With the success of emerging RGB-D cameras such as the Kinect sensor, combining the shape (depth) and texture information to improve the quality of recognition became a trend among computer vision researchers. In this work, we address the problem of face classification in the context of RGB images and depth data. Inspired by the psychological results for human face perception, this article focuses on (i) finding out which facial parts are most effective at making the difference for some social aspects of face perception (gender, ethnicity, and emotional state), (ii) determining the optimal decision by combining the decision rendered by the individual parts, and (iii) extracting the promising features from RGB-D faces to exploit all the potential that this data provide. Experimental results on EurecomKinect Face and CurtinFaces databases show that the proposed approach improves the recognition quality in many use cases.

Since more than a decade, wireless sensor networks is a very attractive field in computer science and networking. Battery management is a crucial issue in the area of wireless sensor networks. The communication between a source node and a destination one may fail if both nodes are located inside a deep shadow-fading zone. Relay-selection strategy has been used in order to extend amplify-and-forward (AF) cooperative networks lifetime. The communication could not be achieved if the signal-to-noise ratio (SNR) at the destination could not reach a reasonable threshold. In the literature, various relay selection schemes have been used under the assumption that batteries are linear, but their effectiveness is not guaranteed when realistic nonlinear battery models are considered. In this paper, we review some relay selection schemes with linear battery mode that were proposed to extend network lifetime. Then, a realistic nonlinear battery model is applied with these schemes. Through numerical studies, we give a performances comparison between these techniques. The results show that the maximum energy-efficiency index MEI and the minimum outage probability MOP schemes give the best network lifetime extension.

In this paper, we present a new approach for human action recognition using [Formula: see text] skeleton joints recovered from RGB-D cameras. We propose a descriptor based on differences of skeleton joints. This descriptor combines two characteristics including static posture and overall dynamics that encode spatial and temporal aspects. Then, we apply the mean function on these characteristics in order to form the feature vector, used as an input to Random Forest classifier for action classification. The experimental results on both datasets: MSR Action 3D dataset and MSR Daily Activity 3D dataset demonstrate that our approach is efficient and gives promising results compared to state-of-the-art approaches.

Automatic gender recognition, from face images, plays an important role in various biometric applications. This task has attracted the interest of not only computer vision researchers, but also of many psychologists. Inspired by the psychological results for human gender perception. There are two main purposes for this work. First; it aims at finding out which facial parts are most effective at making the difference between men and women. Second; it tries to combine the decisions of these parts using a voting system to improve the recognition quality. Recently, with the appearance of depth sensing technology; especially the low cost devices such as the Microsoft kinect; high quality images containing color and depth information can easily be acquired. This gives us the opportunity to combine depth information with standard vision systems in order to offer a better recognition quality. In this paper, we propose an approach for classifying gender using RGB-D data based on the separation of facial parts. The experimental results show that the proposed approach improves the recognition accuracy for gender classification.

Recommender systems are valuable tools for providing suitable recommendations to users. In the last decade, the amount of online information have grown rapidly. Consequently, traditional recommender systems often raise some limitations like inefficiency problems when processing or analysing such large volume of data. Matrix factorization is one of the most popular techniques for prediction problems in the fields of intelligent systems and data mining. It has shown its effectiveness in many real-world applications such as recommender systems. This paper describes a new algorithm that represents a solution to overcome the problem of high dimensionality when using matrix factorization for recommendation. It aims at producing low dimensional representation of data and more accurate predictions. The experimentation results show that the proposed algorithm significantly improves the accuracy of recommender systems over existing approaches.

In this paper, we analyze asynchronous and non linearly distorted FBMC signals in the downlink of multi-cellular networks. The considered system includes a reference mobile perfectly synchronized with its reference base station (BS) and K interfering BSs. Both synchronization errors and high power amplifiers (HPA) distortions will be considered and a theoretical analysis of the interference signal will be conducted. On the basis of this analysis, we will derive an accurate expression of bit error rate (BER) in the presence of a frequency selective channel. In order to reduce the computational complexity of the BER expression, we applied an interesting lemma based on the moment generating function of the interference power. Finally, the proposed model is evaluated through computer simulations which show perfect match between the developed theoretical model and simulation results.

In this paper, we study the performance of asynchronous and non linear FBMC based multi-cellular networks. The considered system consists of a reference mobile user perfectly synchronized with its reference base station (BS) and K interfering BSs. We have considered both synchronization errors and high power amplifiers (HPA) non linear distortions (NLD). We analyzed first the signal to noise plus interference ratio (SINR). On the basis of this analysis, derived an accurate of bit error rate (BER) in the presence of a frequency selective channel. In order to reduce the computational complexity of the BER expression, we applied an interesting lemma based on the moment generating function of the interference power. Finally, the proposed model is evaluated through computer simulations which show a high sensitivity of the asynchronous FBMC based multi-cellular network to HPA non linear distortions.

In a heterogeneous network environment, and within the surge of multimedia applications such as audio, video and voice, which require strict quality of service (QoS), Always Best Connected (ABC) Concept offers the best connection for mobile users since many wireless communication technologies were deployed to cover the needs of mobile users in all circumstances. Multiple Attribute Decision Making (MADM) is one of the first-rated candidate strategies used for Network Selection in 4G and beyond networks. In this paper, we propose a network selection scheme based on VlseKriterijumska Optimizacija I Kompromisno Resenje (VIKOR) method, one of MADM methods. Implementation and simulation experiments with Network Simulator NS-3 are presented in order to compare and validate the proposed scheme with other MADM methods as baseline schemes.

