Electronique

Nombre total de résultats : 482
Pertinence Titre A-Z Plus récents Plus anciens
10 25 50
Année de publication
et

Region-based active contour with adaptive B-spline. Application in radiographic weld inspection

N. Nacereddine, L. Hamami, D. Ziou, A. B. Goumeidane  (2010)
Publication

This paper describes a probabilistic region-based deformable model using a new adaptive scheme for B-spline representation. The idea is to adapt the number of spline control points which are necessary to describe an object with complex shape. For this purpose, the curve segment length (CSL) is used as criterion. The proposed split and merge strategy on the spline model consists in : adding a new control point when CSL is greater than a certain splitting threshold so that the contour tracks all the concavities and, removing a control point when CSL is less to a certain merging threshold so that the contour aspect maintains its smoothness. Noise on synthetic and real weld radiographic images is assumed following Gaussian or Rayleigh distribution. The experiments carried out confirm the adequacy of this approach, especially in tracking pronounced concavities contained in images. Voir les détails

Mots clés : radiography, weld defect, region-based active contour, B-spline, adaptive control point number

Fusion-based shape descriptor for weld defect radiographic image retrieval

N. Nacereddine, D. Ziou, L. Hamami  (2013)
Publication

Content-based image retrieval with relevance feedback plays nowadays an important role in several machine vision applications. In this paper, such a system is proposed for weld radiograms in radiographic testing, with the aim of searching from the overall image database, interactively with the radiograph expert, discontinuities similar to some common weld defect types such as crack, lack of penetration, porosity, and solid inclusion. Therefore, shape features characterizing efficiently these defect indications are required. Two shape descriptors are proposed: a shape geometric descriptor (SGD) consisting of a set of invariant shape geometric measures chosen on the basis of their relationships with the weld defect classes and a generic Fourier descriptor (GFD) known for its discrimination powerfulness for planar filled objects. To improve the weld defect retrieval results, we propose a new fusion-based shape descriptor. The idea of the fusion strategy is to examine the compactness and the rectangularity measures in SGD and derive a criterion permitting the design of a new descriptor f(GFD,SGD) able to better discriminate, particularly, between the problematic defect classes of crack and lack of penetration. Experiments conducted on weld defect image database show the strength of the proposed hybrid descriptor compared to GFD and SGD, simply or hierarchically concatenated or used separately. Voir les détails

Mots clés : Radiographic testing, weld defect, CBIR, SGD, GFD, f(GFD, SGD)

Hybrid Shape Descriptors for an Improved Weld Defect Retrieval in Radiographic Testing

N. Nacereddine, D. Ziou  (2015)
Publication

In this paper, four region-based shape descriptors well reported in the literature are used to characterize weld defect types of crack, lack of penetration, porosity and solid inclusion, usually encountered in radiographic testing of welds. The rectangularity and the roundness in the geometric descriptor (GEO) are used in order to propose an hybridization algorithm so that the hybrid descriptor issued from GEO and each of the other descriptors becomes more discriminant in such application where, due to bad radiographic image quality and weld defect typology, the human film interpretation is often inconsistent and labor intensive. According to the results given in the experiments, the efficiency of the proposed hybrid descriptors is confirmed on the weld defects mentioned above where, the retrieval scores are significantly improved compared to the original descriptors used separately. Voir les détails

Mots clés : Radiographic film, weld defects, shape descriptors, hybridization algorithm

Classification of defects by the SVM method and the Principal Component Analysis (PCA).

M. Khelil, M. Boudraa, A. Kechida, R. Drai  (2005)
Publication

Analyses carried out on examples of detected defects echoes showed clearly that one can describe these detected forms according to a whole of characteristic parameters in order to be able to make discrimination between a planar defect and a volumic defect. This work answers to a problem of ultrasonics NDT like Identification of the defects. The problems as well as the objective of this realized work are divided in three parts: Extractions of the parameters of wavelets from the ultrasonic echo of the detected defect - the second part is devoted to principal components analysis (PCA) for optimization of the attributes vector. And finally to establish the algorithm of classification (SVM, Support Vector Machine) which allows discrimination between a plane defect and a volumic defect. We have completed this work by a conclusion where we draw up a summary of the completed works, as well as the robustness of the various algorithms proposed in this study. Voir les détails

Mots clés : NDT, PCA, SVM, Ultrasonics, wavelet

Application of Hybrid Wavelet-Fractal Compression Algorithm for Radiographic Images of Weld Defects

F. Mekhalfa, D. Berkani  (2011)
Publication

Based on the standard fractal transformation in spatial domain, simple relations may be found relating coefficients in detail subbands in the wavelet domain. In this work we evaluate a hybrid wavelet-fractal image coder, and we test its ability to compress radiographic images of weld defects. A comparative study between the hybrid coder and standard fractal compression technique have been made in order to investigate the compression ratio and corresponding quality of the image using peak signal to noise ratio. Numerical experiments using radiographic images of weld defects illustrate the superior performance of the hybrid coder compared to standard fractal algorithm. Voir les détails

