Neural network classifying method is used in this work to perform facial expression recognition. The processed expressions were the six most pertinent facial expressions and the neutral one. This operation was implemented in three steps. First, a neural network, trained using Zernike moments, was applied to the set of the well known Yale and JAFFE database images to perform face detection. In the second step, detected faces are processed to perform the characterization phase through computed vectors of Zernike moments. At last step, a back propagation neural network was trained to distinguish between the seven emotion's states of a presented face. Finally, method performances were evaluated on the well known JAFEE and YALE database.

Face localization using neural network is presented in this communication. Neural network was trained with two different kinds of feature parameters vectors; Zernike moments and eigenfaces. In each case, coordinate vectors of pixels surrounding faces in images were used as target vectors on the supervised training procedure. Thus, trained neural network provides on its output layer a coordinate's vector (rho,thetas) representing pixels surrounding the face contained in treated image. This way to proceed gives accurate faces contours which are well adapted to their shapes. Performances obtained for the two kinds of training feature parameters were recorded using a quantitative measurement criterion according to experiments carried out on the XM2VTS database.

Facial expression recognition became an important research subject for its diverse applications in human machine interaction. However, many challenges still to be overcome. By the presented work in this paper, we try to provide a new facial expression recognition technique based on combined vectors of multi-feature characterisation of the face. Thus, the face within an image is firstly localised using a simplified method, then it will be characterised in three different ways; by obtaining its Zernike moments feature vectors, known to compact geometric characteristics of the image, then by compiling AR model, supposed to be a representation of its spectral source model and at last, a statistical distribution analysis of the luminance information is performed through the LBP method. Obtained feature vectors were used to train neural network classifiers (NNC) in different manner. To demonstrate the effectiveness of the proposed technique, we record and compare recognition rates for NNC trained with each type of feature vector firstly, then for NNC trained with directly combined feature vectors and finally for NNC trained with composite feature vectors which underwent a fuzzy linear projection operation. Experiments were performed on the JAFFE and Yale database. Recorded results along with comparisons to other methods have affirmed the potency of the proposed approach attaining promising results compared to those reported in the literature.

Face recognition became a daily discipline in human life. At the work, with our PDP and smart phones, for our daily help, our security and many other utilities, face recognition has crossed the laboratory doors and colonized the human quotidian. However, the effectiveness of the developed applications still encounters many challenges. The presented work in this paper tries to deal with these challenges by proposing an advanced characterization way to enrich the feature vectors used by the classifiers to verify or identify faces. This process was done by compiling three types of feature vectors. Each type encapsulates a specific type of face information. At first, we compile a feature vector related to the geometric information of the face using Zernike moments; then spectral components using DCT are extracted to form the second type of feature vectors and finally, the last feature vector type is formed by compiling the texture and luminance information using LBP. The three vector types are then combined to form an enriched feature vector which was post-processed through a feature selection method then presented to the input of a neural network classifier. The validation experiments were realized on the XM2VTS and ORL database and recognition rates of 93.3% and 92.5% were respectively recorded for XM2VTS and ORL database.

DC-to-DC converters are Today widely used in power conversion systems that demand a continuous source and a continuous output, and the most prominent of these systems is the photovoltaic panels system, where dc-dc converters have become an integral part of this application, thanks to the advantages offered by dc-dc converters in this application as stability The system and performance improvement, as well as raising or lowering the output voltage compared to the input voltage, and increase the efficiency of the system and achieve the maximum power point that can be produced from photovoltaic panels by application of MPPT in addition to the ability to provide a fixed output voltage in the case of a variable input voltage due to natural factors such as a change in radiation and temperature. In this study, we describe Buck, Boost, Buck-Boost, CUK, and Zeta Converters, which are the most significant non-isolated DC-DC Converters that are frequently utilized in solar energy systems. This paper also provides an overview of recent studies for each converter; we also present a comparison between these converters, highlighting the most notable benefits and drawbacks of each converter.