نشریه مهندسی برق و مهندسی کامپیوتر ایران
سال نهم شماره 1 (پیاپی 25، بهار 1390)

Face recognition via thermal infrared images is a modern recognition method. It has been so interesting for many researchers during last ten years. This method which operates via thermal features and the situation of human face vessels has much more benefits than visual-based methods. In these images, the effect of environmental lights changes, which is one of the most important obstacles of face recognition via visual images, is totally eliminated. The most important face recognition problem via thermal infrared images is the existence of diffusion obstacles like glasses and beard, which block the exact extraction of the situation of face vessels. Considering the suggested algorithm, these problems have been completely solved. In this paper face recognition is done through face vessels. For extraction of the face features, the situation of vessel branches is used. Also by choosing appropriate classification, fake vessels and false branches has been omitted. On the other hand, the best feature is extracted by using Dynamic Time Wrapping algorithm which is resistant to nonlinear changes. The simulation on UTK-IRIS gallery set has showed the accurate recognition rate 95% on the images with glasses and 88% on the images with beard, so the proposed method has improved the recognition rate about 10% and 44% respectively on same gallery set compared with the best other works.

In this article, for the purpose of improving neural network models applied in face recognition using single image per person, a bidirectional neural network inspired of neocortex functional model is presented. In the proposed model, recognition is not performed in a single stage, but via two bottom-up and top-down phases and the recognition results of first stage is used for model adaptation. We have applied this novel adapting model in combination with clustering person and pose information technique to separate person and pose information and to estimate corresponding manifolds. To increase the number of training samples in the classifier neural network, virtual views of frontal images in the test dataset are synthesized using estimated manifolds. Training classifier network via virtual images obtained from bidirectional network, gives an accuracy rate of 85.45% on the test dataset which shows 1.82% improvement in accuracy of face recognition compared to training classifier with virtual images obtained from clustering person and pose information network.

Variation of Light intensity and its direction have been the main challenges in many face recognition systems that lead to the different normal and abnormal shadows. Today, various methods are presented for face recognition under different lighting conditions which require previous knowledge about Light source and the angle of radiation as well. In this paper, a new approach is proposed to extract the knowledge of/about the lighting angle/direction in face images based on learning techniques. At First, some effective coefficients on lighting variation are extracted on DCT domain. They will be used to determine lighting classes after normalization. Then, three different learning algorithms, Decision tree, SVM, and WAODE (Weightily Averaged One-Dependence Estimators) are used to learn the lighting classes. The algorithms have been tested on the well known YaleB and Extended Yale face databases. The comparative results indicate that the SVM achieves the best average accuracy for classification. On the other hand, WAODE Bayesian approach attains the better accuracy in classes with large lighting angle because of its resistance against data loss.

In this paper, an intelligent feature selection method for recognition of Persian handwritten digits is presented. The fitness function associated with the error in the Persian handwritten digits recognition system is minimized, by selecting the appropriate features, using binary gravitational search algorithm. Implementation results show that the use of intelligent methods is well able to choose the most effective features for this recognition system. The results of the proposed method in comparison with other similar methods based on genetic algorithm and binary particle method of optimizing indicates the effective performance of the proposed method.

An ISO is responsible for responsible for keeping system security within its specified limits. Rapid demand increase on one hand and less investment on transmission system and the other hand, have resulted in more stress on existing transmission grids. Therefore, various types of stability should be monitored and controlled. The small signal stability (SSS) is a type which may be improved using power system stabilizers (PSS). In this paper, though using the non-dominated sorting genetic algorithm version II (NSGA-II), it is, initially, shown how the PSSs may affect the generation cost as well as the SSS. Moreover, the service provided by PSSs is introduced as an ancillary service. A cost allocation framework is prospect in which the PSS owners are properly paid for their services provided.

In this paper a novel direct torque control algorithm based on switching table using three-level diode clamp inverter is introduced. Voltage deviation of DC link capacitors is one of the most significant problems of NPC three-level voltage source inverters. The voltage imbalance of DC link capacitors will result in low level harmonics, undesirable torque variation and motor efficiency reduction. To resolve this problem, a closed loop algorithm is introduced in this paper, in addition to its simple implementation; the algorithm is able to control the voltage fluctuation of DC link capacitors within the desirable limits. The result of simulation and experimental implementation confirms the performance of this method despite capacitors reduced capacity.