Search

This article introduces the basic element to build an augmented reality system allowing to insert a 2D object in a real 3D scene in real time. The first step consists in locating the place where to insert the object using an abstract marker, this marker is a rectangle that surrounds the minimum area of the object's contour detected through its color. This rectangle is a plane surface that provides the position of its four points in the images acquired in real time which allows to have a real time tracking of the detected object. Planar homography describes exactly the relationship between the key points if the scene is flat and only requires four key points to produce an exact solution of the camera position to align a 2D virtual object in a 3D real scene.

Purpose This paper aims to present a new term weighting approach for text classification as a text mining task. The original method, neutrosophic term frequency – inverse term frequency (NTF-IDF), is an extended version of the popular fuzzy TF-IDF (FTF-IDF) and uses the neutrosophic reasoning to analyze and generate weights for terms in natural languages. The paper also propose a comparative study between the popular FTF-IDF and NTF-IDF and their impacts on different machine learning (ML) classifiers for document categorization goals. Design/methodology/approach After preprocessing textual data, the original Neutrosophic TF-IDF applies the neutrosophic inference system (NIS) to produce weights for terms representing a document. Using the local frequency TF, global frequency IDF and text N's length as NIS inputs, this study generate two neutrosophic weights for a given term. The first measure provides information on the relevance degree for a word, and the second one represents their ambiguity degree. Next, the Zhang combination function is applied to combine neutrosophic weights outputs and present the final term weight, inserted in the document's representative vector. To analyze the NTF-IDF impact on the classification phase, this study uses a set of ML algorithms. Findings Practicing the neutrosophic logic (NL) characteristics, the authors have been able to study the ambiguity of the terms and their degree of relevance to represent a document. NL's choice has proven its effectiveness in defining significant text vectorization weights, especially for text classification tasks. The experimentation part demonstrates that the new method positively impacts the categorization. Moreover, the adopted system's recognition rate is higher than 91%, an accuracy score not attained using the FTF-IDF. Also, using benchmarked data sets, in different text mining fields, and many ML classifiers, i.e. SVM and Feed-Forward Network, and applying the proposed term scores NTF-IDF improves the accuracy by 10%. Originality/value The novelty of this paper lies in two aspects. First, a new term weighting method, which uses the term frequencies as components to define the relevance and the ambiguity of term; second, the application of NL to infer weights is considered as an original model in this paper, which also aims to correct the shortcomings of the FTF-IDF which uses fuzzy logic and its drawbacks. The introduced technique was combined with different ML models to improve the accuracy and relevance of the obtained feature vectors to fed the classification mechanism.

Much of the Internet's communication is encrypted, and its content is only accessible at two endpoints, a client and a server. However, any encryption requires a key that must be negotiated without being revealed to potential attackers. The so-called TLS (Transport Layer Security) handshake is often used for this task without obviating that many fundamental parameters of TLS connections are transmitted explicitly. Thus, third parties have access to metadata, including information about the endpoints, how the connection is used. On the other hand, QoS is considered the central part of the communication used to judge the deliverable quality through several parameters (latency, jitter ...). This document describes a secure approach and meets mainly the requirements of quality of service on a communication channel (free, loaded, congested ...), using the robustness and flexibility of the TLS protocol represented on the characteristics of existing encryption keys on its list of "ciphers suites." We focused more particularly on the AES key (Advanced Encryption Standard), including the different sizes (128,192,256), given its resistance to various classical attacks (differential, linear, ...) and its lightness compared to other protocols such as DES, 3DES ... This method is useful in continuous communications in a time axis (video sequence, VOIP call...).

Passwords/passphrases can be either system generated or user-selected. A combination of both approaches is also possible—encryption created by the system and assigned to the user by the information system meeting the policy requirements. Policy rules can be designed to increase security and usability factors, such as information storage and retrieval. This paper proposes an algorithm dedicated to the security of passphrases in an online authentication, so the passphrase entered will be stored in a remote database. Through an SHA-3 hash function, the system must hash the pass phase. Before storage, the system must apply random rotations on the already generated HASH while eliminating any traceability performed on the different transactions performed. To prevent the hacker from using them recurrently if he wants to attack our database. Then the system must recover the real HASH and then the passphrase based on the data provided by the user in the form of codes.

