Convolutional neural network with joint stepwise character/word modeling based system for scene text recognition

Multimedia Tools and Applications - Text recognition in the wild is a challenging task in the field of computer vision and machine learning. Existing optical character recognition engines cannot...     

Introduction

The Journal of Supercomputing -     

An element-based formulation for ES-FEM and FS-FEM models for implementation in standard solid mechanics finite element codes for 2D and 3D static analysis

Edge-based and face-based smoothed finite element methods (ES-FEM and FS-FEM, respectively) are modified versions of the finite element method allowing to achieve more accurate results and to reduce sensitivity to mesh distortion, at least for linear elements. These properties make the two methods very attractive. However, their implementation in a standard finite element code is nontrivial because it requires heavy and extensive modifications to the code architecture. In this article, we present an element-based formulation of ES-FEM and FS-FEM methods allowing to implement the two methods in a standard finite element code with no modifications to its architecture. Moreover, the element-based formulation permits to easily manage any type of element, especially in 3D models where, to the best of the authors' knowledge, only tetrahedral elements are used in FS-FEM applications found in the literature. Shape functions for non-simplex 3D elements are proposed in order to apply FS-FEM to any standard finite element.     

Decision Bayes Criteria for Optimal Classifier Based on Probabilistic Measures

This paper addresses the high dimension sample problem in discriminate analysis under nonparametric and supervised assumptions.Since there is a kind of equivalence between the probabilistic dependence measure and the Bayes classification error probability,we propose to use an iterative algorithm to optimize the dimension reduction for classification with a probabilistic approach to achieve the Bayes classifier.The estimated probabilities of different errors encountered along the different phases of the system are realized by the Kernel estimate which is adjusted in a means of the smoothing parameter.Experiment results suggest that the proposed approach performs well.     

Optimization of nutrient-induced germination of Bacillus sporothermodurans spores using response surface methodology

Spores of Bacillus sporothermodurans are known to be contaminant of dairy products and to be extremely heat-resistant. The induction of endospore germination before a heat treatment could be an efficient method to inactivate these bacteria and ensure milk stability. In this study, the nutrient-induced germination of B. sporothermodurans LTIS27 spores was studied. Testing the effect of 23 nutrient elements to trigger an important germination rate of B. sporothermodurans spores, only d-glucose, l-alanine, and inosine were considered as strong independent germinants. Both inosine and l-alanine play major roles as co-germinants with several other amino acids. A central composite experimental design with three factors (l-alanine, d-glucose, and temperature) using response surface methodology was used to optimize the nutrient-induced germination. The optimal rate of nutrient-induced germination (100%) of B. sporothermodurans spores was obtained after incubation of spore for 60 min at 35 °C in presence of 9 and 60 mM of d-glucose and l-alanine, respectively. The results in this study can help to predict the effect of environmental factors and nutrients on spore germination, which will be beneficial for screening of B. sporothermodurans in milk after induction their germination. Moreover, the chosen method of optimization of the nutrient-induced germination was efficient in finding the optimum values of three factors.     

Study of the Mechanical Properties of Fibers Extracted from Tunisian Agave americana L.

Agave americana L. fibers, the most abundant variety in Tunisia, have a quite important textile potential. This potential is demonstrated by studying the extraction of these fibers from leaves, their physical properties such us fineness or density and their mechanical behavior in tensile tests. In this work, results of a mechanical behavior study of fibers extracted from the Agave americana L. plant are presented. These results deal with the principal and mechanical characteristics of these fibers which are the strain at break, the elasticity modulus and the rupture facture. These results permitted to situate these fibers, compared to the other textile fibers, as materials that can be used in technical applications such as reinforcing composites or geotextile. In order to understand the mechanical properties of these fibers, a correlation study between the properties already cited and the fine structure was done. The obtained results showed that the mechanical properties of Agave americana L. fibers are closely related to the individual fibers deformations and to the natural matrix (lignin and gums) that are linked to these elementary fibers.