dc.contributorUniversidade Estadual Paulista (UNESP)
dc.creatorMarar, João Fernando
dc.creatorCoelho, Helder
dc.date2014-05-20T13:25:59Z
dc.date2014-05-20T13:25:59Z
dc.date2008-01-01
dc.date.accessioned2017-04-05T20:04:13Z
dc.date.available2017-04-05T20:04:13Z
dc.identifierHealthinf 2008: Proceedings of The First International Conference on Health Informatics, Vol 2. Setubal: Insticc-inst Syst Technologies Information Control & Communication, p. 99-106, 2008.
dc.identifierhttp://hdl.handle.net/11449/8308
dc.identifierWOS:000256698200020
dc.identifier.urihttp://repositorioslatinoamericanos.uchile.cl/handle/2250/856701
dc.descriptionIn this paper, we described how a multidimensional wavelet neural networks based on Polynomial Powers of Sigmoid (PPS) can be constructed, trained and applied in image processing tasks. In this sense, a novel and uniform framework for face verification is presented. The framework is based on a family of PPS wavelets,generated from linear combination of the sigmoid functions, and can be considered appearance based in that features are extracted from the face image. The feature vectors are then subjected to subspace projection of PPS-wavelet. The design of PPS-wavelet neural networks is also discussed, which is seldom reported in the literature. The Stirling Universitys face database were used to generate the results. Our method has achieved 92 % of correct detection and 5 % of false detection rate on the database.
dc.languageeng
dc.publisherInsticc-inst Syst Technologies Information Control & Communication
dc.relationHealthinf 2008: Proceedings of The First International Conference on Health Informatics, Vol 2
dc.rightsinfo:eu-repo/semantics/closedAccess
dc.subjectartificial neural network
dc.subjecthuman face verification
dc.subjectPolynomial Powers of Sigmoid (PPS)
dc.subjectwavelets functions
dc.subjectPPS-wavelet neural networks
dc.subjectactivation functions
dc.subjectfeedforward networks
dc.titleHuman face verification based on multidimensional Polynomial Powers of Sigmoid (PPS)
dc.typeOtro


Este ítem pertenece a la siguiente institución