Image mosaicking is a series of successive algorithms that use a sequence of images or a video of a scene to create a single image with a wider field of view of the whole scene. In most cases, when dynamic objects exist in the input data, issues, such as ghosting, parallax effects or object duplication, are visible in the resulting mosaic. These technical errors appear when the objects in motion aren't properly treated. In order to create good result mosaics, a new method is presented in this paper. The proposed approach uses all the images at the same time to divide the images into different areas by using k-means clustering to create categories, then each category is recommended from the original images with a recommender system. In fact, by considering each image as a user, each pixel as an item, and each item belonging to a category, it is possible to use a recommender system by computing scores with the item profiles. The resulting mosaic will then be a new user to the system. Furthermore, by clustering the images, projection errors are avoided and a better quality mosaic can be created as is seen in the obtained results.

Image mosaicking is a combination of algorithms that use two or several images to create a single image. The resulting mosaic is a representation of a scene of the used images with a larger field of vision. However, since dynamic objects can exist in the overlap regions of these images, ghosting and parallax effects appear, therefore poor results are obtained. To overcome these unwanted effects and to achieve better results, a new method is presented in this paper. This approach uses a new way to detect dynamic objects in the common areas by using a fractional Brownian motion with a predetermined similarity function instead of a noise function, the Zero Normalized Cross Correlation. Thus, it will ensure that a map is created with each pixel having a unique value based on their surroundings even in homogeneous areas. Furthermore, this new approach combines the previously computed map with the machine learning algorithm A* for a fast and efficient way to find an optimal seamline. Consequently, the obtained experimental results were compared with different methods and better results were obtained as can be seen by a better quality seamline measure, a result mosaic without any artifacts and a faster computation time.

In this work, we proposed a new approach to encrypt color images using two matrices with size of 16 × 16 whose integer values are between 0 and 255 generated randomly, and the bit-shift operators. These matrices are used to perform the first encryption phase. The first value of the first matrix is calculated from the pixels of each channel (red, green and blue) of the original image; the rest of the values are randomly generated; each value must be unique; the values of the second matrix are unique and generated randomly. The first encryption phase of the original image is done by digraph (two-digit sequence). We take the first digit in the first matrix, the second digit in the second matrix; then, we look in these matrices for the numbers that complete the rectangle. In the second encryption phase, we used a right circular shift of bits; the number of bits to shift is calculated according to a function which considers the values of the two matrices as well as their positions (row and column). Therefore, any change in the two keys (two matrices) will completely change the encrypted image. Our encryption system is resistant against brute force attacks, statistical attacks as well as differential attacks. The results are justified by applying several safety criteria, such as correlation coefficient, entropy and peak signal-to-noise ratio (PSNR). In addition, our method is very sensitive to the change made, either in the original image or in the two keys used for the encryption, which was justified by calculating the number of changing pixel rate (NPCR > 99.69) and the unified averaged changed intensity (UACI > 33.54).

Image mosaicking is a process of assembling multiple images to create an image with a larger field of view. It is used in different studies, but some errors, like ghosting or parallax effects, could occur when the images contain dynamic elements. To avoid the failure of the mosaic and to solve these errors, a new method that searches an optimal seamline for dynamic mosaicking is presented. By finding regions that are similar between the images, and regions that are not alike, the seamline was computed by going through the similar regions and by avoiding the not common regions. To achieve this, a combination of Canny edge detector, and the outliers and inliers from the RANSAC method were used to identify these regions. Then, the regions were incorporated in an intensity difference to create a map that reveals them. Thus, the optimal seamline was computed by going through the similar regions and by avoiding the unalike regions. The experimental results show that the proposed approach is capable of generating robust mosaics against ghosting and parallax effects.

The hash function is designed to fold an input array of any size into a bit string. For the MD5, this is a very convenient algorithm for comparison and storage. For example, Unix systems use it to store user passwords in a 128-bit encrypted format. It is widely used to check the integrity of files. The length of the output string is 128 bits. When it first appeared, it was impossible to break it, but today this is no longer the case. Many programs select the source word based on the hash. The vast majority of them make an enumeration in the dictionary. However, Rainbow Crack methods are based on generating a set of hashes from a set of characters to search for a hash using the resulting base. Besides, the MD5, like any hash function, has a concept such as collisions - it is about getting the same hashes for different characters' source strings. This paper will propose a method capable of increasing password storage security based on the random generation of an MD5 HASH and then use it to transform the original HASH according to pre-defined rules before storing it in the database.

In this article, we propose a robust, flexible and fast system for auto-calibration from two pairs of points of interest matched to two images taken by a mobile camera, characterized by variable parameters, we proposed a new method of auto-calibration based on the use of two unknown scene points with their projections on the two images. To test the effectiveness of our algorithm, we applied it to two types of synthetic and real data. The proposed system achieves satisfactory results within a reasonable period.

