Corpus ID: 18455123

NIST Special Database 10

  title={NIST Special Database 10},
  author={C. Watson},
This document describes the NIST fingerprint database, NIST Special Database 14. [...] Key Result The prints are 832 (w) X 768 (h) pixels (see Appendix A) and the storage required on each CD-ROM is approximately 670 megabytes when the prints are compressed and 11.5 gigabytes of storage when uncompressed (18 : 1 average compression ratio).Expand
A High Performance Fingerprint Matching System for Large Databases Based on GPU
A GPU fingerprint matching system based on MCC is presented that keeps its accuracy and reaches a speed-up up to 100.8× compared with a reference sequential CPU implementation and opens up a whole new field of possibilities for reliable real time fingerprint identification in large databases. Expand
A computationally efficient framework for large-scale distributed fingerprint matching
This research proposal intends to exploit and scale the best known minutiae matching algorithm for a minimum of sixty million fingerprints and design a framework for distributed database to deal with large fingerprint databases based on the results obtained in the former item. Expand
Fast fingerprint identification using GPUs
A new design of the minutiae based fingerprint matching algorithm presented by Jiang et al. is presented, specifically created for GPU based massively parallel architectures. Expand
Fingerprint Matching on GPU – A Review
Fingerprints are the biometric features usually used for identification. These can be characterized through some particular elements which are called as minutiae. The identification of a givenExpand
Distributed incremental fingerprint identification with reduced database penetration rate using a hierarchical classification based on feature fusion and selection
This paper proposes a complete identification system with a hierarchical classification framework that fuses the information of multiple feature extractors, leading to low identification times with small or no accuracy loss. Expand
Fingerprint card classification with statistical feature integration
A fingerprint classification algorithm is described for an automated fingerprint identification system with a large-size ten-print card database that determines a fingerprint's pattern category based on a ridge structure analysis and a direction-based neural network, and computes additional feature characteristics such as core-delta distance. Expand
A Multi-Classifier Approach to Fingerprint Classification
This paper explores the advantages of combining the MASKS and MKL-based classifiers, which are specifically designed for the fingerprint classification task, and proposes a combination at the ‘abstract level’ and a fusion at the 'measurement level' for continuous classification. Expand
Learning compact binary quantization of Minutia Cylinder Code
An optimization model is proposed to learn a feature projection matrix resulting in dimensionality reduction as well as diminishing quantization loss and shows that CBMCC is effective and discriminative as it has maximum intra-bit variance while minimum inter-bit correlation. Expand
Liveness Detection in Biometrics
Results show that it is possible to obtain results comparable or even better than the state-ofthe-art ones, using other iris and fingerprint databases, but that does not occur for every database tested, which proves thatit is still necessary to improve or maybe combine the algorithms, so that the classification error rate drops. Expand
Distortion-tolerant filter for elastic-distorted fingerprint matching
This paper gives results for using distortion tolerant filters to improve performance of fingerprint correlation matching, and shows performance was improved from 49% correct, using one training fingerprint, to 100%correct, using multiple training fingerprints, and a distortion- tolerant MINACE filter, with no false alarms. Expand


Design and Collection of a Handwriting Sample Image Database
NIST, under sponsorship from the Bureau of the Census, has collected a database consisting of 2,100 pages of binary image data of handprinted characters including numerals and text that can be applied to any discipline requiring the use of image archives. Expand