Automated X-ray inspection of aluminum castings

Statistical detection of defects in radiographic images using an adaptive parametric model

“…Such approaches typically involve image processing tools for enhancement (field flattening, contrast enhancement, edge detection, etc.) see [9,28,39] and the references therein, together with pattern recognition [6,36] methods. More recently, state-of-the-art image processing methods, such as multi-resolution representation [54], sparse dictionary learning [37] and variational methods [32], have Contents lists available at ScienceDirect journal homepage: www.elsevier.com/locate/sigpro been applied for automatic defect detection.…”

Feature Extraction and Classification in Automated Inspection of NDE Images

“…If there are not duplicated items, each vector and its desired output value in the training data file lead to a fuzzy rule in the fuzzy rule base. The membership function for the ith feature in the jth rule, denoted as J.lij' is given by a unit-amplitude Gaussian form as (1) in which the center of the membership function is initialized at the training prototype position Xij and the standard deviation cr ij' which is used to control the effective range of the membership function, is derived from the range of each feature in the training data file as…”

“…The output error e is defined by the difference between f(X) and the desired output. A least square error training is then achieved for the system by a steepest descent iteration which reshapes the input and output fuzzy membership functions by updating the means and the standard deviations of Equation (1) and the centroid of the output fuzzy set d j until the error is minimized. This is given by (5) where ex.…”

“…However, since the objects to be inspected usually have complex geometric structures, it is very difficult to separate automatically flaws from the complex geometric background of an image. Most of the automated inspection systems developed so far are customized packages which are tailored for particular types of applications, such as the inspections of aluminum wheel castings [1], the welds of space shuttle fuel tanks [2], and nodules in chest Xrays [3]. Customized packages have the advantages of relatively fast speed and good liability, but they can not be used in other applications without substantial changes in computer programs.…”

A vision inspection system for the surface defects of strongly reflected metal based on multi-class SVM

“…And most frequently, sensory systems use CCD chips (Pernkopf & O'Leary, 2003;Zhang et al, 2008). However, alternative strategies, including laser scanning (Abuazza, Brabazon, & El-Baradie, 2003, 2004, ultrasound (Kercel, Kisner, Klein, Bacher, & Pouet, 1999), and X-ray image sensor systems (Boerner & Strecker, 1988;Mery & Filbert, 2002;Naso & Pantaleo, 2005) are gaining ground.…”