We propose to compute a vector eld, similar to the optical ow computed between successive frames of an image sequence, which maps optimally (in a certain sense) one face image onto another face image. A cost of the mapping is computed and used to quantify the dissimilarity between the two images. The technique is applied to the problem of person identiication by comparing an input face image to...

In this paper, we develop a perfectly competitive spatial equilibrium model in price and quantity variables in the presence of discriminatory ad valorem tariffs, a widely used trade policy instrument. We derive the equilibrium conditions and formulate them as a variational inequality problem. An algorithm is then proposed for the computation of the equilibrium pattern and convergence results es...

We discuss some techniques for preserving locality of reference in index spaces when mapped to memory units in a distributed memory architecture. In particular, we discuss the use of multidimensional address spaces instead of linearized address spaces, partitioning of irregular grids, and placement of partitions among nodes. We also discuss a set of communication primitives we have found very u...

This paper addresses the problem of developing efficient parallel algorithms for the training procedure of a neural network–based Fingerprint Image Comparison (FIC) system. The target architecture is assumed to be a coarse-grain distributed-memory parallel architecture. Two types of parallelism—node parallelism and training set parallel-ism (TSP)—are investigated. Theoretical analysis and exper...

A simplified model predictive control method is presented in this paper. This method is based on a future reference voltage vector for a three-phase four-leg voltage source inverter (VSI). Compared with the three-leg VSIs, the four-leg VSI increases the possible switching states from 8 to 16 owing to a fourth leg. Among the possible states, this should be considered in the model predictive cont...

The complexity of most machine learning techniques can be improved by transforming iterative components into their parallel equivalent. Although this parallelization has been considered in theory, few implementations have been performed on existing parallel machines. The parallel architecture of the Connection Machine provides a platform for the implementation and evaluation of parallel learnin...

with the huge global and wide range of attention placed upon quality, promoting and optimize the reliability of the products during the design process has turned out to be a high priority. in this study, the researcher have adopted one of the existing models in the reliability science and propose a bi-objective model for redundancy allocation in the series-parallel systems in accordance with th...