The rapid progress of wireless technology constraint scholars for working hard to propose advanced methods and techniques to contribute and solve the most common issues of wireless sensor networks. These sensor networks are, generally a set of huge sensor nodes that work with limited resources, batteries lifetime, storage capability, and are generally deployed in regions where human access is of ten impossible. In this work, we analyze and describe commonly routing techniques and adapted algorithms take out of machine learning designed for wireless sensor networks. We aim to give readers a global view and up-to-date vision of the actual proposed techniques and bring an overview of them. We explore commonly routing mechanisms recently proposed and the popular routing protocols are treated. We target to help better acknowledgment and understanding of the current routing protocols for wireless sensor networks that can be dealt with to further research.

By virtue of advances in machine learning, handwriting recognition is considered as one of the main research topics in this field. Many studies have been proposed to improve this recognition of handwritten texts for different languages such as Latin and Chinese. Yet, the processing of Arabic texts remains a particularly distinctive problem due to the complicated nature of the Arabic script compared to other scripts. In this work, we display a study and an evaluation of relevant articles recently published in conferences and indexed journals. The core of the problem is to relatively find out an efficient method capable of recognizing the handwritten text by any user via digital devices. In this article, we study the various works interested in the recognition of handwritten Arabic script implemented by deep learning. We thouroughly discuss different classification approaches like CNN, RNN and DBN. The pros and cons of each approach will be presented, as well as their different results.

Cryptography is a method of controlling and protecting communications, which has been used exclusively in areas that require confidentiality. Today it is undergoing a considerable evolution, and computer networks require a phase of cryptography as a fundamental mechanism to ensure the privacy of digital information. It was beginning with the first Cesar encryption algorithm or those that appeared just afterwards, such as mono-alphabetic substitution encryption, which has a weakness against statistical attacks. In this paper, we will present a hybridization of Vigenere and Hill encryption that belongs to this family. By exploiting the enhancements, they have already implemented in Hill encryption, to hide the weak point of the Vigenere algorithm, represented in the ease to detect the size of the key to start a statistical attack, as well as the weakness of the algorithm to encrypt two same letters located in the same place in different blocks. This cohesion between these two methods will provide us with a reliable hybrid algorithm, resistant to varying attacks, including statistical attacks.

Secure routing is a difficult task because of the limited nature of wireless sensor network resources. This paper provides a Hidden Markov Model solution to identify malicious nodes in wireless sensor networks through prevention of black hole attack. Our proposed approach based on a new routing algorithm which analyses shortest path in order to avoid malicious node path. Our results demonstrate the success and the efficiency of our proposed routing algorithm.

Representation of knowledge remains a problem for models of machine learning (ML). The Paragraph vector is one of the current methods for embedding the text, where many parameters govern the utility of representation. In this context, we are addressing the effect, on the text classification area, of Paragraph Vector-Distributed Memory (PV-DM) as variant of doc2vec. In comparison, we apply other classification systems focused on doc2vec forms, and a collection of classifiers with current practices in this article. Then, we incorporate hybrid ML methods to improve the quality of classification. The experiments, on benchmarking dataset, prove that the results obtained are excellent, with 99% accuracy in the system based on the PV-DM with average method, and majority voting as a classifier.

In the last decade, the speaker recognition systems know a wide interest from many researchers of speech and speaker recognition technologies that led this technology to become a practical identity authentication means. This paper reviews the speaker recognition systems evolution from the first implementation to current trends. In this paper, we present a brief overview of the speaker recognition area by describing its modeling methodologies and different feature extraction techniques with several languages. Then, we will display some speaker recognition strengths and weaknesses and performance indications. Finally, we will classify different research on Arabic and Amazigh speaker identification with various extraction methods and modeling approaches that can potentially be investigated for future works.

With the development and emergence of the concept of the Web, as well as the advancement of social networks, forums, blogs and E-commerce a growing number of Arabs express their views and opinions using their native language on those platforms where we find a wealth of information that could be exploited. This information, whose size is expanding and which describes opinions, has become the subject of several research fields particularly: “Sentiment Analysis” or “Opinion Mining”. Sentiment Analysis considered a subfield of natural language processing (NLP), information retrieval and text mining. Currently, sentiment analysis is commonly used for English, while it is in its infancy in the Arabic language. The most important and critical step in feeling analysis is to select an appropriate technique for classifying feelings. In this paper, we will be reviewing the published work on the application of Deep Learning (DL) techniques to the problems of sentiment analysis. We focus on the Arabic language because of its importance, the large number of its speakers, the scarcity of Arabic resources on it and the challenges related to its work. We explain, categorize, summarize and compare the techniques offered in this area.