Current state-of-the-art denoising methods, such as non-local low-rank approaches, have shown to give impressive results. They are, however, mainly tuned to work with uniform Gaussian noise corruption and known variance, which is far from the real noise scenario. In fact, noise level estimation is already a challenging problem and denoising methods are quite sensitive to this parameter. Moreover, these methods are based on shrinkage models that are too simple to reflect reality, which results in over-smoothing of important structures, such as small-scale text and textures. We propose in this paper a new approach for more realistic image restoration based on the concept of low-rankness transfer. Given a training clean/noisy image pair, our method learns a mapping between the non-local noisy singular values and the optimal values for denoising to be transfered to a new noisy input. One single image is enough for training the model and can be adapted to the noisy input by taking a correlated image. Experiments conducted on synthetic and real camera noise show that the proposed method leads to an important improvement both visually and in terms of PSNR/SSIM.

Abstract Over the last few years, wireless sensor networks have become a great field of interest for the scientific community. This novel kind of network provides an array of applications for different aspects of human life. To give a satisfying performance to the final user, the wireless sensor networks must ensure the quality of service. The use of multipath technique was widely applied in the literature. Nevertheless, there might be a problem if the interference issues are not taken into account by the multipath routing design. In this paper, we propose a novel multipath routing protocol calledCarrier Sense Aware Multipath Geographic Routing protocol(CSA‐MGR). This protocol creates multiple paths while avoiding any shared carrier sense range by using a distributed and dynamic process. In addition, the CSA‐MGR employs a new metrics named the Number of Common Neighbors to guarantee a faster and an efficient path construction. Simulations conducted over the NS‐2 simulator show promising results in terms of delay, Packet Delivery Ratio and routing overhead. The performance gain of CSA‐MGR in terms of delay is up to 275% compared with the Two‐Phase geographical Greedy Forwarding and up to 565% compared with the ad hoc on‐demand multipath distance vector. For the Packet Delivery Ratio, the performance gain of CSA‐MGR is up to 16% compared with the Two‐Phase geographic Greedy Forwarding and up to 28% compared with the ad hoc on‐demand multipath distance vector. Copyright © 2015 John Wiley & Sons, Ltd.

The aim of this work is to automatically identify and extract the upwelling area in the coastal ocean of Morocco using the satellite observation of chlorophyll concentration. The algorithm starts by the application of FCM algorithm for the purpose of finding regions of homogeneous concentration of the chlorophyll, resulting in c-partitioned labeled images. A region-growing algorithm is then used to filter out the noisy structures in the offshore waters not belonging to the upwelling regions. The proposed methodology has been validated by an oceanographer and tested over a database of 166 weekly Sea Surface chlorophyll data. The region of interst cover the southern part of Moroccan atlantic coast spanning from the years 2007 to 2012.

The phase codes is one of important pulse compression waveform methods. This paper shows and compares the PSLR (Peak Sidelobe Ratio), ISLR (Integrated Sidelobe Ratio) and doppler tolerance for different phase codes. At first, a presentation of the ambiguity function is given, as well as some measures to evaluate it. Then we define some existed phase code and plot their ambiguity function. We consider the best sequence, the sequence that has low PSLR, ISLR and low sidelobe in the presence of large doppler shift. The comparison results have shown that for zero doppler, the golay complementary pair is the best. However, the P3, P4 and Chu codes are the best in the case of large doppler shift.

Due to the current progress in Internet, digital contents (video, audio and images) are widely used. Distribution of multimedia contents is now faster and it allows for easy unauthorized reproduction of information. Digital watermarking came up while trying to solve this problem. Its main idea is to embed a watermark into a host digital content without affecting its quality. Moreover, watermarking can be used in several applications such as authentication, copy control, indexation, Copyright protection, etc. In this paper, we propose a blind robust image watermarking approach as a solution to the problem of copyright protection of digital images. The underlying concept of our method is to apply a discrete cosine transform (DCT) to the magnitude resulting from a discrete Fourier transform (DFT) applied to the original image. Then, the watermark is embedded by modifying the coefficients of the DCT using a secret key to increase security. Experimental results show the robustness of the proposed technique to a wide range of common attacks, e.g., Low-Pass Gaussian Filtering, JPEG compression, Gaussian noise, salt & pepper noise, Gaussian Smoothing and Histogram equalization. The proposed method achieves a Peak signal-to-noise-ration (PSNR) value greater than 66 (dB) and ensures a perfect watermark extraction.

Nowadays, adopting an optimized irrigation system has become a necessity due to the lack of the world water resource.Moreover, many researchers have treated this issue to improve the irrigation system by coupling the novel technologies from the information and communication field with the agricultural practices.The Wireless Sensor and Actuators Networks (WSANs) present a great example of this fusion.In this paper, we present a model architecture for a drip irrigation system using the WSANs.Our model includes the soil moisture, temperature and pressure sensors to monitor the irrigation operations.Specifically, we take into account the case where a system malfunction occurs, as when the pipes burst or the emitters block.Also, we differentiate two main traffic levels for the information transmitted by the WSAN, and we use an adequate priority-based routing protocol to achieve high QoS performance.Simulations conducted over the NS-2 simulator show promising results in terms of delay and Packet Delivery Ratio (PDR), mainly for the priority traffic.

