Using Contrast Enhancement and Convolutional Neural Networks

Cited by 28 publications

References 9 publications

Biometric Presentation Attack Detection: Beyond the Visible Spectrum

Biometric Presentation Attack Detection: Beyond the Visible Spectrum

Semantic segmentation on small datasets of satellite images using convolutional neural networks

fPADnet: Small and Efficient Convolutional Neural Network for Presentation Attack Detection

Contact Info

Product

Resources

About