Dynamic Pore Filtering for Keypoint Detection Applied to Newborn Authentication

Lemes, Rubisley de Paula; Segundo, Maurício Pamplona; Bellon, Olga Regina Pereira; Silva, Luciano

doi:10.1109/icpr.2014.299

Cited by 13 publications

(6 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These images enable cross‐matching researches for different purposes. Also, we include sweat pore annotations for 740 images to assist in pore detection research [26]. This is the largest publicly available database with L3 fingerprints nowadays.…”

Section: Introductionmentioning

confidence: 99%

Multiresolution synthetic fingerprint generation

2022

Self Cite

View full text Add to dashboard Cite

Public access to existing high-resolution databases was discontinued. Besides, a hybrid database that contains fingerprints of different sensors with high and medium resolutions does not exist. A novel hybrid approach to synthesise realistic, multiresolution, and multisensor fingerprints to address these issues is presented. The first step was to improve Anguli, a handcrafted fingerprint generator, to create pores, scratches, and dynamic ridge maps. Using CycleGAN, then the maps are converted into realistic fingerprints, adding textures to images. Unlike other neural network-based methods, the authors' method generates multiple images with different resolutions and styles for the same identity. With the authors' approach, a synthetic database with 14,800 fingerprints is built. Besides that, fingerprint recognition experiments with pore-and minutiae-based matching techniques and different fingerprint quality analyses are conducted to confirm the similarity between real and synthetic databases. Finally, a human classification analysis is performed, where volunteers could not distinguish between authentic and synthetic fingerprints. These experiments demonstrate that the authors' approach is suitable for supporting further fingerprint recognition studies in the absence of real databases.

show abstract

Section: Introductionmentioning

confidence: 99%

Multiresolution synthetic fingerprint generation

2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…Recently, Lemes et al [14] proposed a dynamic pore filtering approach which is adaptive to the pore size variations and involves less computational cost. Segundo and Lemes [15] improved the dynamic pore filtering approach in [14] by considering the average ridge width in place of average valley width to obtain global and local radii which are used in the same manner as in [14]. Most recently, Dahia and Segundo [19] presented an approach to generate pore annotation by aligning the fingerprint images in the training set and then learned the descriptor for each of the pore patches by employing an existing CNN-based patch matching model, HardNet [20].…”

Section: Introductionmentioning

confidence: 99%

PoreNet: CNN-based Pore Descriptor for High-resolution Fingerprint Recognition

Anand

Kanhangad

2020

IEEE Sensors J.

View full text Add to dashboard Cite

With the development of high-resolution fingerprint scanners, high-resolution fingerprint-based biometric recognition has received increasing attention in recent years. This letter presents a pore feature-based approach for biometric recognition. Our approach employs a convolutional neural network (CNN) model, DeepResPore, to detect pores in the input fingerprint image. Thereafter, a CNN-based descriptor is computed for a patch around each detected pore. Specifically, we have designed a residual learning-based CNN, referred to as PoreNet that learns distinctive feature representation from pore patches. For verification, the match score is generated by comparing pore descriptors obtained from a pair of fingerprint images in bidirectional manner using the Euclidean distance. The proposed approach for high-resolution fingerprint recognition achieves 2.56% and 0.57% equal error rates (EERs) on partial (DBI) and complete (DBII) fingerprints of the benchmark PolyU HRF dataset. Most importantly, it achieves lower FMR1000 and FMR10000 values than the current state-of-the-art approach on both the datasets.

show abstract

“…These challenges have also led to the development of authentication methods for newborns, say, based on derived features such as key points from pore patterns (e.g. Lemes et al (2014)) or of entire palm prints or footprints (e.g. Lemes et al (2011) and Jia et al (2012)).…”

Section: Introductionmentioning

confidence: 99%

Detecting Anisotropy in Fingerprint Growth

Markert

Krehl

Gottschlich

et al. 2019

Journal of the Royal Statistical Society Series C: Applied Statistics

View full text Add to dashboard Cite

Summary From infancy to adulthood, human growth is anisotropic, much more along the proximal–distal axis (height) than along the medial–lateral axis (width), particularly at extremities. Detecting and modelling the rate of anisotropy in fingerprint growth facilitate the use of children's fingerprints for long‐term biometric identification. Using standard fingerprint scanners, anisotropic growth is highly overshadowed by the varying distortions created by each imprint, and it seems that this difficulty has hampered to date the development of suitable methods, detecting anisotropy, let alone designing models. We provide a tool chain to detect statistically anisotropy in planar shape and its preferred axis. For this we develop a new anisotropic growth model with a Procrustes‐type algorithm and a new parametric and non‐parametric neighbourhood hypothesis test, tunable to measurement accuracy. In application to fingerprint growth, we require only a standard fingerprint scanner and a minutiae matcher. Taking into account realistic distortions caused by pressing fingers on scanners, our simulations based on real data indicate that, for example, already in rather small samples (56 matches) we can significantly detect proximal–distal growth if it exceeds medial–lateral growth by only around 5%. Our method is well applicable to future data sets of child fingerprint time series. We provide an implementation of our algorithms and tests with matched minutiae pattern data.

show abstract

Dynamic Pore Filtering for Keypoint Detection Applied to Newborn Authentication

Cited by 13 publications

References 18 publications

Multiresolution synthetic fingerprint generation

Multiresolution synthetic fingerprint generation

PoreNet: CNN-based Pore Descriptor for High-resolution Fingerprint Recognition

Detecting Anisotropy in Fingerprint Growth

Contact Info

Product

Resources

About