Image mosaicking is a combination of multiple algorithms that use a series of images or a video to obtain as a result a single image with a larger field of view. However, in some cases the input data contains dynamic elements that change their position from a frame to another and this results in the appearance of errors like ghosting and parallax effects. In this paper, we will present a method to obtain a quantitative measure for mosaics with dynamic elements and how to determine the areas that create these errors. In fact, this was done by using dense optical flow to estimate the motion of all pixels and by comparing the Structure Similarity Index Measure of these areas obtained between the result mosaic and the input images. The obtained quantitative measures show better results and reflect better the obtained visual results.

In last years, several biometric modalities are coming back into the field of education. Especially, face recognition modality that allows authenticating humans based on their facial features. The main objective of this paper is to implement the recognition system part for a global software that is intended to be used in many applications related to the educational field. Therefore, we propose to combine the face description method based on Local Gradient Probabilistic Pattern (LGPP), the two dimensional subspace methods, and machine learning classifiers. Firstly, we extract principal face component using the LGPP descriptor. Then, 2DDWT, 2DPCA, and 2DLDA subspace methods were implemented to reduce face features. Finally, support vector machine (SVM) and artificial neural network (ANN) based machine learning algorithms are applied to classify the set of the final features vectors. The experimental results on relevant databases demonstrate the effectiveness of the proposed system.

In this paper, we present a novel efficient face description method called Electric Virtual Binary Pattern (EVBP). The main idea of EVBP descriptor is to combine Local Binary Pattern (LBP) and our new Model based on the Virtual Electric Field. This model consider the neighborhood of each pixel as a grid of virtual electric charges that are electrostatically balanced. Then, we apply the LBP principle for this neighborhood to generate the new EVBP pixel representation. Based on the four trivial space directions, this representation is computed using the corresponding four electrical interactions. Moreover, the spatially enhanced Local Binary Pattern Histogram (eLBPH) algorithm is employed to extract features. Therefore, the proposed EVBP descriptor led to reduce the features vector size by 93.75%. Consequently, we moved from 255 bin-histograms for LBP to 16 bin-histograms for EVBP descriptor. Extensive experiments were carried on relevant databases have proved the effectiveness of the proposed approach.

This paper introduces a new mesh segmentation approach into semantic parts, most closely resemble those made by humans, which is based on the pixel color of the images used in the 3D reconstruction. This approach allows to segment the mesh into semantic and a much simpler way than most of the mesh segmentation methods that are based on the geometrical characteristics of the mesh. The principle of our method is to establish a link between the color objects of the scene and the mesh while exploiting the link between the interest points of the images brought into play and the vertices of 3D mesh. The results in great part, reflect the efficiency and performance of our method.

The normality tests are widely used to estimate the difference between an empirical distribution and the normal distribution. In this paper, we propose to apply the Jarque–Bera normality test (JB-test) in the face recognition field. In order to find out the face areas, which can be approximately represented using a normal distribution, we propose to build a new descriptor based on the JB- test and Local Binary Pattern (LBP) descriptor. To predict whether a pixel belongs to the homogeneous area, Jarque–Bera Local Binary Pattern (JB-LBP) computes the confidence interval basing on the JB- test and uses it later to generate a new pixel grayscale value. The obtained results show that the homogeneous areas pixels are in same way encoded. Therefore, we can easily distinguish them from the peaks areas. Moreover, to reveal that the proposed face representation gives better performances, we combine it with the K-means clustering, the K-Nearest Neighbors (KNN) and the Multi-layers Perceptron (MLP).

This paper presents a complete pipeline of the reconstruction and the modeling of the unknown complex 3D scenes from a sequence of unconstrained images. The proposed system is based on the formulation of a nonlinear cost function by determining the relationship between 2D points of the images and the cameras parameters; the optimization of this function by a genetic algorithm makes finding the optimal cameras parameters. The determination of these parameters allows thereafter to estimate the 3D points of the observed scene. Then, the mesh of the 3D points is achieved by 3D Crust algorithm and the texture mapping is performed by multiple dependent viewpoints. Extensive experiments on synthetic and real data are performed to validate the proposed approach, and the results indicate that our system is robust and can achieve a very satisfactory reconstruction quality.

