CNRS Laboratory of Image Signal and Intelligent Systems

Creteil, France

CNRS Laboratory of Image Signal and Intelligent Systems

Creteil, France
SEARCH FILTERS
Time filter
Source Type

Boussad I.,University of Science and Technology Houari Boumediene | Chatterjee A.,Jadavpur University | Siarry P.,CNRS Laboratory of Image Signal and Intelligent Systems | Ahmed-Nacer M.,University of Science and Technology Houari Boumediene
Computers and Operations Research | Year: 2011

The present paper proposes a new stochastic optimization algorithm as a hybridization of a relatively recent stochastic optimization algorithm, called biogeography-based optimization (BBO) with the differential evolution (DE) algorithm. This combination incorporates DE algorithm into the optimization procedure of BBO with an attempt to incorporate diversity to overcome stagnation at local optima. We also propose to implement an additional selection procedure for BBO, which preserves fitter habitats for subsequent generations. The proposed variation of BBO, named DBBO, is tested for several benchmark function optimization problems. The results show that DBBO can significantly outperform the basic BBO algorithm and can mostly emerge as the best solution providing algorithm among competing BBO and DE algorithms. © 2010 Elsevier Ltd.


Boussaid I.,University of Science and Technology Houari Boumediene | Chatterjee A.,Jadavpur University | Siarry P.,CNRS Laboratory of Image Signal and Intelligent Systems | Ahmed-Nacer M.,University of Science and Technology Houari Boumediene
Computers and Operations Research | Year: 2012

Biogeography-based optimization (BBO) has been recently proposed as a viable stochastic optimization algorithm and it has so far been successfully applied in a variety of fields, especially for unconstrained optimization problems. The present paper shows how BBO can be applied for constrained optimization problems, where the objective is to find a solution for a given objective function, subject to both inequality and equality constraints. To solve such problems, the present work proposes three new variations of BBO. Each new version uses different update strategies, and each is tested on several benchmark functions. A successful implementation of an additional selection procedure is also proposed in this work which is based on the feasibility-based rule to preserve fitter individuals for subsequent generations. Our extensive experimentations successfully demonstrate the usefulness of all these modifications proposed for the BBO algorithm that can be suitably applied for solving different types of constrained optimization problems. © 2012 Elsevier Ltd. All rights reserved.


Chander A.,CNRS Laboratory of Image Signal and Intelligent Systems | Chander A.,Indian Institute of Technology Roorkee | Chatterjee A.,Jadavpur University | Siarry P.,CNRS Laboratory of Image Signal and Intelligent Systems
Expert Systems with Applications | Year: 2011

In this paper, we present a new variant of Particle Swarm Optimization (PSO) for image segmentation using optimal multi-level thresholding. Some objective functions which are very efficient for bi-level thresholding purpose are not suitable for multi-level thresholding due to the exponential growth of computational complexity. The present paper also proposes an iterative scheme that is practically more suitable for obtaining initial values of candidate multilevel thresholds. This self iterative scheme is proposed to find the suitable number of thresholds that should be used to segment an image. This iterative scheme is based on the well known Otsu's method, which shows a linear growth of computational complexity. The thresholds resulting from the iterative scheme are taken as initial thresholds and the particles are created randomly around these thresholds, for the proposed PSO variant. The proposed PSO algorithm makes a new contribution in adapting 'social' and 'momentum' components of the velocity equation for particle move updates. The proposed segmentation method is employed for four benchmark images and the performances obtained outperform results obtained with well known methods, like Gaussian-smoothing method (Lim, Y. K.; & Lee, S. U. (1990). On the color image segmentation algorithm based on the thresholding and the fuzzy c-means techniques. Pattern Recognition, 23, 935-952; Tsai, D. M. (1995). A fast thresholding selection procedure for multimodal and unimodal histograms. Pattern Recognition Letters, 16, 653-666), Symmetry-duality method (Yin, P. Y.; & Chen, L. H. (1993). New method for multilevel thresholding using the symmetry and duality of the histogram. Journal of Electronics and Imaging, 2, 337-344), GA-based algorithm (Yin, P. -Y. (1999). A fast scheme for optimal thresholding using genetic algorithms. Signal Processing, 72, 85-95) and the basic PSO variant employing linearly decreasing inertia weight factor. © 2010 Elsevier Ltd. All rights reserved.


Hadj Slimane Z.-E.,Abou Bekr Belkaid University Tlemcen | Nait-Ali A.,CNRS Laboratory of Image Signal and Intelligent Systems
Digital Signal Processing: A Review Journal | Year: 2010

In this paper, we present a new Empirical Mode Decomposition based algorithm for the purpose of QRS complex detection. This algorithm requires the following stages: a high-pass filter, signal Empirical Mode Decomposition, a nonlinear transform, an integration and finally, a low-pass filter is used. In order to evaluate the proposed technique, the well known ECG MIT-BIH database has been used. Moreover it is compared to a reference technique, namely "Christov's" detection method. As it will be shown later, the proposed algorithm allows to achieve high detection performances, described by means both the sensitivity and the specificity parameters. © 2009 Elsevier Inc. All rights reserved.


