A mixture of gated experts optimized using simulated annealing for 3D face recognition

Abstract : A commonly accepted fact in the biometrics related domain is that fusing multiple classifiers to make decisions general-ly leads to improved classification performance. Meanwhile, the search for an optimal fusion scheme remains extraordi-narily complex because the cardinality of the space of poss-ible combination strategies is exponentially proportional to the number of competing classifiers. This paper proposes a mixture of gated experts for the application of 3D face rec-ognition using an ensemble of 24 different scores. The mix-ture of gated experts is optimized by a Simulated Annealing (SA) based algorithm, and it automatically selects and fuses the most relevant similarity measures. Experimental results of 3D face recognition on the FRGC v2.0 database demon-strate the performance and stability of the proposed method. Moreover, as a learning-based approach, it also has a good robustness to the variations of training database.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01354439
Contributor : Équipe Gestionnaire Des Publications Si Liris <>
Submitted on : Thursday, August 18, 2016 - 7:27:34 PM
Last modification on : Wednesday, November 20, 2019 - 3:02:07 AM

Identifiers

Citation

Wael Ben Soltana, Di Huang, Mohsen Ardabilian, Liming Chen, Chokri Ben-Amar. A mixture of gated experts optimized using simulated annealing for 3D face recognition. IEEE International Conference on Image Processing (ICIP), Sep 2011, Brussels, Belgium. pp.3037-3040, ⟨10.1109/ICIP.2011.6116304⟩. ⟨hal-01354439⟩

Share

Metrics

Record views

244