Browsing by Author "Mery, D"

Now showing 1 - 8 of 8
  • Thumbnail Image
    Item
    A real time visual sensor for supervision of flotation cells
    (PERGAMON-ELSEVIER SCIENCE LTD, 1998) Cipriano, A; Guarini, M; Vidal, R; Soto, A; Sepulveda, C; Mery, D; Briseno, H
    This paper describes an expert system for the supervision of flotation plants based on ACEFLOT, a real time analyzer of the characteristics of the froth that is formed on.:the surface of flotation cells. The ACEFLOT analyzer is based on image processing and measures several physical variables of the froth, including colorimetric, geometric and dynamic information. On the other hand, the expert system detects abnormal operation states and suggests corrective actions, supporting operators on the supervision and control of the flotation plant. (C) 1998 Published by Elsevier Science Ltd. All rights reserved.
  • Thumbnail Image
    Item
    Automated radioscopic testing of aluminum die castings
    (AMER SOC NONDESTRUCTIVE TEST, 2006) Mery, D
    Castings produced for the automotive industry are considered important components for overall roadworthiness. To ensure the safety of construction, it is necessary to check every part thoroughly using nondestructive testing (NDT). Radioscopy rapidly became the accepted way for controlling the quality of die cast pieces. hi this paper, the fundamental principles of the automated detection of casting discontinuities are explained. A general automated testing schema is presented and several techniques that have appeared in the literature in the past 20 years are explained, showing the development of this sector in the areas of industry and academia. Finally, advances in the simulation of discontinuities, used for assessing the performance of a test technique, are outlined.
  • Thumbnail Image
    Item
    Automated testing of aluminum castings using classifier fusion strategies
    (AMER SOC NONDESTRUCTIVE TEST, 2005) Mery, D; Chacon, M; Gonzalez, L; Munoz, L
    Generally, discontinuity detection in automated visual testing consists of two steps: identification of potential discontinuities using image processing techniques and classification of potential discontinuities into discontinuities and regular structures (false alarms) using a pattern recognition methodology. In the second step, since several features cyan be extracted from the potential discontinuities, a feature selection must be performed. In this paper, several known classifiers are studied in automated visual testing: threshold, euclidean, mahalanobis, polynomial, support vector machine and neural network classifiers. First, the performance of the classifiers is assessed individually. Second, the classifiers are combined in order to improve their performance. Seven fusion strategies in the combination were tested: and, or, majority vote, product, sum, maximum and median. The proposed methodology was tested on real data acquired from 50 noisy radiographic images of aluminum wheels, where 23 000 potential discontinuities (with only 60 real discontinuities) were segmented and 405 features were extracted for each potential discontinuity. Using fusion of classifiers, a very good performance was achieved, yielding a sensitivity of 100% and specificity of 99.97%.
  • Thumbnail Image
    Item
    Classification of potato chips using pattern recognition
    (WILEY, 2004) Pedreschi, F; Mery, D; Mendoza, F; Aguilera, JM
    An approach to classify potato chips using pattern recognition from color digital images consists of 5 steps: (1) image acquisition, (2) preprocessing, (3) segmentation, (4) feature extraction, and (5) classification. Ten chips prepared for each of the following 6 conditions were examined: 2 pretreatments (blanched and unblanched) at 3 temperatures (120 degreesC, 150 degreesC, and 180 degreesC). More than 1500 features were extracted from each of the 60 images. Finally, 11 features were selected according to their classification attributes. Seven different classification cases (for example, classification of the 6 classes or distinction between blanched and unblanched samples) were analyzed using the selected features. Although samples were highly heterogeneous, using a simple classifier and a small number of features, it was possible to obtain a good performance value in all cases: classification of the 6 classes was in the confidence interval between 78% and 89% with a probability of 95%.
