Exploiting discriminant information in elastic graph matching

Zafeiriou, Stefanos; Tefas, Anastasios; Pitas, Ioannis

doi:10.1109/icip.2005.1530505

Cited by 10 publications

(3 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A new edges cost term forces that the difference in angle of the corresponding edges in the model and test graphs is below a threshold. Zafeiriou et al [11] used eigen-analysis to find the most discriminant features from the jets and proposed a new similarity measure for these. This work was subsequently extended in [12], by proposing a similarity measure that fuses the feature distance to nodes deformation.…”

Section: Related Workmentioning

confidence: 99%

Periocular biometrics: constraining the elastic graph matching algorithm to biologically plausible distortions

Proença

Briceño

2014

IET biom.

View full text Add to dashboard Cite

In biometrics research, the periocular region has been regarded as an interesting trade-off between the face and the iris, particularly in unconstrained data acquisition setups. As in other biometric traits, the current challenge is the development of more robust recognition algorithms. Having investigated the suitability of the 'elastic graph matching' (EGM) algorithm to handle nonlinear distortions in the periocular region because of facial expressions, the authors observed that vertices locations often not correspond to displacements in the biological tissue. Hence, they propose a 'globally coherent' variant of EGM (GC-EGM) that avoids sudden local angular movements of vertices while maintains the ability to faithfully model non-linear distortions. Two main adaptations were carried out: (i) a new term for measuring vertices similarity and (ii) a new term in the edges-cost function penalises changes in orientation between the model and test graphs. Experiments were carried out both in synthetic and real data and point for the advantages of the proposed algorithm. Also, the recognition performance when using the EGM and GC-EGM was compared, and statistically significant improvements in the error rates were observed when using the GC-EGM variant..

show abstract

Section: Related Workmentioning

confidence: 99%

Periocular biometrics: constraining the elastic graph matching algorithm to biologically plausible distortions

Proença

Briceño

2014

IET biom.

View full text Add to dashboard Cite

show abstract

“…The performance of face verification systems is measured in terms of the False Rejection Rate (FRR) achieved at a fixed False Acceptance Rate (FAR) [26,25]. There is a trade-off between FAR and FRR.…”

Section: Verification Experimentsmentioning

confidence: 99%

The Photoface database

Zafeiriou

Hansen

Atkinson

et al. 2011

CVPR 2011 Workshops

View full text Add to dashboard Cite

In this paper we present a new database suitable for both 2D and 3D face recognition based on photometric stereo, the so-called Photoface database. The Photoface database was collected using a custom-made four-source photometric stereo device that could be easily deployed in commercial settings. Unlike other publicly available databases the level of cooperation between subjects and the capture mechanism was minimal. The proposed device may also be used, to capture 3D expressive faces. Apart from the description of the device and the Photoface database, we present experiments from baseline face recognition and verification algorithms using albedo, normals and the recovered depth maps. Finally, we have conducted experiments in order to demonstrate how different methods in the pipeline of photometric stereo (i.e. normal field computation and depth map reconstruction methods) affect recognition/verification performance.

show abstract

“…This trade-off between the FAR and FRR can create a curve where FRR is plotted as a function of FAR (while altering the threshold value). This curve is called receiver operating characteristic (ROC) curve [28,30,29]. The performance of a verification system is often quoted by a particular operating point of the ROC curve where FAR = FRR.…”

Section: Experimental Validationmentioning

confidence: 99%

Facial behaviometrics: The case of facial deformation in spontaneous smile/laughter

Zafeiriou

Pantić

2011

CVPR 2011 Workshops

View full text Add to dashboard Cite

In this paper we explore the use of dense facial deformation in spontaneous smile/laughter as a biometric signature. The facial deformation is calculated between a neutral image (as neutral we define the least expressive image of the smile/laughter episode) and the apex of spontaneous smile/laughter (as apex we define the frame of the maximum facial change/deformation) and its complex representation is regarded. Subsequently, supervised and unsupervised complex dimensionality reduction techniques, namely the complex Principal Component Analysis (PCA) and the complex Linear Discriminant Analysis (LDA), are applied at the complex vector fields for feature extraction. We demonstrate the efficacy of facial deformation as a mean for person verification in a database of spontaneous smiles/laughters.

show abstract

Exploiting discriminant information in elastic graph matching

Cited by 10 publications

References 5 publications

Periocular biometrics: constraining the elastic graph matching algorithm to biologically plausible distortions

Periocular biometrics: constraining the elastic graph matching algorithm to biologically plausible distortions

The Photoface database

Facial behaviometrics: The case of facial deformation in spontaneous smile/laughter

Contact Info

Product

Resources

About