Harnrnouche K.,Mouloud Mammeri University | Diaf M.,Mouloud Mammeri University | Siarry P.,CNRS Laboratory of Image Signal and Intelligent Systems
Engineering Applications of Artificial Intelligence | Year: 2010

The multilevel thresholding problem is often treated as a problem of optimization of an objective function. This paper presents both adaptation and comparison of six meta-heuristic techniques to solve the multilevel thresholding problem: a genetic algorithm, particle swarm optimization, differential evolution, ant colony, simulated annealing and tabu search. Experiments results show that the genetic algorithm, the particle swarm optimization and the differential evolution are much better in terms of precision, robustness and time convergence than the ant colony, simulated annealing and tabu search. Among the first three algorithms, the differential evolution is the most efficient with respect to the quality of the solution and the particle swarm optimization converges the most quickly. © 2009 Elsevier Ltd. All rights reserved.


Madani K.,CNRS Laboratory of Image Signal and Intelligent Systems | Sabourin C.,CNRS Laboratory of Image Signal and Intelligent Systems
Neurocomputing | Year: 2011

We propose a machine-learning based multi-level cognitive model inspired from early-ages' cognitive development of human's locomotion skills for humanoid robot's walking modeling. Contrary to the most of already introduced works dealing with biped robot's walking modeling, which place the problem within the context of controlling specific kinds of biped robots, the proposed model attends to a global concept of biped walking ability's construction independently from the robot to which the concept may be applied. The chief-benefit of the concept is that the issued machine-learning based structure takes advantage from "learning" capacity and "generalization" propensity of such models: allowing a precious potential to deal with high dimensionality, nonlinearity and empirical proprioceptive or exteroceptive information. Case studies and validation results are reported and discussed evaluating potential performances of the proposed approach. © 2010 Elsevier B.V.


Nait-Ali A.,CNRS Laboratory of Image Signal and Intelligent Systems
3rd European Workshop on Visual Information Processing, EUVIP 2011 - Final Program | Year: 2011

The aim of this invited paper is to discuss some emerging biometric approaches that are currently under consideration. After presenting the state of the art, including some advanced techniques, the idea of using some specific medical data for the purpose of identifying individuals is considered. This type of biometrics is called hidden biometrics. Its main advantage is its robustness regarding any potential forgeries. For example, when dealing with brain Magnetic Resonance (MR) images as a biometric tool, no one can modify deliberately features of his own brain even if these features can change over the time in case of pathological individuals, or during the growth period (not considered in this study). In particular, a special interest is given to brain MRI and X-Ray based biometrics. Some examples using brain MRI images, Hand and Lung X-Ray are highlighted in this paper. © 2011 IEEE.


Nait-Ali A.,CNRS Laboratory of Image Signal and Intelligent Systems
7th International Workshop on Systems, Signal Processing and their Applications, WoSSPA 2011 | Year: 2011

When dealing with biometrics, we generally refer to security biometrics which is a set of techniques used to identify an individual using his biological or behavioral features. But sometimes, biometrics, in particular medical biometrics, refers to some specific methods that are used to quantify or to measure some parameters extracted from medical data. In this paper, we bridge the gap between the security biometrics and the medical biometrics and we try to discuss and highlight the idea which consists in using medical data, such as biosignals, MRI images and X-Ray images for the purpose of individual identification or verification. This is what we call the "Hidden biometrics" or "Intrinsic biometrics". As we will see, some of the techniques using biosignals are suited for applications requiring frequent up-dates and other approaches which use medical images are particularly robust regarding any potential forgery. © 2011 IEEE.


Bahrammirzaee A.,CNRS Laboratory of Image Signal and Intelligent Systems
Neural Computing and Applications | Year: 2010

Nowadays, many current real financial applications have nonlinear and uncertain behaviors which change across the time. Therefore, the need to solve highly nonlinear, time variant problems has been growing rapidly. These problems along with other problems of traditional models caused growing interest in artificial intelligent techniques. In this paper, comparative research review of three famous artificial intelligence techniques, i. e., artificial neural networks, expert systems and hybrid intelligence systems, in financial market has been done. A financial market also has been categorized on three domains: credit evaluation, portfolio management and financial prediction and planning. For each technique, most famous and especially recent researches have been discussed in comparative aspect. Results show that accuracy of these artificial intelligent methods is superior to that of traditional statistical methods in dealing with financial problems, especially regarding nonlinear patterns. However, this outperformance is not absolute. © 2010 Springer-Verlag London Limited.


Dirami A.,Mouloud Mammeri University | Hammouche K.,Mouloud Mammeri University | Diaf M.,Mouloud Mammeri University | Siarry P.,CNRS Laboratory of Image Signal and Intelligent Systems
Signal Processing | Year: 2013

For the image segmentation by the histogram bilevel thresholding, several methods have been proposed. However, they are computationally time consuming and their effectiveness is reduced when applied to a complex image and when the number of the different regions composing this image is high. In this paper, a fast and efficient method for segmenting complex images is proposed. This method is based on the determination of the number and the values of the thresholds required for the segmentation by introducing a new multilevel thresholding technique using a multiphase level set technique. First, the gray-level histogram of the image is approximated by a weighted sum of Heaviside functions by using the Chan-Vese segmentation model. In order to obtain a better approximation of this histogram and to speed up the calculations, an improved version of the multiphase level set method is introduced. The valleys are then highlighted and isolated by deriving the approximated histogram so that the thresholds are easily extracted by searching the minima of these valleys. Experimental results and a comparative study with three other efficient and known multilevel thresholding methods over synthetic and real images have shown that the proposed method offers very good segmentation results with a low computing time, whatever the complexity of the image and the number of regions composing it. © 2012 Elsevier B.V.

Loading CNRS Laboratory of Image Signal and Intelligent Systems collaborators
Loading CNRS Laboratory of Image Signal and Intelligent Systems collaborators