hrcak mascot   Srce   HID

Izvorni znanstveni članak
https://doi.org/10.2498/cit.1002412

Differential Evolution to Optimize Hidden Markov Models Training: Application to Facial Expression Recognition

Khadoudja Ghanem   ORCID icon orcid.org/0000-0003-4401-4554 ; MISC Laboratory, Constantine 2 University, Constantine, Algeria
Amer Draa ; MISC Laboratory, Constantine 2 University, Constantine, Algeria
Elvis Vyumvuhore ; MISC Laboratory, Constantine 2 University, Constantine, Algeria
Arsène Simbabawe ; MISC Laboratory, Constantine 2 University, Constantine, Algeria

Puni tekst: engleski, pdf (541 KB) str. 157-170 preuzimanja: 484* citiraj
APA 6th Edition
Ghanem, K., Draa, A., Vyumvuhore, E. i Simbabawe, A. (2015). Differential Evolution to Optimize Hidden Markov Models Training: Application to Facial Expression Recognition. Journal of computing and information technology, 23 (2), 157-170. https://doi.org/10.2498/cit.1002412
MLA 8th Edition
Ghanem, Khadoudja, et al. "Differential Evolution to Optimize Hidden Markov Models Training: Application to Facial Expression Recognition." Journal of computing and information technology, vol. 23, br. 2, 2015, str. 157-170. https://doi.org/10.2498/cit.1002412. Citirano 21.10.2020.
Chicago 17th Edition
Ghanem, Khadoudja, Amer Draa, Elvis Vyumvuhore i Arsène Simbabawe. "Differential Evolution to Optimize Hidden Markov Models Training: Application to Facial Expression Recognition." Journal of computing and information technology 23, br. 2 (2015): 157-170. https://doi.org/10.2498/cit.1002412
Harvard
Ghanem, K., et al. (2015). 'Differential Evolution to Optimize Hidden Markov Models Training: Application to Facial Expression Recognition', Journal of computing and information technology, 23(2), str. 157-170. https://doi.org/10.2498/cit.1002412
Vancouver
Ghanem K, Draa A, Vyumvuhore E, Simbabawe A. Differential Evolution to Optimize Hidden Markov Models Training: Application to Facial Expression Recognition. Journal of computing and information technology [Internet]. 2015 [pristupljeno 21.10.2020.];23(2):157-170. https://doi.org/10.2498/cit.1002412
IEEE
K. Ghanem, A. Draa, E. Vyumvuhore i A. Simbabawe, "Differential Evolution to Optimize Hidden Markov Models Training: Application to Facial Expression Recognition", Journal of computing and information technology, vol.23, br. 2, str. 157-170, 2015. [Online]. https://doi.org/10.2498/cit.1002412

Sažetak

The base system in this paper uses Hidden Markov Models (HMMs) to model dynamic relationships among facial features in facial behavior interpretation and understanding field. The input of HMMs is a new set of derived features from geometrical distances obtained from detected and automatically tracked facial points. Numerical data representation which is in the form of multi-time series is transformed to a symbolic representation in order to reduce dimensionality, extract the most pertinent information and give a meaningful representation to humans. The main problem of the use of HMMs is that the training is generally trapped in local minima, so we used the Differential Evolution (DE) algorithm to offer more diversity and so limit as much as possible the occurrence of stagnation. For this reason, this paper proposes to enhance HMM learning abilities by the use of DE as an optimization tool, instead of the classical Baum and Welch algorithm. Obtained results are compared against the traditional learning approach and significant improvements have been obtained.

Ključne riječi
facial expressions; occurrence order; Hidden Markov Model; Baum-Welch; optimization; differential evolution

Hrčak ID: 139793

URI
https://hrcak.srce.hr/139793

Posjeta: 691 *