Mots clés : Fractal Compression, Discrete wavelet transform, Wavelet-Fractal coder, Radiographic images of weld defects, Compression ratio, Peak signal to noise ratio

A Quantitative Comparative Study of Back Projection, Filtered Back Projection, Gradient and Bayesian Reconstruction Algorithms in Computed Tomography (CT)

Zoubeida MESSALI, Nabil CHETIH, Amina Serir, Abdelwahab Boudjelal  (2015)
Publication

Images of the inside of the human body can be obtained noninvasively using tomographic acquisition and processing techniques. In particular, these techniques are commonly used to obtain X-ray images of the human body. The reconstructed images are obtained given a set of their projections, acquired using reconstruction techniques. A general overview of analytical and iterative methods of reconstruction in computed tomography (CT) is presented in this paper, with a special focus on Back Projection (BP), Filter Back Projection (FBP), Gradient and Bayesian maximum a posteriori (MAP) algorithms. Projections (parallel beam type) for the image reconstruction are calculated analytically by defining two phantoms: Shepp-Logan phantom head model and the standard medical image of abdomen with coverage angle ranging from 0 to ± 180° with rotational increment of 10°. The original images are grayscale images of size 128 × 128, 256 × 256, respectively. The simulated results are compared using quality measurement parameters for various test cases and conclusion is achieved. Through these simulated results, we have demonstrated that the Bayesian (MAP) approach provides the best image quality and appears to be efficient in terms of error reduction. Voir les détails

Mots clés : Computed tomography, Bayesian approach, Reconstruction techniques, Filter Back Projection (FBP), Gradient algorithm

A Region-Based Model and Binary Level Set Function Applied to Weld Defects Detection in Radiographic Images

Y. Boutiche  (2011)
Publication

In this paper, we propose a model for active contours to detect boundaries’ objects in given image. The curve evolution is based on Chan-Vese model implemented via binary variational level set formulation. The particularity of this model is the capacity to detect boundaries’ objects without need to use gradient of the image, this property gives its several advantages: it allows detecting both contours with or without gradient, it has ability to detect automatically interior contours, and it is robust in the presence of noise. For increasing the performance of model, we introduce the level sets function to describe the active contour, the more important advantage to use level set is the ability to change topology. Experiments on synthetic and real (weld radiographic) images show both efficiency and accuracy of implemented model. Voir les détails

Mots clés : image segmentation, Curve evolution, Chan-Vese Model, EDPs, Level set, radiographic images

La Méthode Descente De Gradient Pour La ReconstructionTomographique Des Images 2D A Rayon-X

Chetih Nabil, Messali Zoubeida, Serir Amina  (2014)
Publication

Cet article concerne la reconstruction tomographique 2D d’images à rayon-x. Le problème dereconstruction tomographique est un problème inverse c.-à-d. Estimer l’objet à partir de ses projections. Dans cetravail, nous avons établi une étude détaillée sur la méthode de descente de gradient, qui s’inscrit dans le cadredes méthodes itératives de reconstruction tomographique. Ces méthodes consistent à exprimer le problèmedirectement sous une forme discrète. Grâce aux résultats de simulation, nous avons montré que l’algorithme degradient offre une bonne qualité de reconstruction en termes des critères d’évaluation en plus la qualité visuelledes images reconstruites. Voir les détails

Mots clés : Reconstruction Tomographique, problème inverse, projections, Descente de Gradient

A Comparative Study of Analytical,Iterative and Bayesian Reconstruction Algorithms in Computed Tomography(CT)

Zoubeida MESSALI, Nabil CHETIH, Amina Serir, and Abdelwahhab Boudjelal  (2012)
Publication

These Images of the inside of the human body can be obtained using tomographic acquisition and processing techniques. In particular, these techniques are commonly used to obtain X-ray images of the human body. The reconstructed images are obtained given a set of their projections, acquired using reconstruction techniques. A general overview of analytical and iterative methods of reconstruction in computed tomography (CT) is presented in this paper, with a special focus on Bayesian algorithms. The simulated results are compared using quality measurements for various test cases and conclusion is achieved. Through these simulated results, we have demonstrated that the Bayesian approach provides the best image quality and the small values of the quality measurements. Voir les détails

Mots clés : Computed tomography, Bayesian approach, reconstruction techniques.

Local Segmentation via an Implicit Region-Based Deformable Model Applied To Weld Defects Extraction

Y. Boutiche  (2013)
Publication

This paper is devoted to present and discuss a model that allows a local segmentation by using statistical information of a given image. It is based on Chan-Vese model, curve evolution, partial differential equations and binary level sets method. The proposed model uses the piecewise constant approximation of Chan-Vese model to compute Signed Pressure Force (SPF) function, this one attracts the curve to the true object(s)’s boundaries. The implemented model is used to extract weld defects from weld radiographic images in the aim to calculate the perimeter and surfaces of those weld defects. Encouraged resultants are obtained on synthetic and real radiographic images. Voir les détails

Mots clés : Active contour, Chan-Vese Model, binary Level set, local segmentation, weld radiographic images