  • Thumbnail Image
    Item
    Neural network method for failure detection with skewed class distribution
    (BRITISH INST NON-DESTRUCTIVE TESTING, 2004) Carvajal, K; Chacon, M; Mery, D; Acuna, G
    The automatic detection of flaws through non-destructive testing uses pattern recognition methodology with binary classification. In this problem a decision is made about whether or not an initially segmented hypothetical flaw in an image is in fact of law. Neural classifiers are one among a number of different classifiers used in the recognition of patterns. Unfortunately, in real automatic flaw detection problems there are a reduced number of flaws in comparison with the large number of non-flatus. This seriously limits the application of classification techniques such is artificial neural networks elite to the imbalance between classes. This work presents a new methodology for efficient training with imbalances in classes. The premise of the present work is that if there are sufficient cases of the smaller class, then it is possible to reduce the Size of the larger class by using the correlation between cases of this latter class, with a minimum information loss. It is then possible to create it training set for a neural model that allows good classification. To test this hypothesis a problem of great interest to the automotive industry is used, which is the radioscopic inspection of cast aluminium pieces. The experiments resulted in perfect classification of 22936 hypothetical flaws, of which only 60 were real flat-vs and the rest were false alarms.
  • Thumbnail Image
    Item
    Segmentation of circular casting defects using a robust algorithm
    (BRITISH INST NON-DESTRUCTIVE TESTING, 2005) Ghoreyshi, A; Vidal, R; Mery, D
    In this paper, we describe three methods for detecting defects in cast aluminium using X-radioscopic images. The first method is based on the assumption that most defects have the shape of a circular high-intensity spot. Therefore, defects are detected using a template matching-like algorithm. This method works well when the defects are far enough from the edges of the major shapes in the image, and when the image gives a closer view of the defect. The second method deals with the defects which are closer to the edges in the image, and therefore are missed by the first method. This method distinguishes between defects and edges by using the following properties of a defect: they are local maxima of the image intensity, and the distribution of the intensity in a patch around the defect should resemble more that of a corner than that of an edge. Both local maxima and corner-like properties are computed using the second order derivatives of the image intensities, and the Harris Corner Detector algorithm. The third algorithm is a simple combination of the aforementioned methods in which a pixel is considered to be a defect if it is detected as a defect by either of the two methods. We present experiments using the third method showing that 94.3% of the defects are correctly detected, with only 1.3 false alarms per image.
  • Thumbnail Image
    Item
    Segmentation of colour food images using a robust algorithm
    (ELSEVIER SCI LTD, 2005) Mery, D; Pedreschi, F
    In this paper, a robust algorithm to segmenting food image from a background is presented using colour images. The proposed method has three steps: (i) computation of a high contrast grey value image from an optimal linear combination of the RGB colour components; (ii) estimation of a global threshold using a statistical approach; and (iii) morphological operation in order to fill the possible holes presented in the segmented binary image. Although the suggested threshold separates the food image from the background very well, the user can modify it in order to achieve better results. The algorithm was implemented in Matlab and tested on 45 images taken in very different conditions. The segmentation performance was assessed by computing the area A(z) under the receiver operation characteristic (ROC) curve. The achieved performance was A(z) = 0.9982. (C) 2004 Elsevier Ltd. All rights reserved.
  • Thumbnail Image
    Item
    Simulation of defects in aluminium castings using CAD models of flaws and real X-ray images
    (BRITISH INST NON-DESTRUCTIVE TESTING, 2005) Mery, D; Hahn, D; Hitschfeld, N
    In order to evaluate the sensitivity of defect inspection systems, it is convenient to examine simulated data. This gives the possibility to tune the parameters of the inspection method and to test the performance of the system in cases where the detection is known to be difficult. In this paper, an interactive environment for the simulation of defects in radioscopic images of aluminium castings is presented. The approach simulates only the flaws and not the whole radioscopic image of the object under test. A manifold surface is used to model a flaw with complex geometry, which is projected and superimposed onto real radioscopic images of a homogeneous object according to the exponential attenuation law for X-rays. The new grey value of a pixel, where the 3D flaw is projected, depends only on four parameters: a) the grey value of the original X-ray image without flaw; b) the linear absorption coefficient of the examined material; c) the maximal thickness observable in the radioscopic image; and d) the length of the intersection of the 3D flaw with the modelled X-ray beam, that is projected into the pixel. The approach allows the user the simulation of complex flaws at any position of an aluminium casting. Simulation results of flaws like blow holes and cracks on X-ray images are shown and contrasted with real digital images with real flaws.