Nowadays, a recent trend has emerged in the Wireless Multimedia Sensor Networks (WMSNs) field. This trend consists of ensuring the best Quality of Experience (QoE) while transferring the multimedia content, as well as keeping an acceptable Quality of Service (QoS) concerning the scalar data transmission. However, ensuring this request needs more flexible and robust protocols at different communication layers. Especially, the network layer must provide an efficient routing protocol with awareness of the interference phenomenon and the carrier sense range effect. In this paper we provide analysis of the carrier sense range effect on multimedia communication in the WMSNs. Therefore, we present a realistic solution at the routing layer to enhance the QoS/QoE while avoiding any type of multipath coupling effect. Our solution differs from the existing approaches that handle the problem at the MAC layer. Simulations conducted over the NS-2 simulator show promising results in terms of delay, Packet Delivery Ratio (PDR) and QoE.

Biometric cryptosystems represent emerging techniques for biometric template protection. These cryptosystems are vulnerable to different types of attacks, as brute force attacks or correlation attacks if several templates are compromised. Another biometric security issue comes from certain biometric data (as fingerprint or face image) that can leave traces, but are, in the same time, the most commonly biometric modalities used in mobile security. In this paper, a new attack based on the alteration of original user data is investigated on fuzzy Vault biometric cryptosystems. We assume that the attacker uses a modified version of the real user image to gain unauthorized access to the system (mobile phone). Experimental results carried out using fingerprint and face modalities show that this assumption has serious impact on the security of this type of biometric cryptosystems.

Vehicular Ad-Hoc Network (VANET) has recently become an attractive area of research in the wireless networking. The mobility model is considered one of the most critical issues in a simulation of VANET, which can create realistic moving behavior of each vehicle in the network. Thus, the mobility model play a vital role in determining the performance of VANET system. This paper will tackle five types of mobility models, proposed in the recent research literature, based on the Impulse Radio Ultra wide-Band (IR-UWB) technology to enable communication between vehicles and evaluate their impact on packet delivery carried out in OMNeT++ simulator.

An unsupervised classification method is developed for the coarse segmentation of Moroccan coastal upwelling using the sea surface temperature (SST) satellite images. The algorithm is started with the generation of a c-partitioned labeled image using Otsu's method for the purpose of finding regions of homogenous temperatures. Then, two well-known validity indices are used to select the c-partition that best reproduces the shape of upwelling area. A region-growing algorithm is developed that is used to remove the noisy structures in the offshore waters not belonging to the upwelling area. The algorithm is used to provide a seasonal variability of upwelling activity in the southern Moroccan Atlantic coast using 70 SST images of the years 2007 and 2008. The performance of the proposed methodology has been validated by an oceanographer, showing its effectiveness for automatic delimitation of the Moroccan upwelling region.

We present a new framework for fast edge-aware processing of images and videos. The proposed smoothing method is based on an optimization formulation with a non-convex sparse regularization for a better smoothing behavior near strong edges. We develop mathematical tools based on first order approximation of proximal operators to accelerate the proposed method while maintaining high-quality smoothing. The first order approximation is used to estimate a solution of the proximal form in a half-quadratic solver, and also to derive a warm-start solution that can be calculated quickly when the image is loaded by the user. We extend the method to large-scale processing by estimating the smoothing operation with independent 1D convolution operations. This approach linearly scales to the size of the image and can fully take advantage of parallel processing. The method supports full color filtering and turns out to be temporally coherent for fast video processing. We demonstrate the performance of the proposed method on various applications including image smoothing, detail manipulation, HDR tone-mapping, fast edge simplification and video edge-aware processing.

The Named Entity Recognition (NER) is very important task revolving around many natural language processing applications. However, many studies have achieved the maturity stage in a variety of languages such as English and French, but a few limited research efforts have attacked the named entity recognition problem in Amazighe script. This is due to the resources scarcity for Amazighe named entities and the limited work made in Amazighe natural language processing in general. In this paper, we describe our attempt at the development and implementation of a named entity recognition system for the Amazighe Language using a rule based approach. Our system has been effectively evaluated using our own corpus; it reached acceptable results in terms of precision, recall, and F-measure.

Reconstructing a surface/image from corrupted gradient fields is a crucial step in many imaging applications where a gradient field is subject to both noise and unlocalized outliers, resulting typically in a non-integrable field. We present in this paper a new optimization method for robust surface reconstruction. The proposed formulation is based on a triple sparsity prior: a sparse prior on the residual gradient field and a double sparse prior on the surface gradients. We develop an efficient alternate minimization strategy to solve the proposed optimization problem. The method is able to recover a good quality surface from severely corrupted gradients thanks to its ability to handle both noise and outliers. We demonstrate the performance of the proposed method on synthetic and real data. Experiments show that the proposed solution outperforms some existing methods in the three possible cases: noise only, outliers only and mixed noise/outliers.

