On the importance of using high resolution images, third level features and sequence of images for fingerprint spoof detection

Silva, Murilo Varges da; Marana, Aparecido Nilceu; Paulino, Alessandra A.

doi:10.1109/icassp.2015.7178282

Cited by 4 publications

(4 citation statements)

References 11 publications

(12 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Liveness detection methods based on characteristics of the pores are attracting the attention of the academic and industrial communities, since it is more difficult to create fake fingers simulating the position of the pores of a real fingerprint, with respect to counterfeiting only the minutia points [26]. Liveness detection methods in the literature evaluate the number of pores [14,36,45], statistical features [21,31,45], Euclidean distance [36], and quality indexes [36,45].…”

Section: Extraction Of Pores From Fingerprint Imagesmentioning

confidence: 99%

A novel pore extraction method for heterogeneous fingerprint images using Convolutional Neural Networks

Labati

Genovese

Muñoz

et al. 2018

Pattern Recognition Letters

View full text Add to dashboard Cite

Most fingerprint recognition systems use Level 1 characteristics (ridge flow, orientation, and frequency) and Level 2 features (minutiae points) to recognize individuals. Level 3 features (sweat pores, incipient ridges and ultra-thin characteristics of the ridges) are less frequently adopted because they can be extracted only from high resolution images, but they have the potential of improving all the steps of the biometric recognition process. In particular, sweat pores can be used for quality assessment, liveness detection, biometric matching in live applications, and matching of partial latent fingerprints in forensic applications. Currently, each type of fingerprint acquisition technique (touch-based, touchless, or latent) requires a different algorithm for pore extraction. In this paper, we propose the first method in the literature able to extract the coordinates of the pores from touch-based, touchless, and latent fingerprint images. Our method uses specifically designed and trained Convolutional Neural Networks (CNN) to estimate and refine the centroid of each pore. Results show that our method is feasible and achieved satisfactory accuracy for all the types of evaluated images, with a better performance with respect to the compared state-of-the-art methods.

show abstract

Section: Extraction Of Pores From Fingerprint Imagesmentioning

confidence: 99%

A novel pore extraction method for heterogeneous fingerprint images using Convolutional Neural Networks

Labati

Genovese

Muñoz

et al. 2018

Pattern Recognition Letters

View full text Add to dashboard Cite

show abstract

“…Furthermore, antispoofing methods based on Level 3 features have been recently gaining popularity, since the position and size of the pores is more difficult to counterfeit, with respect to the ridge structure and the minutiae [36]. In this context, several methods use statistical features [37]- [39], NIST NFIQ quality indexes [37], [40], Euclidean distance between pores [40], or the number of pores [37], [40], [41].…”

Section: Related Workmentioning

confidence: 99%

“…For these reasons, currently only Level 1 or Level 2 features have been used for recognition [16], and no approach has been yet proposed for a touchless fingerprint recognition using Level 3 features. The use of such features could help in implementing liveness-based antispoofing methods [24] and in improving the recognition accuracy in touchless fingerprint recognition systems. In some cases, a reduction in the EER up to 20% has been obtained by combining Level 1, Level 2, and Level 3 features [25].…”

Section: Introductionmentioning

confidence: 99%

Towards touchless pore fingerprint biometrics: A neural approach

Genovese

Muñoz

Piuri

et al. 2016

2016 IEEE Congress on Evolutionary Computation (CEC)

View full text Add to dashboard Cite

Touchless fingerprint recognition systems are being increasingly used for a fast, hygienic, and distortion-free recognition. However, due to the greater complexity of the algorithms required for processing touchless fingerprint samples, currently only Level 1 and Level 2 features are being used for recognition, and Level 3 features are used only in touch-based optical devices with about 1000 ppi resolution. In this paper, we propose the first innovative method in the literature able to extract Level 3 features, in particular sweat pores, from fingerprint images captured with a touchless acquisition using a commercial offthe-shelf camera. The method uses image processing algorithms to extract a set of candidate sweat pores. Then, computational intelligence techniques based on neural networks are used to learn the local features of the real pores, and select only the actual sweat pores from the set of candidate points. The results show the validity of the proposed methodology, with the majority of the pores correctly extracted, indicating that a touchless fingerprint recognition using Level 3 features is feasible.

show abstract

“…The classification scheme based on SVM, GMM, Gaussian Copula and Quadratic Discriminant Analysis is used to classify whether the input fingerprint is coming from live person or not. Murilo et al [13] combined fingerprint level3 feature, statistical features and image quality features to detect the spoofing. The pore frequency and number of pores are calculated.…”

Section: B Fingerprint Anti-spoofingmentioning

confidence: 99%

An Intelligent Approach for Anti-Spoofing in a Multimodal Biometric System

Devakumar¹,

Sarala²

2017

IJARCSSE

View full text Add to dashboard Cite

Abstract-Biometric systems are vulnerable to certain type of attacks at various points in the biometric model. A spoofing attack which is submitting a stolen, copied biometric trait to the sensor to gain unauthorized access to the biometric system is one among them. Multimodal biometric systems are designed to increase the accuracy of the biometric system, but they are more vulnerable to spoofing attacks than a unimodal biometric system. The existing approaches for anti-spoofing do not consider multiple biometric traits and also have a high false acceptance rate. The proposed method is designed to overcome spoofing in a multimodal biometric system that uses a combination of face, fingerprint and iris images. The extracted biometric features are fused and fed to a convolution neural network that employs deep learning to detect spoofed features from real features. The proposed method gives better results than existing anti-spoofing methods.

show abstract

On the importance of using high resolution images, third level features and sequence of images for fingerprint spoof detection

Cited by 4 publications

References 11 publications

A novel pore extraction method for heterogeneous fingerprint images using Convolutional Neural Networks

A novel pore extraction method for heterogeneous fingerprint images using Convolutional Neural Networks

Towards touchless pore fingerprint biometrics: A neural approach

An Intelligent Approach for Anti-Spoofing in a Multimodal Biometric System

Contact Info

Product

Resources

About