In this paper, we present a flexible and fast system for multi-scale objects/scenes 3D reconstruction from uncalibrated images/video taken by a moving camera characterized by variable parameters. The proposed system is based on incremental structure from motion and good exploitation of bundle adjustment. At first, from two selected images, our system allows to recover, in a well-chosen reference, coordinates of a set of 3D points. In this context, we have proposed a new method of self-calibration based on the use of two unknown scene points with their image projections. After that, new images are inserted progressively using 3D information already obtained. Local bundle adjustment is used to adjust the new estimated entities. At some time, we introduce a global bundle adjustment to adjust as best as possible all estimated entities and to have an initial 3D model of quality covering an interesting part of the object/scene. This model will be used as reference for the insertion of the rest of images. The proposed system allows to obtain satisfactory results within a reasonable time.

The matching points extracted from images play a very important role in many applications and particularly in computer vision. The use of point sets as being characteristics that describe the entire images brought into play, it greatly contributes to the reduction of the execution time, unlike the use of all the information contained in these images. The major problem of the matching process is the possibility to generate a large number of false correspondences, or outliers, in addition to a limited number of true correspondences (inliers). The objective of this paper is to propose a robust algorithm to eliminate or reduce the false correspondences, or outliers, among the putative set extracted from stereoscopic images. The principle of our method is based on the notion of belonging to the corresponding circles and the concept of similarity of stereoscopic images. The results largely reflect the efficiency and performance of our algorithm in comparison to the other used methods in this framework like RANSAC algorithm.

Automatic speech recognition is a technology that allows a computer to transcribe in real time spoken words into readable text. In this work an HMM automatic speech recognition system was created to detect smoker speaker. This research project is carried out using Amazigh language for comparison of the voice of normal persons to smokers one. To achieve this goal, two experiments were performed, the first one to test the performance of the system for non-smokers for different parameters. The second experiment concern smokers speakers. The corpus used in this system is collected from two groups of speaker, non-smokers and smokers native Morocan tarifit speakers aged between 25 and 55 years. Our experimental results show that we can use our system to make diagnostic for smoking people and confirm that a speaker is smoker when the observed recognition rate is below 50%.

This paper proposes a new appearance model for human tracking based on Mean Shift framework. The proposed method uses a novel target representation by using joint Color-Texture features and Foreground-Weighted Histogram (CTFWH) for a more distinctive and effective target representation. Our contribution is threefold: firstly, to exploit the texture information of the target, we have used joint color-texture histogram to represent the target. Local Binary Pattern (LBP) technique is employed to identify texture features in the target region. Secondly, we have proposed a representation model of the foreground region named Foreground-Weighted Histogram (FWH), in order to exploit the significant features of the foreground region and to use it for selecting only the salient parts from the target model. Thirdly, we propose a simple method to update the foreground model due to the important foreground changes over the tracking process. Hence, by combining these concepts we generate new features for target representation and human tracking. The proposed method is designed for human tracking in complex scenarios and tested for comparative results with existing state-of-the-art algorithms. Experimental results on numerous challenging video sequences verify the significance of the proposed approach in terms of robustness and performance to complex background, illumination and appearance changes, similar target and background appearance, presence of distractors, target and camera motion, occlusions and large background variation.

In this approach, we will process a self-calibration problem of camera characterized by varying parameters. Our approach is based on estimating of homography of the plane at infinity and depths of interest points. This estimation is made from resolution of nonlinear equation system that is formulated from the projection of some points of the scene in the planes of different images. The relationships established between the homography of the plane at infinity and matches, between images, and those established between points of the 3D scene and their projections, in image planes, allow formulating the second nonlinear equations. This system is minimized by using the Levenberg-Marquardt algorithm to estimate the intrinsic parameters of used camera. This approach has several strong points: i) The use of any cameras (having varying parameters), ii) The use of any scenes (3D) and iii) the use of a minimum number of images (two images only). Experiments and simulations show the performance of this approach in terms of stability, accuracy and convergence.

Interactions between trophic and halieutic populations, have often been ignored in most mathematical models that are interested in prey–predator dynamics. However, the presence of vegetation in hydraulic environments, is important, and it has a direct impact on the life cycle of many fishes. In fact, aquatic populations are essential for providing oxygen, food and also shelter for grazers. For this, we suggest a mathematical and optimization approach, in an attempt to discuss the possibility of finding effective harvesting control strategies that aim to optimize the fishing efforts without affecting the trophic-halieutic populations and compromising with the interests of fishermen. The model is in the form of three ordinary differential equations, and which describes dynamics of multi-species of a fishery that includes grazer–predator fishes and aquatic plants, during fishing periods. We study the stability of the proposed differential system, and we suggest harvesting optimal control approaches for the environmental sustainability and bioeconomic cases after the introduction of two control functions in the model and which represent the efforts of fishing in grazer and predator populations respectively. The two optimal controls are characterized in the first case, based on Pontryagin’s maximum principle, and we seek their analytical formulations in the second case, when they are singular functions. Hence, these two optimal control approaches lead to two two-point boundary value problems which are resolve numerically based on the forward-backward sweep method with the incorporation of iterative Runge-Kutta fourth order progressive-regressive schemes.

