We propose a novel coupled mappings method for low resolution face recognition using deep convolutional neural networks (DCNNs). The proposed architecture consists of two branches of DCNNs to map the high and low resolution face images into a common space with nonlinear transformations. The branch corresponding to transformation of high resolution images consists of 14 layers and the other branch which maps the low resolution face images to the common space includes a 5layer super-resolution network connected to a 14-layer network. The distance between the features of corresponding high and low resolution images are backpropagated to train the networks. Our proposed method is evaluated on FERET data set and compared with state-of-the-art competing methods. Our extensive experimental evaluations show that the proposed method significantly improves the recognition performance especially for very low resolution probe face images (11.4% improvement in recognition accuracy). Furthermore, it can reconstruct a high resolution image from its corresponding low resolution probe image which is comparable with the state-of-the-art super-resolution methods in terms of visual quality.

Considering the competition in today's business environment, tactical planning of a supply chain becomes more complex than before. In many multi-product inventory systems, substitution flexibility can improve profits. This paper aims to prepare a comprehensive substitution inventory model, where an inventory system with two substitute products with ignorable lead time has been considered, and effects of simultaneous ordering have been examined. In this paper, demands of customers for both of the products have been regarded as stochastic parameters, and queuing theory has been used to construct a mathematical model. The model has been coded by C??, and it has been analyzed due to a real example, where the results indicate efficiency of proposed model.

No abstract

No abstract