From a theoretical point of view, Hidden Markov Models (HMMs) and Dynamic Bayesian Networks (DBNs) are similar, still in practice they pose different challenges and perform in a different manner. In this study we present a comparative analysis of the two spatial-temporal classification methods: HMMs and DBNs applied to the Facial Action Units (AUs) recognition problem. The Facial Action Coding System (FACS) developed by Ekman and Friesen decomposes the face into 46 AUs, each AU being related to the contraction of one or more specific facial muscles. FACS proved its applicability to facial behavior modeling, enabling the recognition of an extensive palette of facial expressions. Even though a lot has been published on this theme, it is still difficult to draw a conclusion regarding the best methodology to follow, as there is no common basis for comparison and sometimes no argument is given why a certain classification method was chosen. Therefore, our main contributions reside in discussing and comparing the relative performance of the two proposed classifiers (HMMs vs. DBNs) and also of different Region of Interest (ROI) selections proposed by us and different optical flow estimation methods. We can consider our automatic system towards AUs classification an important step in the facial expression recognition process, given that even one emotion can be expressed in different ways, fact that suggests the complexity of the analyzed problem. The experiments were performed on the Cohn-Kanade database and showed that under the same conditions regarding initialization, labeling, and sampling, both classification methods produced similar results, achieving the same recognition rate of 89% for the classification of facial AUs. Still, by enabling non-fixed sampling and using HTK, HMMs rendered a better performance of 93% suggesting that they are better suited for the special task of AUs recognition.
Representatives of Ligophorus Euzet et Suriano, 1977 were found on the gills of Mugil liza Valenciennes caught in southern Brazil. They were identified as Ligophorus uruguayense Failla Siquier et Ostrowski de Núñez, 2009 and Ligophorus saladensis Marcotegui et Martorelli, 2009, even though specific identification proved to be difficult due to inconsistencies in some diagnostic features reported for these two species. Therefore, a combined morphological and molecular approach was used to critically review the validity of these species, by means of phase contrast and confocal fluorescence microscopical examination of sclerotised hard parts, and assessing the genetic divergence between L. saladensis, L. uruguayense and their congeners using rDNA sequences. The main morphological differences between the two species relate to the shape of the accessory piece of the penis and the median process of the ventral bar. The accessory piece in L. uruguayense is shorter than in L. saladensis, has a cylindrical, convex upper lobe and straight lower lobe (vs with the distal tip of the lower lobe turning away from the upper lobe in the latter species). The ventral bar has a V-shaped anterior median part in L. uruguayense (vs U-shaped in L. saladensis). The two species are suggested to be part of a species complex together with L. mediterraneus Sarabeev, Balbuena et Euzet, 2005. We recommend to generalise such comparative assessment of species of Ligophorus for a reliable picture of the diversity and diversification mechanisms within the genus, and to make full use of its potential as an additional marker for mullet taxonomy and systematics., Natalia C. Marchiori, Antoine Pariselle, Joaber Pereira Jr., Jean-François Agnèse, Jean-Dominique Durand, Maarten P.M. Vanhove., and Obsahuje bibliografii