Pores and Ridges: High-Resolution Fingerprint Matching Using Level 3 Features

By Anil K. Jain, Yi Chen, Meltem Demirkus. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2007

574 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Safety Research, Signal Processing

View Paper: https://www.semanticscholar.org/paper/a4bc8a05aafc549cab0e2ddc30028232bec1d5f0

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Safety Research

In Signal Processing

Citations in the corpus

Automated human identification using ear imaging (2012, background): “7 illustrates set of such automatically normalized, segmented and enhanced ear images employed for the feature extraction and classification.”
Human Identification Using Finger Images (2012, background): “In addition to fingerprint features [19], the palmprint [27], finger knuckle [15] and hand geometry [1] acquired in visible illumination, and palm-vein features acquired from near-infrared [35] and far-infrared [33] imaging have invited lot of attention from researchers and developers over the last…”
Fingerprint Liveness Detection Using Convolutional Neural Networks (2016, methodology): “There are techniques such as those in [2] and [9], in which the”
A Review of Fingerprint Feature Representations and Their Applications for Latent Fingerprint Identification: Trends and Evaluation (2019, background): “Finally, other authors [44], [89], [94] have reported fingerprint feature representation with level 3 features.”
Fingermarks, more than just a ridge pattern (2014, methodology): “Level three features are also described as unique and immutable and can therefore be used in the identification process [4].”
Quality-augmented fusion of level-2 and level-3 fingerprint information using DSm theory (2009, unknown): “Researchers have proposed fingerprint recognition algorithms which use level-3 features such as ridge counts and sweat pores for matching [5–8] but very limited research has been undertaken to scientifically analyze the effectiveness of combining level-2 and level-3 features [9].”