No abstract

In computer vision, automatic facial expression recognition (FER) continued a difficult and interesting topic. The majority of extant techniques are based on traditional features descriptors such as local binary pattern (LBP) and histogram of oriented gradient (HOG), in which the classifier's hyperparameters are tailored to produce the best recognition accuracies across a single database or a small set of similar databases. This paper integrates the power of deep learning techniques with the LBP and HOG. The LBP and HOG are estimated from each image in the dataset. The resulting dataset is applied to a convolutional neural network (CNN). The architecture of this CNN constitutes three convolutional layers and three max-pooling layers. The output layers involve BatchNormalization, three dense layers, and two dropout layers. The proposed architecture is validated on the extended cohn-kanade dataset (CK+). We obtain improvement in the accuracy of the CNN model from 0.9593 to 0.967 and 0.975 after using the LBP and HOG respectively.

Image classification is an extensively researched sub-fields of computer vision implemented in face recognition, self-driving, medical image segmentation, biological identification, and others. Traditional models of image classification require manual construction of feature extraction techniques and classification accuracy which are closely associated with these utilized techniques. During the rapid progress of multimedia technologies, the number of images that require classification got bigger, and this led to making image classification more complicated, hence, the manual construction of feature extraction techniques consumes more time and provides lower accuracy. In the recent decade, deep learning-based models have appeared in various applications. These models hold the merits of an effective extraction of image features, low-weight features filtering, a large capacity for processing, and higher classification speed and accuracy. Thus, lots of researchers have attempted to utilize deep learning algorithms, especially convolutional neural networks (CNNs) for image classification. Therefore, this paper concentrates on providing an abbreviated review of deep learning-based image classification models, by covering the recently utilized deep learning algorithms, comparing various related works and benchmark datasets mentioned in this paper, and summarizing the fundamental analysis and discussion.

The use of recycled materials as one of the great results for the industrial raw materials shortage may face serious problems during the mold casting process. This paper researches the difference in solidification step between the edges and the center of the aluminum recycled cast. The implementation of such research passes through two verification steps; the removal of the chemical dyes and then to melt the recycled aluminum cans in a ceramic container in order to produce the metallic 60 x 13cm mold. Six thermocouples are inserted on the casting edges and the center and liked directly to a computer system in order to simultaneously record the temperature readings from the start of the cooling/solidification process. The Artificial Neural Network ANN approach is applied to the recorded data via the utilization of the software MATLAB in order to analyze the cooling curves and determine the mathematical representation of the solidification layers through the casting. The interior layers microstructure is examined via SPECTROPORT mobile metal analyzer so as to detect the solidification trend through the examined ingots. The edges of the casting are shown to solidify more quickly than the central region and also it is demonstrated via the microstructural samples that the boundaries are more clear in the center than these at the edges.

Modern industrial projects face many challenges in order to sustain their productivity in a capital effective manner. Operational costs and production lines maintenance policy is on the top factors that play critical roles in that challenge. Linear programming is utilized in this paper to examine the possible minimization of the operational cost and determine an effective optimal maintenance policy for middle-sized furniture manufacturing plant in Baghdad city, taking under consideration all alternatives, non-sensitivity, and solidness. A mixture of Markov decision processes and linear programming analysis is implemented for the actual site and operational data to help decision-makers in planning for their project’s mid and long term maintenance policy and performing Solidness and, as result, the tentative cost reduction scheme.