Mosaic reconstruction is a stitching process of multiple images, of a particular scene, in a single frame that provides a larger amount of information compared to the separate images. Nowadays, image mosaic is a key tool that has invaded different fields and disciplines such as photography, virtual environment, medicine, etc. In this work, we propose a new pre-processing approach of multi-scale images we have named MSIP (Multi-Scale Image Pre-processing), invariant to scale changes and based on the distance between the matched points detected by SIFT. Its main purpose is to correct the scale difference between images to reduce outliers and alignment errors. The experimentation and statistical analysis, on a real database, show the robustness of our approach by improving the quality of mosaic results.

In this paper, we studied image segmentation to which we applied a combination of the genetic algorithm and the cooperation between unsupervised classification by K-means and contour detection by the Sobel filter to improve image segmentation results by the K-means method alone. First, we will apply the segmentation process by combining two methods in the following way: We have hybridized the K-means method which is used to classify pixels into classes (regions), with the Sobel gradient filter which will then detect the edges of these regions, and then we will apply the genetic algorithm and by scanning further in the response space, try to find better quality class centers. This process is withdrawn until they are unable to find two sufficiently similar neighboring regions. The effectiveness of the proposed method was studied on a number of images. It is also compared by the K-means algorithm.

This paper aims to build an interactive speaker-independent automatic Amazigh speech recognition system. The proposed system offers a methodology to extract data remotely from a distance database using the combined interactive voice response (IVR) and automatic speech recognition (ASR) technologies. We describe our experience to design an interactive speech system based on hidden Markov models (HMMs), Gaussian mixture models (GMMs) and Mel frequency spectral coefficients (MFCCs) based on ten first Amazigh digits and six Amazigh words. The best-obtained performance is 89.64% by using 3 HMMs and 16 GMMs.

In this paper, we introduce a new method of color image encryption. The principle of this approach is to encrypt any color image (called the original image), into a sequence of N images whose (N − 1) of them are generated randomly, and the Nth image is calculated from the original image and the (N − 1) generated images using a linear equation. This process will be repeated for each color image channel (red, green, and blue). Those (N − 1) generated images are used as a symmetric key in the decryption phase; therefore, they should be shared with the receiver privately or via a secure channel. Only the Nth image will be sent. To obtain the original image, we need all N images in the decryption phase. Our encryption system can resist brute-force attacks as well as statistical attacks. The results are justified by applying several safety criteria, such as correlation coefficient and histogram.

This paper presents a hybrid approach for 3D object reconstruction from multiple images taken from different viewpoints. The proposed method allows to obtain a complete and automatic reconstruction from limited number of images. It begins with a sparse 3D reconstruction based on camera self-calibration and interest point matching between images. The integration of sparse approach allows us to automatically estimate the projection matrices without using a turn-table (controlled environment) often used in the Shape from Silhouette approach. In addition, it offers the possibility of an accurate estimation of the initial bounding box of the object. This bounding box is discretized into voxels afterward. Then, the reconstruction process consists in using the image Silhouettes and the photo-consistency test to finally have a volumetric textured model that can be transformed into surface model by applying the marching cube algorithm. The experiments on real data are performed to validate the proposed approach; the results indicate that our method can achieve a very satisfactory reconstruction quality.

Our article discusses existing methods in marker-based and markerless augmented reality and their evolution over time. Markers are the most optimal solution to solve the problem of calculating the pose for augmented reality and do not require powerful devices. Its simplicity, robustness and efficiency have a great advantage; the objects to detect are provided to the application and require to be always visible by the sensor. On the other hand, markerless augmented reality detects objects or characteristic points of a scene without any prior knowledge of the environment. This mechanism is more difficult to implement because it implements algorithms that are expensive in terms of computation time. The appearance and improvement of new devices have made it possible to exploit this technology and to detach from the presence of a marker in a scene and emerge to markerless methods.

We propose an algorithm for elimination of false correspondences from given putative point correspondences in couples of stereoscopic images based on corresponding circles (ICC) technique. In this paper, we propose a new method that reduces the cost of computing false correspondences. The aim of this method is mainly to take better advantage of the corresponding circles. The quantitative results demonstrate the efficiency and performance of our algorithm.

