Detail publikace

3D face recognition based on the hierarchical score-level fusion classifiers

Originální název

3D face recognition based on the hierarchical score-level fusion classifiers

Anglický název

3D face recognition based on the hierarchical score-level fusion classifiers

Jazyk

en

Originální abstrakt

This paper describes the 3D face recognition algorithm that is based on the hierarchical score-level fusion classifiers. In a simple (unimodal) biometric pipeline, the feature vector is extracted from the input data and subsequently compared with the template stored in the database. In our approach, we utilize several feature extraction algorithms. We use 6 different image representations of the input 3D face data. Moreover, we are using Gabor and Gauss-Laguerre filter banks applied on the input image data that yield to 12 resulting feature vectors. Each representation is compared with corresponding counterpart from the biometric database. We also add the recognition based on the iso-geodesic curves. The final score-level fusion is performed on 13 comparison scores using the Support Vector Machine (SVM) classifier.

Anglický abstrakt

This paper describes the 3D face recognition algorithm that is based on the hierarchical score-level fusion classifiers. In a simple (unimodal) biometric pipeline, the feature vector is extracted from the input data and subsequently compared with the template stored in the database. In our approach, we utilize several feature extraction algorithms. We use 6 different image representations of the input 3D face data. Moreover, we are using Gabor and Gauss-Laguerre filter banks applied on the input image data that yield to 12 resulting feature vectors. Each representation is compared with corresponding counterpart from the biometric database. We also add the recognition based on the iso-geodesic curves. The final score-level fusion is performed on 13 comparison scores using the Support Vector Machine (SVM) classifier.

BibTex


@inproceedings{BUT111533,
  author="Štěpán {Mráček} and Jan {Váňa} and Karolína {Kupková} and Martin {Drahanský} and Michal {Doležel}",
  title="3D face recognition based on the hierarchical score-level fusion classifiers",
  annote="This paper describes the 3D face recognition algorithm that is based on the
hierarchical score-level fusion classifiers. In a simple (unimodal) biometric
pipeline, the feature vector is extracted from the input data and subsequently
compared with the template stored in the database. In our approach, we utilize
several feature extraction algorithms. We use 6 different image representations
of the input 3D face data. Moreover, we are using Gabor and Gauss-Laguerre filter
banks applied on the input image data that yield to 12 resulting feature vectors.
Each representation is compared with corresponding counterpart from the biometric
database. We also add the recognition based on the iso-geodesic curves. The final
score-level fusion is performed on 13 comparison scores using the Support Vector
Machine (SVM) classifier.",
  address="SPIE - the international society for optics and photonics",
  booktitle="Proceedings of Biometric and Surveillance Technology for Human and Activity Identification XI, Vol. 9075",
  chapter="111533",
  doi="10.1117/12.2050547",
  edition="NEUVEDEN",
  howpublished="print",
  institution="SPIE - the international society for optics and photonics",
  year="2014",
  month="june",
  pages="1--12",
  publisher="SPIE - the international society for optics and photonics",
  type="conference paper"
}