In the recent years, Wireless Sensor Networks (WSNs) have become a great field of interest for scientific community. This kind of network provides a panoply of applications in different areas of human life. However WSNs must ensure the quality of service (QoS) to give the requested performance for the final user. Among different issues presented in the literature to provide high QoS, multipath routing is commonly used. But such a solution could be not enough efficient if the multipath routing design does not consider the phenomena of interference. Indeed the constructed paths can have an interference zone, mainly a shared carrier sense range. In this paper we show by analytical and experimental results, that using multipath routing can never overshoot the performance of single path when the interferences are not taken into account. Also, we show how the carrier sense range can influence the network performance.

Wireless multimedia sensor networks (WMSNs) is one of the hotest topic nowadays which attracts more and more researchers as being an interdisciplinary research interest. Its cost decreases continously due to advances in micro-electromechanical systems, and the proliferation and progression of wireless communications. However, the transmission of multimedia information must satisfy QoS criteria which increases energy consumption. This issue should be taken into consideration in the protocol design for WMSNs. In this paper1, we propose an implementation and an evaluation of the TPGF routing protocol (Two Phase geographical Greedy Forwarding) over the network simulator NS2. The TPGF module over NS-2 is available for the research community. In this evaluation, we compare the TPGF performances with two other protocols: the well known AODV protocol and the EA-TPGF protocol (our previous work on an extension of the TPGF protocol which takes into account the remaining energy of nodes during the process of path identification). The performance metrics measured to evaluate the QoS of each protocol are: delay, PDR, remaining energy of each node at the end of the communication and the standard deviation of remaining energy. Simulations show promising results in terms of network life extension when TPGF is used.

This paper proposes a model to predict the energy consumption of a H.264/AVC intra-only based encoder designed for the wireless video sensor networks (WVSNs). Such model is of great interest in an energy-constrained context like the WVSN, where the video streams are processed prior to transmission. In fact, accounting for both processing's and transmission's consumed energies allows the optimization of the global energy consumption. The proposed model predicts the processing's energy consumption based on the considered Quantization Parameter (QP) and the Frame Rate (FR) values. The generic form of this model enables it to predict the energy consumption of any H.264/AVC intra-only based encoder. Simulation results demonstrate the accuracy of the proposed model, that is validated under different resolutions, QP and FR, with an average prediction error of 4%.

The design of efficient Wireless Sensor Networks is a very hot topic nowadays. The efficiency could be observed at many levels, from the application layer to the physical part. In order to get better performances over WSN, many layers could be considered. Indeed, routing over Wireless Sensor Networks (WSN) has been considered in many studies. The energy consumption is one of the hottest issue in this area. Many papers have proposed solutions in order to reduce the energy consumption while handling routing. However, energy optimisation could not ensure a network lifetime extension, since the battery discharge is not linear. We propose in this paper a routing protocol which considers carefully the battery recovery in path searching. We prefer use paths composed of nodes having their batteries fully recovered and letting other nodes completing their batteries recovery to extend their time usage. The paths change continuously since some nodes need to shut down in order to have enough time to recover additional energy.

Filter Bank Multicarrier (FBMC) is an efficient multicarrier modulation characterized by its good spectral efficiency and low out of band leakage. Nevertheless, FBMC signals suffer from the high Peak-to-Average Power Ratio (PAPR). This leads nonlinear devices such as Power Amplifiers, when used, to operate in their saturation region which may severely impair system performance. In this paper, we propose a PAPR reduction technique based on the combination of Hadamard transform with the exponential companding transform. Simulation results show that the proposed scheme can offer better PAPR reduction than exponential companding and Hadamard transforms when used separately.

Despite its position as second official language of Morocco, Amazigh language still suffers from the lack of studies from computational point of view. To achieve this goal, and given that the noun classification system in Amazigh is computationally interesting and constitutes a major word category which plays a major role in syntactic analysis, we have undertaken to develop a component of a noun morphological analysis for standard Amazigh of Morocco using finite state technology, within the linguistic developmental environment NooJ.

The problem of time to contact or time to collision (TTC) estimation is largely discussed in perspective images. However, a few works have dealt with images of catadioptric sensors despite of their utility in robotics applications. The objective of this paper is to develop a novel model for estimating TTC with catadioptric images relative to a planar surface, and to demonstrate that TTC can be estimated only with derivative brightness and image coordinates. This model, called “gradient based time to contact”, does not need high processing such as explicit estimation of optical flow and feature detection and/or tracking. The proposed method allows to estimate TTC and gives additional information about the orientation of planar surface. It was tested on simulated and real datasets.

The field of wireless multimedia sensor networks (WMSN) is attracting more and more research community as an interdisciplinary field of interest. This type of network is low-cost, multifunctional due to advances in micro-electromechanical systems, and the proliferation and progression of wireless communications. However transmit multimedia information captured must satisfy the criteria of QoS , which increases energy consumption, fact that should be taken into consideration in the design of any routing protocols for WMSNs. In this paper we present routing protocol which we call an Energy Aware TPGF (EA-TPGF), that improves the Two Phase geographical Greedy Forwarding (TPGF). The basic idea is to take into account the residual energy of the nodes in the identification of pathways. Simulations and statistics produced by the simulator NeTtopo showing a significant contribution with regard to the extension of the life of the network.

We utilize ideas from two growing but disparate ideas in computer vision-shape analysis using tools from differential geometry and feature selection using machine learning-to select and highlight salient geometrical facial features that contribute most in 3-D face recognition and gender classification. First, a large set of geometries curve features are extracted using level sets (circular curves) and streamlines (radial curves) of the Euclidean distance functions of the facial surface; together they approximate facial surfaces with arbitrarily high accuracy. Then, we use the well-known Adaboost algorithm for feature selection from this large set and derive a composite classifier that achieves high performance with a minimal set of features. This greatly reduced set, consisting of some level curves on the nose and some radial curves in the forehead and cheeks regions, provides a very compact signature of a 3-D face and a fast classification algorithm for face recognition and gender selection. It is also efficient in terms of data storage and transmission costs. Experimental results, carried out using the FRGCv2 dataset, yield a rank-1 face recognition rate of 98% and a gender classification rate of 86% rate.

This paper presents aircraft target recognition (ATR) system using Inverse Synthetic Aperture Radar (ISAR) images. Knowing the pose of the target can improve the ATR performance (recognition rate and computational complexity). So, we propose in this paper a new pose estimator from ISAR images, based on the axis of symmetry and the similarity measure. The method proposed is compared with several approaches proposed recently in the literature, such as 2-D Continuous wavelet Transform and Hough transform. Once the pose of target is estimated, the classification if finally performed by K-Nearest Angle (KNA) classifier which insert the pose information into image retrieval task.

International audience

This correspondence proposes a novel template matching technique using a fourth central moment. The fourth central moment is an established estimator which uses higher order statistics theory, important in the presence of an additive Gaussian noise. By use of some substitutions and complex arithmetic, computation of the fourth central moment is derived from correlation functions of substituting functions. The fourth central moment can be computed using the fast Fourier transform (FFT) approach. Simulation results show that the proposed algorithm performs better than the classical estimators in terms of robustness, while the extra computational cost is negligible.

Image watermarking has today a growing success in the community of image processing. Many methods were already proposed making it possible to obtain increasingly more powerful algorithms. So, most of insertion schemes in the spatial domain are based on the decomposition of the image to blocs, with similar sizes, in order to insert a sequence of information bits. To reach good performances, content-based watermarking schemes aim to use feature points detectors to link the mark with the content of the image. Feature points are after used to perform a decomposition based on a Delaunay triangulation, using triangular tessellation. These methods use classical geometrical transforms that generally induce a loss of synchronization that prevents the detection of the mark, and the image may lose some of its properties. In the proposed scheme, feature points detection are used to decompose the image using a rectangular tessellation and the mark is embedded in each rectangle of the decomposition. The proposed watermarking method, performed in spatial domain, is based on the image content, aims to be simple and to improves mark detection in comparison with methods based on triangular decomposition.

Gene expression data usually contains a large number of genes (several thousand or more) but a small number of samples (usually ≪100). Among all the genes, many are irrelevant, insignificant or redundant to the discriminant problem under investigation. Hence the identification of informative genes, which have the greatest power for classification, is of fundamental and practical importance to the investigation of specific discriminant problems, such as cancer versus non-cancer or different tumor types. In this paper, we propose a two-stage selection algorithm by combining Minimum Redundancy Maximum Relevance (MRMR) and Genetic Algorithm (GA). In the first stage, MRMR is used to filter noisy and redundant genes in high dimensional microarray data. In the second stage, GA and SVM work together for selecting the highly discriminating genes. The proposed method is tested on five open datasets: NCI, Lymphoma, Lung, Leukemia and Colon. In the experiments, we compare our proposed MRMR-GA algorithm with GA-SVM wrapper and MRMR filter. The experimental results show that the proposed method has excellent selection and classification performances.

In this paper, we propose a novel feature extraction scheme based on the multi-resolution curvelet transform for face recognition. The obtained curvelet coefficients act as the feature set for classification, and are used to train the ensemble-based discriminant learning approach, capable of taking advantage of both the boosting and LDA (BLDA) techniques. The proposed method CV-BLDA has been extensively assessed using different databases: the ATT, YALE and FERET, Tests indicate that using curvelet-based features significantly improves the accuracy compared to standard face recognition algorithms and other multi-resolution based approaches.

In this paper, based on a set of Ultra Wide Bandwidth Channel (UWB) measurements the dependance between Path Loss and frequency is investigated. The measurements are provided in frequency domain over a channel bandwidth 6 GHz (from 3 to 9 GHz) in different locations. A Vector Network Analyzer is used to measure the frequency channel response of the frequency bandwidth of interest. An Omni-directional antennas are used for both the transmitter (Tx) and receiver (Rx) antennas. Probability Density Function (PDF) and Cumulative Distribution Function (CDF) of received signal, power variation and path loss fluctuations are evaluated in frequency domain. An investigation of path loss shows no dependency between frequency and the path loss, but the path loss and central frequency present a correlation.

1Next generation wireless personal area networks (WPAN) are intended for a variety of applications. The Multiband OFDM Alliance (MBOA) is currently developing a new physical layer (PHY) and medium access control (MAC) protocol, which fit the needs of this mass market. The MBOA standards provide wireless technology offering data rates of up to 480 Mbit/s [1]. Motivated by the sub-band approach, this paper presents measurement analysis of the mean (excess) delay, RMS delay spread and number of significants paths for different locations. First, we present the channel measurements based in this study. Secondly, the interpretation of the obtained results show a correlation between the channel bandwidth and the tow main dispersion parameters namely τrmsand τmin all tested settings, Laboratory, Corridor and Outdoor. Our measurement included terminal separations of 1 – 14 meters, the based data are for terminal separation 6 m.

In a wireless sensor network (WSN), nodes are battery powered, therefore, there are energy constrained. Network lifetime is one of the most important characteristics of performance for wireless sensor networks. A number of routing schemes, energy efficient and energy-aware, have been proposed to maximize the network lifetime. These schemes typically try to find the minimum energy path to optimize energy usage at a node. In this paper, we consider the lifetime maximization problem, we propose a routing protocols that take into account the battery residual energy in sensor nodes and the energy required for transmission along the path. For each transmission round, only the nodes which have their remaining energies greater than a threshold can participate as relays for other nodes data in addition to sensing the environment. This choice allows the distribution of energy load among any sensor nodes, thus extends network lifetime. Simulation results show that the network lifetimes is increased largely comparable to direct and MTE schemes.

In this paper, an efficient local appearance feature extraction method based steerable pyramid (S-P) is proposed for face recognition. Local information is extracted from S-P sub-bands using block-based statistics. The underlying statistics allow us to reduce the required amount of data to be stored. The obtained local features are combined at the feature and decision level to enhance face recognition performance. Experimental results on ORL, Yale and FERET face databases convince us that the proposed method provides a better representation of the class information and obtains much higher recognition accuracies.

We investigate the probability tree models to approximate skin and non-skin distributions. These models have presented good results in solving the skin detection problem. However, there are two main disadvantages of the existing skin/non-skin tree distributions based models: (1) the structure of some tree distributions is predefined; and (2) the inter and the intra classes of skin/non-skin are not taken into account at the same time by the existing skin and/or non-skin tree models. To overcome these drawbacks, we propose a new classifier based on an image patch joint distribution approximation modelled by a discriminative skin/non-skin tree. On the Compaq database, we examine the performances of the proposed approach compared with the baseline model and two others based on dependency tree's distributions. Experimental results show that the new approach is a significant improvement over the others.

This paper aims to improve H.264 bit-rate control. The proposed algorithm is based on a new and efficient rate-quantization (R-Q) model for the intra frame. For the inter frame, we propose to replace the current use of MAD by a new MAD-based human contrast sensitivity (MAD-CS) which is a more accurate complexity measure. R-Q model for the intra frame results from extensive experiments. The optimal initial quantization parameter QP is based on both target bit-rate and complexity of I-frame. The I-frame target bit-rate is derived from the global target bit-rate by using a new non linear model. MAD-CS includes the contrast sensitivity of the human visual system and weights the absolute differences by the probability of their occurrence. Extensive simulation results show that the use of MAD-CS and the proposed R-Q model achieves better rate control for intra frames, reduces the bit-rates when compared to the H.264 rate control adopted in JM reference software, minimizes the peak to signal ratio variations among encoded pictures and increases significantly as well subjective visual quality (measured by psycho visual experiments) as objective one.

In this paper, we present a system for aircraft automatic target recognition (ATR) using inverse synthetic aperture radar (ISAR) and based on knowledge discovery from data process adapted to radar domain. We propose a method for target shape extraction from ISAR images based on the combination of two methods, SUSAN modified and active deformable contours via level set. In the second part of this work, we propose to fuse two commonly used shape descriptors algorithms based on moments invariant and Fourier descriptors. We have investigated the impact of the information fusion on the recognition rate. The classification scheme is ensured using support vector machine (SVM) classifier. Several combination strategies are compared at score/decision/feature level. Experimental results of the proposed method are provided and discussed.

In this paper, we propose a highly efficient algorithm to model the human skin color. The underlying algorithm involves generating a discrete Cosine transform (DCT) at each pixel location, using the surrounding points. These DCT coefficients are assumed to follow a generalized Gaussian distribution (GGD). Next, the model parameters are estimated using the maximum-likelihood (ML) criterion applied to a set of training skin samples. Finally, each pixel is classified as skin or the opposite if its likelihood ratio is above some threshold. The experimental results show that our model avoids excessive false detection while still retaining a high degree of correct detection.

We examine the problem of how to discriminate between objects of more than two classes using psilaminimum informationpsila. This paper presents an efficient face recognition system, based on discrete cosine transform (DCT) and support vector machines (SVM). The idea is to reduce dimensionality of face space. DCT is used to extract pertinent information which represent low frequency in each block. Then the extracted DCT coefficients are used as features for the classification process, which is performed using SVM. The proposed approach was thoroughly tested, using ORL face databases. The obtained results are very encouraging, outperforming traditional methods like PCA, LDA or DCT based MLP in recognition systems.

A great challenge of text mining arises from the increasingly large text datasets and the high dimensionality associated with natural language. In this research, a systematic study is conducted in the context of the document clustering, using the recently introduced diffusion framework and some characteristics of the singular value decomposition. This study is three-fold. First, we propose to construct a diffusion kernel based on the cosine distance. Second, we compare the performances of the k-means algorithm in four different vector spaces: Salton space, latent semantic analysis space, diffusion space based on the cosine distance, and diffusion space based on the Euclidian distance. Third, we undertake a statistical study of the k-means algorithm in the LSA space and the diffusion space based on the cosine distance. In most of our experiments, k-means in diffusion space, based on the cosine distance performs better. In addition, the running time in this space is negligible compared to the time needed for k-means in Salton space.

