NFIQ 2 NIST fingerprint image quality

Tabassi, Elham; Olsen, Martin Aastrup; Bausinger, Oliver; Busch, Christoph; Figlarz, Andrew; Fiumara, Gregory; Henniger, Olaf; Merkle, Johannes; Ruhland, Timo; Schiel, C.; Schwaiger, Michael

doi:10.6028/nist.ir.8382

Cited by 31 publications

(17 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…2) Quality distribution analysis: To evaluate the quality of the super-resolved samples, we have used the NFIQ 2.0 utility from NBIS [40]. The NFIQ 2.0 assigns a quality score to an image ranging from 0 to 100.…”

Section: Experiments and Results Analysismentioning

confidence: 99%

Super-resolution Guided Pore Detection for Fingerprint Recognition

Ferdous¹,

Dabouei²,

Dawson³

et al. 2020

Preprint

View full text Add to dashboard Cite

Performance of fingerprint recognition algorithms substantially rely on fine features extracted from fingerprints. Apart from minutiae and ridge patterns, pore features have proven to be usable for fingerprint recognition. Although features from minutiae and ridge patterns are quite attainable from low-resolution images, using pore features is practical only if the fingerprint image is of high resolution which necessitates a model that enhances the image quality of the conventional 500 ppi legacy fingerprints preserving the fine details. To find a solution for recovering pore information from low-resolution fingerprints, we adopt a joint learning-based approach that combines both super-resolution and pore detection networks. Our modified single image Super-Resolution Generative Adversarial Network (SRGAN) framework helps to reliably reconstruct high-resolution fingerprint samples from low-resolution ones assisting the pore detection network to identify pores with a high accuracy. The network jointly learns a distinctive feature representation from a real low-resolution fingerprint sample and successfully synthesizes a high-resolution sample from it. To add discriminative information and uniqueness for all the subjects, we have integrated features extracted from a deep fingerprint verifier with the SRGAN quality discriminator. We also add ridge reconstruction loss, utilizing ridge patterns to make the best use of extracted features. Our proposed method solves the recognition problem by improving the quality of fingerprint images. High recognition accuracy of the synthesized samples that is close to the accuracy achieved using the original high-resolution images validate the effectiveness of our proposed model.

show abstract

Section: Experiments and Results Analysismentioning

confidence: 99%

Super-resolution Guided Pore Detection for Fingerprint Recognition

Ferdous¹,

Dabouei²,

Dawson³

et al. 2020

Preprint

View full text Add to dashboard Cite

show abstract

“…We validate the realism of our synthetic live and spoof images through extensive qualitative and quantitative metrics including NFIQ2 [31], minutiae statistics, match scores from a SOTA fingerprint matcher, and T-SNE feature space analysis showing the similarity of real live and spoof embeddings to the embeddings of our synthetic live and spoof fingerprints. Besides verifying the realism of our synthetic spoof generator, we also show how SpoofGAN fingerprints can be used to train a DNN for fingerprint spoof detection.…”

Section: Introductionmentioning

confidence: 87%

“…This problem is related to mode-collapse and has been noted in several GAN related works [63], [64], [65], with some recent papers proposing strategies to improve the generation process in classimbalanced datasets [66], [67]. Next, we computed the NFIQ 2.0 quality metric [31] on both datasets. The NFIQ 2.0 scores for SpoofGAN are, on average, lower compared to LivDet.…”

Section: Quantitative Analysis Of Synthetic Live and Spoof Imagesmentioning

confidence: 99%

SpoofGAN: Synthetic Fingerprint Spoof Images

Grosz¹,

Jain²

2022

Preprint

View full text Add to dashboard Cite

A major limitation to advances in fingerprint spoof detection is the lack of publicly available, large-scale fingerprint spoof datasets, a problem which has been compounded by increased concerns surrounding privacy and security of biometric data. Furthermore, most state-of-the-art spoof detection algorithms rely on deep networks which perform best in the presence of a large amount of training data. This work aims to demonstrate the utility of synthetic (both live and spoof) fingerprints in supplying these algorithms with sufficient data to improve the performance of fingerprint spoof detection algorithms beyond the capabilities when training on a limited amount of publicly available "real" datasets. First, we provide details of our approach in modifying a state-of-the-art generative architecture to synthesize high quality live and spoof fingerprints. Then, we provide quantitative and qualitative analysis to verify the quality of our synthetic fingerprints in mimicking the distribution of real data samples. We showcase the utility of our synthetic live and spoof fingerprints in training a deep network for fingerprint spoof detection, which dramatically boosts the performance across three different evaluation datasets compared to an identical model trained on real data alone. Finally, we demonstrate that only 25% of the original (real) dataset is required to obtain similar detection performance when augmenting the training dataset with synthetic data.

show abstract

“…Consequently, we utilize the BOZORTH3 minutiae-based fingerprint matcher [16] to evaluate the uniqueness of the synthetically generated fingerprints through their imposter distribution [8] and expand upon previous works by evaluating the quality and diversity of the synthetic fingerprints through fingerprint metrics. We evaluated the quality of the fingerprints using NIST NFIQ 2.0 [17] and utilized the NIST NBIS software [16] to evaluate and compare the minutiae configuration of the training (DB-1) and synthetic (DB-2) fingerprints. Additionally, we leveraged the work of Olsen et al to extract features based on ridgevalley signature [18].…”

Section: Training and Evaluationmentioning

confidence: 99%

High Fidelity Fingerprint Generation: Quality, Uniqueness, And Privacy

Bahmani

Plesh

Johnson

et al. 2021

2021 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

In this work, we utilize progressive growth-based Generative Adversarial Networks (GANs) to develop the Clarkson Fingerprint Generator (CFG). We demonstrate that the CFG is capable of generating realistic, high fidelity, 512 × 512 pixels, full, plain impression fingerprints. Our results suggest that the fingerprints generated by the CFG are unique, diverse, and resemble the training dataset in terms of minutiae configuration and quality, while not revealing the underlying identities of the training data. We make the pre-trained CFG model and the synthetically generated dataset publicly available at https: //github.com/keivanB/Clarkson_Finger_Gen

show abstract

NFIQ 2 NIST fingerprint image quality

Cited by 31 publications

References 4 publications

Super-resolution Guided Pore Detection for Fingerprint Recognition

Super-resolution Guided Pore Detection for Fingerprint Recognition

SpoofGAN: Synthetic Fingerprint Spoof Images

High Fidelity Fingerprint Generation: Quality, Uniqueness, And Privacy

Contact Info

Product

Resources

About