Distributed simulation with a virtual environment of quality is a qualified teaching solution, especially in the military field. A soldier's performance will be better if deployed preferably in a known combat space. This article deals, with a comparative study, the performance of two teams in training with two different simulation methods. One based on simulation in an imaginary virtual battlefield and the other on that existing in reality. The research and the results of this study represent the new approach of dynamic invention of real ground established, during the research carried out during the realization of a distributed simulator of combat for soldiers training on shooting techniques. This new method aims to provide trainees with a virtual combat space existing in reality and presenting the best results and performance and based on geographic information systems (GIS), some 3D modeling tools and 3D engines in this case the 3D Unity engine.

The representation of the information has an important impact on the text classification task. Several weighting methods were proposed in the literature, and the term frequency-inverse term frequency (TFIDF), the most know on the text treatment field. The FTF-IDF is a vector representation where the components of the TFIDF are presented as inputs to the Fuzzy Inference System (FIS). In this work, we compare several Machin Learning algorithms such as Naive Bayes and its derivatives, SVM and Random forest classifiers, using the FTF-IDF representation. To improve the quality of the used classifiers, we call sum attribute selection methods. The recognition rate, for the tested systems, is satisfied, where the system based on naive Bayes classifier, the FTF-IDF weighting terms, and the info gain select attributes method gives 98.7% as accuracy.

Image segmentation is an important step in any image analysis process. In the literature, there are two dual approaches. The contour segmentation approach consists in locating the object boundaries and the segmentation approach by region consists in partitioning the image into a set of regions. The best results of segmentation are obtained by cooperating these two approaches. They are more effective because the disadvantages of one method can be overcome by the advantages of another method. In an image processing system, the most important operation is image segmentation. To date, there is no universal method of image segmentation. Any technique is only effective for a given type of image, for a given type of application, and in a given computer context. Because of these constraints, the various image processing strategies that have been proposed have asserted their inadequacies and limitations. It is therefore perfectly normal to explore new horizons and find new methods that are more flexible and more effective. In this paper, we will propose and discuss a cooperative approach between a k-means unsupervised classification method and Canny's contour detection method to improve color image segmentation results. First, we will apply the contour segmentation process by Canny's algorithm, and then we integrate the results obtained by another unsupervised classification segmentation process, which is k-means. Experimental results show the strengths of our approach in terms of accuracy, simplicity and efficiency.

This paper presents an approach to reconstructing 3D objects based on the generation of dense depth map. From a two 2D images (a pair of images) of the same 3D object, taken from different points of view, a new grayscale image is estimated. It is an intermediate image between a purely 2D image and a 3D image where each pixel of this image represents a z-height according to its gray level value. Our objective therefore is to play on the precision of this map in order to prove the interest and effectiveness of this map on the quality of the reconstruction.

The main problem in the handwritten character recognition systems (HCR) is to describe each character by a set of features that can distinguish it from the other characters. Thus, in this paper, we propose a robust set of features extracted from isolated Amazigh characters based on decomposing the character image into zones and calculate the density and the total length of the histogram projection in each zone. In the experimental evaluation, we test the proposed set of features, to show its performance, with different classification algorithms on a large database of handwritten Amazigh characters. The obtained results give recognition rates that reach 99.03% which we presume good and satisfactory compared to other approaches and show that our proposed set of features is useful to describe the Amazigh characters.

Self-calibrate cameras with varying focal length.Automatic estimation of the intrinsic parameters of the camera.Works freely in the domain of self-calibration without any prior knowledge about the scene or on the cameras. We propose a new self-calibration technique for cameras with varying intrinsic parameters that can be computed using only information contained in the images themselves. The method does not need any a priori knowledge on the orientations of the camera and is based on the use of a 3 D scene containing an unknown isosceles right triangle. The importance of our approach resides at minimizing constraints on the self-calibration system and the use of only two images to estimate these parameters. This method is based on the formulation of a nonlinear cost function from the relationship between two matches which are the projection of two points representing vertices of an isosceles right triangle, and the relationship between the images of the absolute conic. The resolution of this function enables us to estimate the cameras intrinsic parameters. The algorithm is implemented and validated on several sets of synthetic and real image data.

