An introduction evaluating biometric systems

Phillips, P. Jonathon; Martín, Alfonso Casas; Wilson, Charles L.; Przybocki, Mark A.

doi:10.1109/2.820040

Cited by 286 publications

(111 citation statements)

References 6 publications

Supporting

Mentioning

105

Contrasting

Unclassified

Order By: Relevance

“…It is essential that BISs are tested on biometric signatures not previously seen by the system (otherwise the system would only prove its ability to tune to a particular data set). In general, for an evaluation to be accepted by the biometric community, the details of the evaluation procedure must be known, as well as the evaluation protocol, performance results, and representative examples of the data set [54]. This way, information about testing should allow anyone to repeat the evaluation.…”

Section: A General Bis Modelmentioning

confidence: 99%

See 1 more Smart Citation

Biometric identification systems

et al. 2003

View full text Add to dashboard Cite

In this paper, we provide an overview of the fundamentals of biometric identiÿcation, together with a description of the main biometric technologies currently in use, all of them within a common reference framework. A comparison on di erent qualitative parameters of these technologies is also given, so that the reader may have a clear perspective of advantages and disadvantages of each. A section on multibiometrics describes the state of the art in making these systems work coordinately. Fusion at di erent conceptual levels is described. Finally, a section on commercial issues provides the reader a perspective of the main companies currently involved in this ÿeld. ?

show abstract

Section: A General Bis Modelmentioning

confidence: 99%

“…An important element for the adoption of biometric technologies is to establish the performance of individual biometric modalities and overall systems in a credible, objective and standard way [54,63,34]. In particular, the following issues should be considered:…”

Section: A General Bis Modelmentioning

confidence: 99%

Biometric identification systems

et al. 2003

View full text Add to dashboard Cite

show abstract

“…Typically, an evaluation protocol defines a set of data, how it should be used by a system to perform a set of experiments and how the performance of the system should be quantified [16]. The protocol should be designed in such a manner that no bias in the performance is introduced, e.g.…”

Section: Introductionmentioning

confidence: 99%

Face Verification Competition on the XM2VTS Database

Messer

Kittler

Sadeghi

et al. 2003

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. In the year 2000 a competition was organised to collect face verification results on an identical, publicly available data set using a standard evaluation protocol. The database used was the Xm2vts database along with the Lausanne protocol [14]. Four different institutions submitted results on the database which were subsequently published in [13]. Three years later, a second contest using the same dataset and protocol was organised as part of AVBPA 2003. This time round seven seperate institutions submitted results to the competition. This paper presents the results of the competition and shows that verification results on this protocol have increased in performance by a factor of 3.

show abstract

“…Therefore it was decided that a new database for the project would be recorded and a new experimental protocol using the database defined [6]. Typically, an evaluation protocol defines a set of data, how it should be used by a system to perform a set of experiments and how the performance of the system should be computed [11]. Hopefully, the protocol should of been designed in such a manner that there no bias in the performance is introduced, e.g.…”

Section: Introductionmentioning

confidence: 99%

The BANCA Database and Evaluation Protocol

Bailly-Bailliére

Bengio

Bimbot

et al. 2003

Lecture Notes in Computer Science

297

208

View full text Add to dashboard Cite

Abstract. In this paper we describe the acquisition and content of a new large, realistic and challenging multi-modal database intended for training and testing multi-modal verification systems. The BANCA database was captured in four European languages in two modalities (face and voice). For recording, both high and low quality microphones and cameras were used. The subjects were recorded in three different scenarios, controlled, degraded and adverse over a period of three months. In total 208 people were captured, half men and half women. In this paper we also describe a protocol for evaluating verification algorithms on the database. The database will be made available to the research community through http://www.ee.surrey.ac.uk/Research/VSSP/banca.

show abstract

An introduction evaluating biometric systems

Abstract: How and where biometric systems are deployed will depend on their performance. Knowing what to ask and how to decipher the answers can help you evaluate the performance of these emerging technologies.

Cited by 286 publications

References 6 publications

Biometric identification systems

Biometric identification systems

Face Verification Competition on the XM2VTS Database

The BANCA Database and Evaluation Protocol

Contact Info

Product

Resources

About