Open AccessFiducial Points Detection Using SVM Linear Classifiers
Author(s) -
Luiz Eduardo S. e Silva,
Pedro Donadio de T.,
Kenny Santos,
S. S. Waldir
Publication year - 2014
Language(s) - English
Resource type - Conference proceedings
DOI - 10.5121/csit.2014.4403
Subject(s) - support vector machine , fiducial marker , computer science , artificial intelligence , pattern recognition (psychology) , random subspace method , machine learning
Currently, there is a growing interest from the sci\udentific and/or industrial community in respect \udto methods that offer solutions to the problem of fi\udducial points detection in human faces. Some \udmethods use the SVM for classification, but we obser\udved that some formulations of optimization \udproblems were not discussed. In this article, we pr\udopose to investigate the performance of \udmathematical formulation C-SVC when applied in fiduc\udial point detection system. Futhermore, \udwe explore new parameters for training the proposed\ud system. The performance of the proposed \udsystem is evaluated in a fiducial points detection p\udroblem. The results demonstrate that the \udmethod is competitiv