Multi Loss Fusion For Matching Smartphone Captured Contactless Finger Images

Jawade, Bhavin; Setlur, Srirangaraj; Ratha, Nalini K.

doi:10.1109/wifs53200.2021.9648393

Cited by 12 publications

(5 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, using ROC AUC (which stands for receiver operating characteristic-area under the curve) (37), we quantify the ability of these deeply learned fingerprint representations to discriminate between same-person fingerprint pairs and different-person fingerprint pairs, based on representation vector distance (ROC AUC ranges from 0 → 1, where values above 0.5 indicate better discriminative ability). We trained and validated our model on NIST SD302 (38), NIST SD300 (39), UB RidgeBase (40,41), and MSU PrintsGAN (42) (more details in Materials and Methods). We tested on NIST SD301 (23 people) (43) and different subsets (i.e., containing previously unseen people) of NIST SD302 (20 people) (38) and NIST SD300 (90 people) (39) than were used in training/validation.…”

Section: General Similarity Analysismentioning

confidence: 99%

“…However, the synthetic dataset only has one finger per person, but our target task is to match different fingers from the same person. Thus, we fine-tune real fingerprint datasets that contain multiple fingers per person (NIST SD302, NIST SD300, and UB RidgeBase) (38)(39)(40)(41).…”

Section: Training Process Transfer Learningmentioning

confidence: 99%

“…We fine-tune using 53,315 fingerprint samples from 927 people (and use 5819 fingerprint samples from 114 different people for validation), from the SD302 (38), SD300 (39), and UB RidgeBase (40,41) datasets. All of these datasets contain samples from multiple fingers (e.g., left index, right pinky) per person.…”

Section: Fine-tuningmentioning

confidence: 99%

See 2 more Smart Citations

Unveiling intra-person fingerprint similarity via deep contrastive learning

Guo,

Ray,

Izydorczak

et al. 2024

Sci. Adv.

View full text Add to dashboard Cite

Fingerprint biometrics are integral to digital authentication and forensic science. However, they are based on the unproven assumption that no two fingerprints, even from different fingers of the same person, are alike. This renders them useless in scenarios where the presented fingerprints are from different fingers than those on record. Contrary to this prevailing assumption, we show above 99.99% confidence that fingerprints from different fingers of the same person share very strong similarities. Using deep twin neural networks to extract fingerprint representation vectors, we find that these similarities hold across all pairs of fingers within the same person, even when controlling for spurious factors like sensor modality. We also find evidence that ridge orientation, especially near the fingerprint center, explains a substantial part of this similarity, whereas minutiae used in traditional methods are almost nonpredictive. Our experiments suggest that, in some situations, this relationship can increase forensic investigation efficiency by almost two orders of magnitude.

show abstract

Section: General Similarity Analysismentioning

confidence: 99%

Section: Training Process Transfer Learningmentioning

confidence: 99%

See 1 more Smart Citation

Unveiling intra-person fingerprint similarity via deep contrastive learning

Guo,

Ray,

Izydorczak

et al. 2024

Sci. Adv.

View full text Add to dashboard Cite

show abstract

“…These requirements highly align with recommendations of many established tools from the contactless and contact-based domain. Also, many works propose pre-processing workflows which align to these requirements [23], [24], [25], [26], [27], [28]. From the cited literature, it is also observable that different capturing methods are used and that the pre-processing algorithms are optimized for the dedicated capturing setup.…”

Section: A Sample Pre-processingmentioning

confidence: 99%

MCLFIQ: Mobile Contactless Fingerprint Image Quality

Priesnitz,

Weißenfeld,

Ruzicka

et al. 2024

IEEE Trans. Biom. Behav. Identity Sci.

View full text Add to dashboard Cite

We propose MCLFIQ: Mobile Contactless Fingerprint Image Quality, the first quality assessment algorithm for mobile contactless fingerprint samples. To this end, we retrained the NIST Fingerprint Image Quality (NFIQ) 2 method, which was originally designed for contact-based fingerprints, with a synthetic contactless fingerprint database. We evaluate the predictive performance of the resulting MCLFIQ model in terms of Error-vs.-Discard Characteristic (EDC) curves on three realworld contactless fingerprint databases using three recognition algorithms. In experiments, the MCLFIQ method is compared against the original NFIQ 2 method, a sharpness-based quality assessment algorithm developed for contactless fingerprint images and the general purpose image quality assessment method BRISQUE. Furthermore, benchmarks on four contact-based fingerprint datasets are also conducted. Obtained results show that the fine-tuning of NFIQ 2 on synthetic contactless fingerprints is a viable alternative to training on real databases. Moreover, the evaluation shows that our MCLFIQ method works more accurately and is more robust compared to all baseline methods on contactless fingerprints. We suggest considering the proposed MCLFIQ method as a starting point for the development of a new standard algorithm for contactless fingerprint quality assessment.

show abstract

“…Fingerprint identification is one of the most authentic approaches for human identification [ 1 ], where ridges and minutiae (ridge ending and branch) of the fingerprint information play a significant role in the recognition process [ 2 , 3 , 4 , 5 , 6 , 7 ]. The fingerprint is the oldest and a widely adopted biometric trait in forensic and civilian applications [ 8 ]. Until the use of DNA profiling, fingerprints were the central identification tool in criminal investigation.…”

Section: Introductionmentioning

confidence: 99%

Fingerprint Systems: Sensors, Image Acquisition, Interoperability and Challenges

Mohamed-Abdul-Cader

Banks

Chandran

2023

Sensors

View full text Add to dashboard Cite

The fingerprint is a widely adopted biometric trait in forensic and civil applications. Fingerprint biometric systems have been investigated using contact prints and latent and contactless images which range from low to high resolution. While the imaging techniques are advancing with sensor variations, the input fingerprint images also vary. A general fingerprint recognition pipeline consists of a sensor module to acquire images, followed by feature representation, matching and decision modules. In the sensor module, the image quality of the biometric traits significantly affects the biometric system’s accuracy and performance. Imaging modality, such as contact and contactless, plays a key role in poor image quality, and therefore, paying attention to imaging modality is important to obtain better performance. Further, underlying physical principles and the working of the sensor can lead to their own forms of distortions during acquisition. There are certain challenges in each module of the fingerprint recognition pipeline, particularly sensors, image acquisition and feature representation. Present reviews in fingerprint systems only analyze the imaging techniques in fingerprint sensing that have existed for a decade. However, the latest emerging trends and recent advances in fingerprint sensing, image acquisition and their challenges have been left behind. Since the present reviews are either obsolete or restricted to a particular subset of the fingerprint systems, this work comprehensively analyzes the state of the art in the field of contact-based, contactless 2D and 3D fingerprint systems and their challenges in the aspects of sensors, image acquisition and interoperability. It outlines the open issues and challenges encountered in fingerprint systems, such as fingerprint performance, environmental factors, acceptability and interoperability, and alternate directions are proposed for a better fingerprint system.

show abstract

Multi Loss Fusion For Matching Smartphone Captured Contactless Finger Images

Cited by 12 publications

References 16 publications

Unveiling intra-person fingerprint similarity via deep contrastive learning

Unveiling intra-person fingerprint similarity via deep contrastive learning

MCLFIQ: Mobile Contactless Fingerprint Image Quality

Fingerprint Systems: Sensors, Image Acquisition, Interoperability and Challenges

Contact Info

Product

Resources

About