In this article, we propose a new method of image stitching that computes, in a robust manner, the transformation model applied to creating a panorama that is close to reality. The random selection of matching points used in existing methods, using Random Sample Consensus (RANSAC) or the threshold of the execution process (iteration number) cannot generally provide sufficient precision. Our approach, in this regard, comes to solve this problem. The calculation of the transformation model is based on the VORONOI diagram that divides images into regions to be used in the matching instead of control points. In this case, the transformation estimation will be based on the regions seeds that provide the best correlation score. Among the advantages of our method is solving problems related to outliers that can, in existing methods, affect the reliability of the mosaic. The results obtained are satisfactory in terms of stability, quality, execution time and reduction of the computational complexity.

Sentiment analysis is a very substantial area of research in our environment. Many studies have focused on the topic in recent years. It has rapidly gained interest due to the unusual volume of opinion-bearing data on the Internet (Big Social Data). In this paper, we focus on sentiment environment analysis from Amazon customer reviews shared by a machine learning based approach. This process starts with the collection of reviews and their annotation followed by a text pre-processing phase in order to extract words that are reduced to their root. These words will be used for the construction of input variables using several combinations of extraction and weighting schemes. Classification is then performed by a supervised Machine Learning classifier. The results obtained from the experiments are very promising.

Nowadays, companies and researchers are facing a real challenge to process amounts of data generated daily from different sources. To remedy this major problem, a range of technical solutions BIG DATA [1] is offered today. This article provides a detailed study of the main Big Data methods namely supervised and unsupervised methods as well as an interpretation.

In this work, we propose a method for reconstructing three-dimensional scenes from a sequence of images of which only one image is calibrated. The system is initialized by a calibrated image. The projection matrices of the other images in the sequence are estimated, from the first projection matrix (obtained by the calibration of the camera) and the matching between the images, by solving a system of linear equations. The intrinsic and extrinsic parameters of the camera used are estimated from the Cholesky decomposition of the projection matrix. Finally, obtaining the 3D scene is based on the Euclidean reconstruction of the detected and matched control points in the pairs of images.

In this work, we propose a method of cryptography of grayscale images. The principle of this approach is to encrypt any image (called the original image), into a sequence of N images whose (N-1) are generated randomly and the Nth image is determined from the original image and the (N-1) generated images. A key will be used in order to increase the security of the image transmitted to the receiver. The pixels of the original image are first converted into bits and then we use the shift bits operators to obtain a matrix, which will be used in the encryption procedure. All N images as well as the key used are needed in the decryption process, to obtain the source image. Experiments show the importance and quality of the approach that we proposed in terms of accuracy.

The best texture mapping techniques that focus on the microrelief effect use iterative algorithms. The number of iterations must be determined in advance, but for real-time rendering, the number of iterations must be chosen dynamically to take into account the change of the depth scale and the viewing angle (viewing direction). In this paper, we presented a real-time rendering technique that allows a combined synchronization between depth scaling, viewing angle and number of iterations.

The increasing of the textual databases and its representation in large spaces prevents the automation of the treatment of these great masses and the extraction of knowledge. In order to address the challenges of high dimensionality which using the methods and technics of the text mining. Where the term frequency-inverse document frequency (TF-IDF), weighting method, is the most required approach to represent the document. Unfortunately, TF-IDF produces descriptors of large sizes (generally greater than 1000), which requires models with great complexity. However, the texts classification systems based on these models suffer from the overfitting phenomenon and are very slow. Therefore, to overcome these problems, we use the select attributes methods; by giving the deterministic aspect of this latter, we risk to lose huge information. Thus, to recover from this loss, we propose a probabilistic vector representation of each document, based on the relevant terms selected previously. Then, we associate a set of features to each document composed by local and global probabilistic coefficients basing on the selected terms. More specifically and precisely, the components formulas are composed by the frequency of each descriptor, the length of each document and the size of the corpus. To show the performance of this treatment we propose comparative studies between TF-IDF representation and the new probabilistic representation, to classify the BBCSPORT corpus. Moreover, in the classification phase, we use several versions of Bayesian Network and Multilayer Perceptron. The obtained results are satisfied, where the neural network classifier, multilayer perceptron, gives 100% as a recognition rate, using the new representation and 94.69%, using the simple TF-IDF weighting.

In this paper, we will study a new approach of reconstruction of three-dimensional scenes from an auto calibration method of camera characterized by variable parameters. Indeed, obtaining the 3D scene is based on the Euclidean reconstruction of the interest points detected and matched between pair of images. The relationship between the matches and camera parameters is used to formulate a nonlinear equation system. This system is transformed into a nonlinear cost function, which will be minimized to determine the intrinsic and extrinsic camera parameters and subsequently estimate the projection matrices. Finally, the coordinates of the 3D points of the scene are obtained by solving a linear equation system. The results of the experiments show the strengths of this contribution in terms of precision and convergence.