Evangelia Micheli-Tzanakou

Measuring Information Content in Biometric Features

This chapter contains sections titled: Introduction Theoretical Framework Face Recognition Discussion References ]]>

Face Verification Based on Elastic Graph Matching

This chapter contains sections titled: Introduction The Elastic Graph Matching Algorithm Facial Region Modeling Discriminant Elastic Graph Matching Discriminant Graphs in Elastic Graph Matching Face Verification Performance of Elastic Graph Matching Conclusion References ]]>

Distributed Source Coding for Biometrics: A Case Study on Gait Recognition

This chapter contains sections titled: Introduction Related Work Overview of the Proposed System Gait Representation Distributed Source Coding for Gait Recognition Experimental Results Discussion Appendix A: Generalized Radon Transformations Appendix B: Orthogonal Discrete Transform Based on Krawtchouk Moments References

Privacy in Biometrics

This chapter contains sections titled: Introduction Biometric Traits and Privacy Biometric Templates Protection Privacy in Multimodal Systems An Exemplifying Scheme Conclusions References ]]>

Learning in Fingerprints

This chapter contains sections titled: Introduction Acquisition Preprocessing Feature Extraction Matching Fingerprint Classification Conclusion Acknowledgments References

A Comparison of Classification and IndexingBased Approaches for Fingerprint Identification

There are two kinds of biometric systems that use fingerprints for the personal identity: verification and identification. In a verification system, the input includes a query fingerprint and a known identity (ID), and the system verifies whether the ID is consistent with the input fingerprint. The output of a verification system is an answer of yes or no. In an identification system, the input only includes a query fingerprint, and the system tries to answer the following question: Are there any fingerprints in the database which resemble the query fingerprint? In this chapter, we are dealing with the identification problem. There are three kinds of approaches to solve the fingerprint identification problem: