WorldCat Identities

Aboutajdine, Driss

Overview
Works: 47 works in 68 publications in 3 languages and 212 library holdings
Genres: Conference papers and proceedings 
Roles: Editor, Thesis advisor, Other, htt, Contributor, Opponent
Classifications: TA1637, 006.42
Publication Timeline
.
Most widely held works by Driss Aboutajdine
Image and Signal Processing : 5th International Conference, ICISP 2012, Agadir, Morocco, June 28-30, 2012. Proceedings by Abderrahim Elmoataz( )

6 editions published in 2012 in English and held by 50 WorldCat member libraries worldwide

This book constitutes the refereed proceedings of the 5th International Conference on Image and Signal Processing, ICISP 2012, held in Agadir, Morocco, in June 2012. The 75 revised full papers presented were carefully reviewed and selected from 158 submissions. The contributions are grouped into the following topical sections: multi/hyperspectral imaging; image itering and coding; signal processing; biometric; watermarking and texture; segmentation and retieval; image processing; pattern recognition
Image and signal processing : 5th International Conference, ICISP 2012, Agadir, Morocco, June 28-30, 2012. Proceedings by ICISP (Conference)( )

3 editions published in 2012 in English and German and held by 24 WorldCat member libraries worldwide

This book constitutes the refereed proceedings of the 5th International Conference on Image and Signal Processing, ICISP 2012, held in Agadir, Morocco, in June 2012. The 75 revised full papers presented were carefully reviewed and selected from 158 submissions. The contributions are grouped into the following topical sections: multi/hyperspectral imaging; image itering and coding; signal processing; biometric; watermarking and texture; segmentation and retieval; image processing; pattern recognition
Image et vidéo( Book )

1 edition published in 2000 in French and held by 22 WorldCat member libraries worldwide

Proceedings of 2013 International Conference on Industrial Engineering and Systems Management (IESM) 28-30 Oct. 2013, Rabat, Morocco( )

1 edition published in 2013 in English and held by 17 WorldCat member libraries worldwide

2010 5th International Symposium on I/V Communications and Mobile Network (ISVC) Sept. 30, 2010 - Oct. 2, 2010, Rabat, Morocco( )

1 edition published in 2010 in English and held by 16 WorldCat member libraries worldwide

IEEE - IESM'2013 : proceedings of 2013 International Conference on Industrial Engineering and Systems Management (IESM) : October 28-30, 2013, Rabat, Morocco by International Conference on Industrial Engineering and Systems Management( )

1 edition published in 2013 in English and held by 14 WorldCat member libraries worldwide

Image and signal processing : 4th international conference, ICISP 2010, Trois-Rivieres, QC, Canada, June 30-July 2, 2010 ; proceedings by Abderrahim Elmoataz( Book )

1 edition published in 2012 in English and held by 6 WorldCat member libraries worldwide

This volume constitutes the refereed proceedings of the 7th International Conference, ICISP 2016, held in May/June 2016 in Trois-Rivières, QC, Canada. The contributions are organised in topical sections on features extraction, computer vision, and pattern recognition; multispectral and color imaging; image filtering, segmentation, and super-resolution; signal processing; biomedical imaging; geoscience and remote sensing; watermarking, authentication and coding; and 3d acquisition, processing, and applications
Reconnaissance de formes et d'objets en environnement incertain : application à la reconnaissance de cibles radar by Mohamed Nabil Saidi( )

2 editions published in 2010 in French and held by 3 WorldCat member libraries worldwide

This thesis presents Radar Automatic Target Recognition (RATR) in uncertam environment using Inverse Synthetic Aperture Radar (ISAR) images. By including the human operator in the system, the recognition process 15 achieved from the acquisition step aux! the image reconstruction to the features extraction and the classification step. The methodology adopted in this thesis is inspired from the artificial intelligence approach. This methodology is known as Knowledge Discovery from Data (KDD) which we have adapted to radar target recognition system. After the radar signal acquisition from an ahechoic chamber of ENSIETA (Brest, France) and the ISAR images reconstruction by Fourier analysis, the most discriminant features, in particular the shapes of targets are extracted. The classification stage is performed by supervised methods such as Support Vector Machines (SVM) and K-Nearest Neighbors (K-NN). Then, we investigate the impact of information fusion on recognition performance using fusion methods like the theory of belief functions and the majority vote rule. Finally, we propose another approach that included the pose of the targets in the recognition system
Comparaison des représentations temps-fréquence de signaux présentant des discontinuités spectrales by Y Grenier( )

1 edition published in 1983 in French and held by 2 WorldCat member libraries worldwide

Conception et usage des composants métier processus pour les systèmes d'information by Rajaa Saidi( Book )

2 editions published in 2009 in French and held by 2 WorldCat member libraries worldwide

Les Systèmes d'Information (SI) de même domaine d'activité gèrent de nombreux concepts similaires. Ces concepts peuvent être analysés et généralisés dans des abstractions informatiques qui seront réutilisées lors de nouveaux développements. De telles abstractions sont appelées Composants Métier (CM). Cependant, il est souvent difficile d'expliciter des critères clairs de réutilisation, en particulier la manière dont on peut identifier, spécifier, organiser et en grande partie automatiser la réutilisation de ces CM. Les contributions de cette thèse adressent cette problématique et s'articulent autour de trois principaux résultats. La première contribution concerne un modèle de CM de nature processus appelé « CMP ». Ce modèle est centré sur les propriétés fonctionnelles des composants. L'accent est mis sur la complétude et la variabilité de la solution exprimée sous la forme de quatre vues complémentaires intégrant des points de variation. Le travail réalisé sur les mécanismes de spécification de la variabilité a abouti à un profil UML pouvant être utilisé pour modéliser non seulement des processus réutilisables mais aussi des processus flexibles. Une deuxième contribution s'inscrit dans le cadre de la proposition d'un processus permettant la spécification d'un CMP selon le modèle proposé. Dans ce processus, nous définissons un ensemble de règles de construction, de traduction et de cohérence qui assurent la traçabilité des artefacts produits tout au long du cycle de développement. Une troisième contribution concerne la proposition de directives qui assistent l'ingénieur de SI lors de la réutilisation de CMP. L'accent est particulièrement mis sur la proposition d'un formalisme de documentation et de classification de CMP validé dans le cadre d'un environnement de stockage de composants. Nous proposons également un processus d'imitation intégré à la méthode de développement Symphony et permettant de tirer partie de la spécification d'un CMP lors de la conception d'un SI. L'ensemble des propositions est accompagné d'outils et d'expérimentations utilisateurs servant de supports de validation et de mise en œuvre des travaux réalisés
Special issue image video communication( Book )

1 edition published in 2002 in English and held by 2 WorldCat member libraries worldwide

Apport de l'hypothèse de cyclostationnarité dans le cadre de séparation de mélanges convolutifs : application à des signaux mécaniques et biomécaniques by Khalid Sabri( Book )

2 editions published in 2008 in French and held by 2 WorldCat member libraries worldwide

Le sujet abordé dans cette thèse consiste à l'étude et au développement de méthodes en identification aveugle MIMO et en Séparation Aveugle de Sources (SAS) dans le cadre des mélanges convolutifs en exploitant les propriétés de cyclostationnarité. Le choix de l'hypothèse de cyclostationnarité est guidé par le souci d'appliquer ces méthodes aux signaux réels qui présentent en effet des propriétés de cyclostationnarité. De nouvelles méthodes qui utilisent les matrices spectrales cycliques ont été proposées tout au long de cette thèse. En effet, le problème majeur associé avec les approches fréquentielles, cependant, est de retrouver la permutation et la phase à chaque canal de fréquence. Les ambiguïtés de permutation et de phase ont été corrigées par exploitation des propriétés de cyclostationnarité à l'ordre deux au moyen de différentes techniques. Ainsi, à chaque canal de fréquence, le système séparant est identifié, ensuite les sources sont restaurées à la sortie et les canaux dans le domaine temporel sont formés par la transformée de Fourier discrète inverse
Efficient deployment quality analysis for intrusion detection in wireless sensor networks by Noureddine Assad( )

1 edition published in 2015 in English and held by 2 WorldCat member libraries worldwide

Modeling of Video Sequences by Gaussian Mixture: Application in Motion Estimation by Block Matching Method by Abdenaceur Boudlal( )

1 edition published in 2010 in English and held by 2 WorldCat member libraries worldwide

An Evaluation of Routing Protocols for Vehicular Ad-Hoc Network Considering the Video Stream by Imane Zaimi( )

1 edition published in 2017 in English and held by 2 WorldCat member libraries worldwide

A corroborative study on improving pitch determination by time-frequency cepstrum decomposition using wavelets by Fadoua Bahja( )

1 edition published in 2016 in English and held by 2 WorldCat member libraries worldwide

Optimisation du contrôle de débit de H.264/AVC basée sur une nouvelle modélisation Débit-Quantification et une allocation sélective de bits by Miryem Hrarti( Book )

2 editions published in 2011 in French and held by 2 WorldCat member libraries worldwide

The explosion of multimedia applications is largely due to the efficiency of the compression techniques used. H.264/AVC, also known as MPEG-4 Part 10 is the newest video coding standard. It is more effective than previous standards (MPEG1, MPEG2, part 4, H26x...) and achieves significant compression gains. As for other standards, the rate control is a key element of H.264/AVC because it helps to regulate the visual quality of the reconstructed sequence while respecting the bandwidth constraints imposed by the channel transmission. In accordance with the specified target bit-rate, the rate control algorithm determines appropriately the quantization parameters. Basically, a first Rate-Quantization function elaborates a relationship between the rate and the quantization parameter (QP). A second function called Distortion-Quantization estimates the distortion (or quality) of the reconstructed video based on the used quantization parameter. These two functions lead together to a relationship (usually quadratic) between the quantization parameter, the target number of bits and the basic unit (Frame, Slice, macroblock or set of macroblocks) statistics. These functions have been the subject of several studies. The models that have been adopted and therefore recommended by the group standardization, do not generally offer better performances and they are far from optimal. This thesis is in this context. Its main objective is to develop and design new techniques to improve the performance of the rate control algorithm and those of the H.264/AVC standard. These techniques are based on both a detailed analysis of the major current limitations and a wide literature review. Our purpose is to provide a more appropriate determination of the quantization parameter, a selective bit allocation that integrates Human Visual System properties and enhances the reconstructed video quality. To determine accurately the quantization parameter, two Rate-Quantization models (R-Q) have been proposed. The first model designed for Intra-Frames, is a non-linear one. It is used to determine the optimal initial quantization parameter, while exploiting the relationship between the target bit-rate and the complexity of Intra-Frames. The second model is a logarithmic one and it is designed for Inter coding units. It replaces the two models used by the H.264/AVC rate controller and reduces the computational complexity. The frame layer bit allocation of the H.264/AVC baseline profile remains basic. It assumes that GOPs (Groups Of Pictures) have similar characteristics and the target number of bits are fairly allocated to coding units regardless of their complexity. For a more accurate bit allocation, a new model has been proposed including two complexity measures. The first is a motion ratio determined from the actual bits used to encode the previous frames. The second measure uses the difference between adjacent frames and the histogram of this difference. Finally, to better control the visual quality of the reconstructed video, a saliency map is included into the bit allocation process. The saliency map generated by a bottom-up approach, simulates the human visual attention. It has been used to adjust the quantization parameter at frame layer. This adjustment allows the assignment of more bits to frames containing more salient regions (supposed to be more important than others). At macroblock layer, the saliency map is exploited to efficiently allocate the number of bits among the macroblocks of the same frame. This bit repartition by ''region'' of interest improves the visual quality of the frame. Experimental simulations show that the proposed models, when compared with two recent algorithms of rate control (JVT-O016 and JM15.0), improve significantly the coding performances in terms of average bit-rates and PSNR. More consistent quality and therefore a quality smoothness through frames is also observed
Reconnaissance automatique du locuteur par des GMM à grande marge by Reda Jourani( Book )

2 editions published in 2012 in French and held by 2 WorldCat member libraries worldwide

Most of state-of-the-art speaker recognition systems are based on Gaussian Mixture Models (GMM), trained using maximum likelihood estimation and maximum a posteriori (MAP) estimation. The generative training of the GMM does not however directly optimize the classification performance. For this reason, discriminative models, e.g., Support Vector Machines (SVM), have been an interesting alternative since they address directly the classification problem, and they lead to good performances. Recently a new discriminative approach for multiway classification has been proposed, the Large Margin Gaussian mixture models (LM-GMM). As in SVM, the parameters of LM-GMM are trained by solving a convex optimization problem. However they differ from SVM by using ellipsoids to model the classes directly in the input space, instead of half-spaces in an extended high-dimensional space. While LM-GMM have been used in speech recognition, they have not been used in speaker recognition (to the best of our knowledge). In this thesis, we propose simplified, fast and more efficient versions of LM-GMM which exploit the properties and characteristics of speaker recognition applications and systems, the LM-dGMM models. In our LM-dGMM modeling, each class is initially modeled by a GMM trained by MAP adaptation of a Universal Background Model (UBM) or directly initialized by the UBM. The models mean vectors are then re-estimated under some Large Margin constraints. We carried out experiments on full speaker recognition tasks under the NIST-SRE 2006 core condition. The experimental results are very satisfactory and show that our Large Margin modeling approach is very promising
Méthodes d'extraction de l'information spatiale et de classification en imagerie de télédétection : applications à la cartographie thématique de la région d'Agadir (Maroc) by Soufiane Idbraim( Book )

2 editions published in 2009 in English and held by 2 WorldCat member libraries worldwide

The work of this thesis focuses around two axes: the classification for the mapping of land cover and the extraction of roads from satellite and aerial images. The first axis aims to propose a method of classification which takes in account the spatial information contained in a satellite image. Thus, we developed a method of Markov classification with the search for the optimal solution by an ICM (Iterated Conditional Mode) algorithm. This method is parameterized by a new factor of temperature, this parameter will allow, first, to rule the tolerance of the disadvantageous configurations during the evolution of the classification process, and secondly, to ensure the convergence of the algorithm in a reasonable time of calculation. In parallel, we introduced a new contextual constraint of the segmentation in the algorithm. This constraint will allow, over the iterations, to refine the classification by accentuating the detected details by the segmentation contours. The second axis of this thesis is the extraction of roads from satellite and aerial images. We proposed a completely automatic methodology with an extraction system in blocks which act separately and independently on the image. The first block operates a directional adaptive filtering, allowing detecting roads in each window of the image according to the dominant directions. The second one applies segmentation, and then selects the segments representing roads according to a criterion of the segment form. These two blocks provide a different type of information on the studied image. These results are then complemented with a third block to generate an image of the road network. The performances of the proposed methodologies are verified through examples of satellite and aerial images. In general, the experimental results are encouraging
Biométrie faciale 3D par apprentissage des caractéristiques géométriques : application à la reconnaissance des visages et à la classification du genre by Lahoucine Ballihi( Book )

2 editions published in 2012 in French and held by 2 WorldCat member libraries worldwide

Since facial biometric recognition is contactless, non-intrusive, and somehow natural (i.e more accepted by end-users), it emerges as one attractive way to achieve identity recognition. Unfortunately, 2D-based face technologies (still image or image sequence) still face difficult challenges such as pose variations, changes in lighting conditions, occlusions, and facial expressions. Over the last ten years, face recognition using the 3D shape of the face has become a major research area due to its robustness to lighting conditions and pose variations. Most of state-of-the-art works focused on the variability caused by facial deformations and proposed methods robust to such shape variations. Achieving good performances in automatic 3D face recognition and gender classification is an important issue when developing intelligent systems. In this thesis we propose a unified framework, which is fully automatic 3D face recognition and gender classification. We propose to represent a 3D facial surface by a set of radial curves and iso-level curves. The proposed framework combines machine learning techniques (Boosting, etc.) and Riemannain geometry-based shape analysis in order to select relevant facial curves extracted from 3D facial surfaces. The feature selection step improves the performances of both our identity recognition and gender classification approaches. Besides, the set of the obtained relevant curves provides a compact signature of 3D face, which significantly reduces the computational cost and the storage requirements for face recognition and gender classification.. The main contributions of this thesis include:1) A new geometric feature selection approach for efficient 3D face recognition, which operating the most relevant characteristics to resolve the challenge of facial expressions. In particular, we are interested in selecting facial curves that are most suitable for 3D face recognition by using machine learning techniques.2) A new gender classification approach using the 3D face shape represented by collections of curves. In particular, we are interested in finding the set of facial curves that are most suitable for gender discrimination.Exhaustive experiments were conducted on the FRGCv2 database, the obtained results were compared with those of the state-of-the-art work, and the effectiveness of local geometric shape analysis of facial surfaces combined with machine learning techniques were outlined
 
moreShow More Titles
fewerShow Fewer Titles
Audience Level
0
Audience Level
1
  General Special  
Audience level: 0.00 (from 0.00 for Image and ... to 0.00 for Image and ...)

Image and Signal Processing : 5th International Conference, ICISP 2012, Agadir, Morocco, June 28-30, 2012. Proceedings Image and signal processing : 4th international conference, ICISP 2010, Trois-Rivieres, QC, Canada, June 30-July 2, 2010 ; proceedings
Covers
Image and signal processing : 4th international conference, ICISP 2010, Trois-Rivieres, QC, Canada, June 30-July 2, 2010 ; proceedings
Alternative Names
Aboutajdine, D.

Languages
English (19)

French (14)

German (1)