To improve information retrieval system performances, it seems important to identify key phrases which constitute a better representation of text semantic content than single word terms. In this paper, we adapt the standard method for multi-word term extraction for Arabic language. We define the linguistic specifications and develop a term extraction tool. We experiment the term extraction program for document retrieval in a specific domain, evaluate two kinds of multi-word term weighting functions considering either the corpus or the document, and demonstrate the efficiency of multi-word term indexing for both weighting up to 5.8% of average precision.

In this paper we propose a new automatic face tracking method using the gray information. The method uses the gray information for extracting online the color skin of the main person. Therefore the proposed method is more robust than other approaches that uses a given database of skin, and more practical than methods witch uses manual initialization. The proposed framework combines face detection, on line skin color extraction, Kalman filter, and Gaussian skin color model for robust face tracking. The system is relatively insensitive to illumination conditions. In fact the system is able to track the face in the presence of blue light for example.

This paper addresses the problem of blind source separation (BSS). To recover original signals, from linear instantaneous mixtures, we propose a new separation technique based on the use of a double referenced system. The reference signals will be incrusted in the cumulant to evaluate the statistical independence between sources. The non-orthogonal joint diagonalization of a set of referenced cumulant matrices gives an estimation of the separating matrix. The important advantage of our proposed technique is the high separation quality in noisy environment by an appropriate choice of reference signals. Computer simulations are presented to illustrate the effectiveness of the suggested approach.

This paper presents and evaluates the use of the maximum mutual information criterion to textural feature selection for satellite image classification. Our approach is based on a recent work of Mutual Information Feature Selector Algorithm. The effectiveness of the proposed approach is evaluated on real data. In fact, the textural features are extracted using the cooccurrence matrix from two forest zones of SPOT HRV(XS) image in the region of Rabat, Morocco. The experimental tests of this study prove that the proposed approach gives a better performance for satellite image classification than classical methods such as principal components analysis (PCA) and linear discriminant analysis (LDA). The classifier used in this work is the support vectors machine (SVM).

In this paper, a robust watermarking scheme based on Dual Tree Complex Wavelet Transform (DT-CWT) is proposed. The embedded watermark image is preprocessed with a random location matrix. The original image is transformed in the complex wavelet domain by using DT-CWT, then, according to the characteristics of the image data, the preprocessed watermark image is adaptively spread spectrum and added into the host image DT-CWT coefficients. The watermark detection process is accomplished without referring to the original image. Simulation results are presented to demonstrate the effectiveness of the proposed algorithm.

This paper is concerned with blind separation of convolutive mixtures of spatially independent, and temporally possible non linear processes. We consider the MIMO extraction based on the maximization of a contrast function. A new self-styled referenced contrast (RC) function is proposed, which is based on cross-trispectra between the estimated output and a reference signal. Using Parsevals formula, the former criterion yields a new class of time-domain contrast. It presents two main advantages over other more traditional contrasts. Firstly, it concerns the computational cost, and secondly the extension takes into consideration the extraction of the independent sources in the presence of Gaussian sources by making some constraints on the reference signals. There is no comparison with other methods because this is the first technique that deals with this kind of signals in the convolutif mixtures.

In this paper, we introduce a hierarchical classification approach in the incremental framework of speaker indexing. The technique of incremental generation of speaker-homogeneous segments is applied in the first phase. Then, we propose a hierarchical classification approach that applied in the speaker indexing framework. This approach benefits from the efficiency of Gaussian mixture model (GMM) merge algorithm to the high accuracy of update Gaussian mixture models which referenced by speakers tree index. The adaptive threshold algorithm reduces the cost of exploring the speakers GMM into the balanced binary tree of speaker's index, whose complexity becomes logarithmic curve

This paper deals with the problem concerning the framework of rotating machines diagnostics by using signal processing advanced tools and more precisely blind source separation (BSS) methods. An application on gear box is given, the objective is to separate gear mesh signals corresponding to each reducer's wheel. It enables us to diagnose and separate each defect in the event of degradation. The proposed method exploits the information redundancy around the meshing frequency and its harmonics resulting from cyclostationarity properties. This redundancy allows us to separate the contribution of each wheel from only one sensor, by tacking advantage of the non-uniformity of the mechanical structure frequency response (MSFR) connecting the exciting source to the sensor

In this paper we propose an optimal and robust correlation technique for the local motion estimation purposes. It is based on the maximization of a statistical robust matching function, which is computed in the frequency domain and therefore can be implemented by fast transformation algorithms. We show that our method achieves a significant speed up and robustness over the full search block-matching algorithm. We also present a comparative performance analysis, which shows that the proposed method greatly outperforms the state-of-the-art in correlation motion estimation.

In this paper, a new spatiotemporal filtering scheme is described for noise reduction in video sequences. For this purpose, the scheme processes each group of three consecutive sequence frames in two steps: 1) estimate motion between frames and 2) use motion vectors to get the final denoised current frame. A family of adaptive spatiotemporal L-filters is applied. A recursive implementation of these filters is used and compared with its nonrecursive counterpart. The motion trajectories are obtained recursively by a region-recursive estimation method. Both motion parameters and filter weights are computed by minimizing the kurtosis of error instead of mean squared error. Using the kurtosis in the algorithms adaptation is appropriate in the presence of mixed and impulsive noises. The filter performance is evaluated by considering different types of video sequences. Simulations show marked improvement in visual quality and SNRI measures cost as well as compared to those reported in literature.

