-
Multimedia Content Representation, Classification and Security, International Workshop, MRCS 2006, Istanbul, Turkey, September 11-13, 2006, Proceedings; 01/2006
-
[show abstract]
[hide abstract]
ABSTRACT: Reliable verification and identification can be achieved by fusing hard and soft information from multiple classifiers. Correlation filter based classifiers have shown good performance in biometric verification applications. In this paper, we develop a method of fusing soft information from multiple correlation filters. Usually, correlation filters are designed to produce a strong peak in the correlation filter output for authentics whereas no such peak should be produced for impostors. Traditionally, the peak-to-sidelobe-ratio (PSR) has been used to characterize the strength of the peak and thresholds are set on the PSR in order to determine whether the test image is an authentic or an impostor. In this paper, we propose to fuse multiple correlation output planes, by appending them for classification by a Support Vector Machine (SVM), to improve the performance over traditional PSR based classification. Multiple Unconstrained Optimal Tradeoff Synthetic Discriminant Function (UOTSDF) filters having varying degrees of discrimination and distortion tolerance are employed here to create a feature vector for classification by a SVM, and this idea is evaluated on the plastic distortion set of the NIST 24 fingerprint database. Results on this database provide an Equal Error Rate (EER) of 1.36% when we fuse correlation planes, in comparison to an average EER of 3.24% using the traditional PSR based classification from a filter, and 2.4% EER on fusion of PSR scores from the same filters using SVM, which demonstrates the advantages of fusing the correlation output planes over the fusion of just the peak-to-sidelobe-ratios (PSRs).© (2005) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.
03/2005;
-
IEEE Transactions on Systems, Man, and Cybernetics, Part C. 01/2005; 35:411-418.
-
Pattern Recognition and Image Analysis, Third International Conference on Advances in Pattern Recognition, ICAPR 2005, Bath, UK, August 22-25, 2005, Proceedings, Part II; 01/2005
-
[show abstract]
[hide abstract]
ABSTRACT: Weinvestigated the performance of 3 face verification algorithms (Correlation Filters, Individual PCA, FisherFaces) on an
image database that was collected by a cell phone camera. Cell phone camera images tend to be of poorer quality and because
of their portability, algorithms must deal with scale changes and dynamic outdoor illumination changes. While Individual PCA
and FisherFaces focus on the image domain, Correlation Filters work in the frequency domain and offer advantages such as shift-invariance,
ability to accommodate in-class image variability and closed form expressions. Results suggest that correlation filters offer
better verification performance with this database.
07/2004: pages 74-80;
-
[show abstract]
[hide abstract]
ABSTRACT: Using biometrics for subject verification can significantly improve security over that of approaches based on passwords and personal identification numbers, both of which people tend to lose or forget. In biometric verification the system tries to match an input biometric (such as a fingerprint, face image, or iris image) to a stored biometric template. Thus correlation filter techniques are attractive candidates for the matching precision needed in biometric verification. In particular, advanced correlation filters, such as synthetic discriminant function filters, can offer very good matching performance in the presence of variability in these biometric images (e.g., facial expressions, illumination changes, etc.). We investigate the performance of advanced correlation filters for face, fingerprint, and iris biometric verification.
Applied Optics 02/2004; 43(2):391-402. · 1.41 Impact Factor
-
Biometric Authentication, First International Conference, ICBA 2004, Hong Kong, China, July 15-17, 2004, Proceedings; 01/2004
-
[show abstract]
[hide abstract]
ABSTRACT: Biometric verification refers to the process of matching an input biometric to stored biometric information. In particular, biometric verification refers to matching the live biometric input from an individual to the stored biometric template of that individual. Examples of biometrics include face images, fingerprint images, iris images, retinal scans, etc. Thus, image processing techniques prove useful in biometric recognition. In particular, composite correlation filters have proven to be effective. In this paper, we will discuss the application of composite correlation filters to biometric verification.© (2003) COPYRIGHT SPIE--The International Society for Optical Engineering. Downloading of the abstract is permitted for personal use only.
08/2003;
-
Audio-and Video-Based Biometrie Person Authentication, 4th International Conference, AVBPA 2003, Guildford, UK, June 9-11, 2003 Proceedings; 01/2003
-
[show abstract]
[hide abstract]
ABSTRACT: In this paper we investigate the use of correlation filters for fingerprint verification. Correlation filters have advantages In this paper we investigate the use of correlation filters for fingerprint verification. Correlation filters have advantages
such as their built-in shift invariance, closed form expressions, graceful degradation, and their ability to trade off discrimination such as their built-in shift invariance, closed form expressions, graceful degradation, and their ability to trade off discrimination
for distortion tolerance. The NIST Special Database 24 is used here to evaluate fingerprint verification performance in the for distortion tolerance. The NIST Special Database 24 is used here to evaluate fingerprint verification performance in the
presence of distortions. presence of distortions.
12/2002: pages 1056-1056;
