Combining multiple matchers for a high security fingerprint verification system

@article{Jain1999CombiningMM,
  title={Combining multiple matchers for a high security fingerprint verification system},
  author={Anil K. Jain and Salil Prabhakar and Shaoyun Chen},
  journal={Pattern Recognit. Lett.},
  year={1999},
  volume={20},
  pages={1371-1379}
}

Figures from this paper

Experimental Results on Fusion of Multiple Fingerprint Matchers

Experimental results showed that such fusion of two or more matching algorithms can outperform the best individual verification algorithm and increase the discrimination between genuine and impostor classes.

Fusion of Multiple Matchers for Fingerprint Verification

This work proposes a methodology to fuse the decisions of multiple verification algorithms in order to increase the robustness and the performance of a fingerprint verification system.

Integration of Multiple Fingerprint Matching Algorithms

Results obtained on the FVC 2004 DB1-A database shows that a integration of the texture-based and minutiae-based matching scores leads to a substantial improvement in the overall matching performance.

Combining Fingerprint Matchers based on D-S Evidence Theory

A new framework that takes advantage of both minutiae and orientation field is proposed that can improve the performance of a fingerprint verification system.

Fingerprint Verification System – A Fusion Approach

Fingerprint recognition is done using minutiae extraction in time domain method and using Discrete Cosine Transform in frequency domain method to implement fingerprint recognition system using minimum resources for online application.

A Novel Highly Secured Session Based Data Encryption Technique Using Robust Fingerprint Based Authentication

The proposed approach using Session based password in addition to the features of the fingerprint for authentication shows significant promise and potential for improvement, compared with the other conventional authentication techniques with regard to efficiency of the process.

Investigation of fingerprint verification algorithm based on local centers method

  • E. Pólrolniczak
  • Computer Science, Physics
    Enhanced Methods in Computer Security, Biometric and Artificial Intelligence Systems
  • 2005
In this article method of minutia patterns matching using local centers is investigated and some results and conclusions are presented.

Fingerprint Verification System based on Active Forgery Techniques

Scale Invariant Feature Transform (SIFT) is extensively used for representation and extraction of features, and RANSAC algorithm is used for determining the matching area exactly.

Decision Level Fusion in Standardized Fingerprint Match-on-Card

  • Robert MuellerU. Martini
  • Computer Science
    2006 9th International Conference on Control, Automation, Robotics and Vision
  • 2006
A hybrid match-on-card algorithm that combines standardized templates from two different standards to make up a system with enhanced matching accuracy is designed.
...

References

SHOWING 1-10 OF 17 REFERENCES

FingerCode: a filterbank for fingerprint representation and matching

This work proposes a filter-based algorithm that uses a bank of Gabor filters to capture both the local and the global details in a fingerprint as a compact 640-byte fixed length FingerCode and shows identification accuracies comparable to the best results of minutiae-based algorithms published in the open literature.

On-Line Fingerprint Verification

An improved minutia extraction algorithm that is much faster and more accurate than an earlier algorithm has been implemented and an alignment-based elastic matching algorithms has been developed for minutian matching.

A Real-Time Matching System for Large Fingerprint Databases

The approach integrates a number of domain-specific high-level features such as pattern class and ridge density at higher levels of the search and incorporates elastic structural feature-based matching for indexing the database at the lowest level.

Methods of combining multiple classifiers and their applications to handwriting recognition

On applying these methods to combine several classifiers for recognizing totally unconstrained handwritten numerals, the experimental results show that the performance of individual classifiers can be improved significantly.

Biometrics, Personal Identification in Networked Society: Personal Identification in Networked Society

Biometrics: Personal Identification in Networked Society is an invaluable work for scientists, engineers, application developers, systems integrators, and others working in biometrics.

On multiple classifier systems for pattern recognition

  • T. HoJ. HullS. Srihari
  • Computer Science
    Proceedings., 11th IAPR International Conference on Pattern Recognition. Vol.II. Conference B: Pattern Recognition Methodology and Systems
  • 1992
Difficult pattern recognition problems involving large class sets and noisy input can be solved by a multiple classifier system, which allows simultaneous use of arbitrary feature descriptors and

Expert Conciliation for Multi Modal Person Authentication Systems by Bayesian Statistics

By using real data coming from a person authentication system using image and speech data, it is confirmed that the proposed supervisor improves the quality of individual expert decisions by reaching success rates of 99.5 %.

Decision Combination in Multiple Classifier Systems

This work proposes three methods based on the highest rank, the Borda count, and logistic regression for class set reranking that have been tested in applications of degraded machine-printed characters and works from large lexicons, resulting in substantial improvement in overall correctness.

A theoretical analysis of the application of majority voting to pattern recognition

  • L. LamC. Suen
  • Computer Science
    Proceedings of the 12th IAPR International Conference on Pattern Recognition, Vol. 3 - Conference C: Signal Processing (Cat. No.94CH3440-5)
  • 1994
The intention of this research is to analyze the foundations of the majority vote method in order to gain a deeper understanding and new results about its mode of operation.

Optimal combinations of pattern classifiers