The standard phase correlation method has been known as a powerful image processing technique for grey levels image registration and motion estimation, yet its use has, in general, been limited to grey level images. Here, we propose an efficient extension of phase correlation technique, with global and inter color channel measures. Our proposed extension is based on a new reversible and integer color space transformation.

The paper aims at characterizing the second order statistics of indoor ultra-wideband (UWB) channels using channel sounding techniques. We present measurement results for different scenarios conducted in a laboratory setting at Institut Eurecom. These are based on a eigendecomposition of the channel autocovariance matrix, which allows for determining the growth in the number of significant degrees of freedom of the channel process as a function of the signaling bandwidth as well as the statistical correlation between different propagation paths. We show empirical eigenvalue distributions as a function of the signal bandwidth for both line-of-sight and non line-of-sight situations. Furthermore, we give examples where paths from different propagation clusters (possibly arising from reflection or diffraction) show strong statistical dependence.

In this letter, we consider contrast functions, which are useful tools for the sources separation problem. We present new generalized contrasts by considering a so-called reference signal. In particular, this allows us to show that a criterion recently proposed in the literature is a contrast. Furthermore, a link with a joint-diagonalization criterion is also emphasized. Finally, we show that another classical contrast can also be extended by considering a reference signal.

A two-dimensional (2-D) autoregressive (AR) model driven by a non-Gaussian zero-mean independent identically distributed 2-D sequence is considered. The input sequence is not observed. The signal observations may be contaminated by additive Gaussian noise. We consider the problem of model order determination using higher order cumulants of the 2-D signal. We show that the necessary information to determine the 2-D AR model order is implicitly contained in a specific cumulant matrix. The algorithm is based on the computation of three matrix ranks via singular value decomposition. The proposed approach is illustrated via computer simulations.

This paper presents a new algorithm of disparity map estimation. The originality of this method lies in the process of dense disparity map estimation using dynamic programming constrained by interest points and using the higher order statistics (HOS) criteria for matching noisy images. Experiments with noisy real images have validated our method and have clearly shown the improvement over the existing ones. The dense disparity map obtained is more reliable when compared to the similar second-order statistics (SOS)-based dynamic programming and HOS-based correlation methods.

This paper presents a 3-D adaptive Volterra filter with an LMS type adaptation algorithm. This filter is used for equalizing an unknown channel with some point-wise nonlinearity and restoring image sequences degraded by this channel. First a robust higher order statistics (HOS) based motion estimation method is employed. Then, a 3-D Volterra equalizer is applied. The performance of this algorithm is demonstrated using real image sequences.

This paper presents a new algorithm of disparity map segmentation in planar facets. The origins of this method lie in the process of dense disparity map estimation, using the dynamic programming subject to interest points previously extracted. The segmentation of this map uses the normal vector at each pixel surface. The matching of pixels between the two images by dynamic programming provides us with a scattered disparity map. So the densification of this map is achieved by matching contour points extracted between the two available images. Experiments with real images have validated our method and have clearly shown the improvement over the existing methods. The dense disparity map obtained is reliable when compared to classical methods. We also get a normal vector map segmented in contours and in homogeneous regions reflecting 3D planar facets.

In this paper, we present a new fractal-based indexing scheme that can handle different variations and disturbances of the query image. Our approach is a "query-by-example" approach based on the convergence speed of the decompression process. It consists in one application of the stored image iterated function system (IFS) to the query one. Two questions can then be answered. The first one is the existence of the query: if it exists in the database we find it immediately. The second concerns the retrieval of similar images which are given in order of similarity to the query. The disimilarity measure is expressed in terms of mean and variance of the image. Other measures are under study. Experimental results, using images from Vistex databases of MIT, to demonstrate the validity of the approach, shows the robustness and tolerance of the method to different kind of disturbance.

It is shown that the spectral difference between a short vowel and its long counterpart in the Arabic language can be neglected for isolated vowels. The analysis technique used is time-varying linear predictive coding. To obtain the set of parameters corresponding to an analysis duration T, the reconstruction of the same segment with different durations is performed automatically. The excitation of the LPC synthesis filter is provided by a modified multipulse algorithm. The intelligibility of the synthetic long vowels is satisfactory.>

In explosion seismology, the arrival time determination of reflected waves is the fundamental problem in relating seismograms to the subsurface structure. A robust method, combining both energitical and zero-crossings analyses of the signal, is proposed. The basic idea is to analyse the variations of the signal power computed between consecutive zero-crossings. In order to handle noisy signals, discrimination of the effects of noise on the so-computed power is performed by means of an unsupervised automatic classification procedure. Synthetic signals and field data, recorded in the south of Morocco, have been used to illustrate the performance of the procedure.

In explosion seismology, computer detection of reflected waves is the most important process in relating seismograms to subsurface structure. In this paper the analysis of the complex oscillations of the seimometers is undertaken in the phase plane. The variations of the "phase plane velocity", defined as the velocity of the point moving along the phase trajectory, reflect the changing properties of a dynamic model of the seismic signal. A procedure is presented that determines the arrival times of the waves by segmenting the signals into intervals where the "phase plane velocity" tends to vary in a monotonic manner. Field results show that the arrival times can be precisely identified.