Pattern recognition in the automatic inspection of aluminium castings

Abstract

∑ Image Formation: The images are obtained by X-ray irradiation of the test-piece. The X-rays are then converted to a visible image by means of an image amplifier or a flat-panel detector that are sensitive to X-rays. The sensor is bi-dimensional (or unidimensional in motion) in order to capture the two dimensions of the image. An A/D converter turns the electrical signal into binary code that can be interpreted by a computer to form a digital image of the study object. ∑ Pre-processing: This stage is devoted to improving the quality of the image in order to better recognise flaws. Some of the techniques used in this stage are elimination of noise by means of digital filters or integration, improvement of contrast, and restoration. ∑ Segmentation: The segmentation process divides the digital image into disjoint regions with the purpose of separating the parts of interest from the rest of the scene. Over the last few decades, diverse segmentation techniques have been developed. These can largely be divided into three groups: pixel, edge and region orientated techniques. The present investigation uses the segmentation process oriented towards the detection of edges by employing the LoG filter (Mery and Filbert, 2002b). As can be seen in Figure 2, this technique searches for changes in the grey values of the image (edges), thus identifying zones delimited by edges that indicate flaws. ∑ Feature extraction: In the inspection of cast pieces, segmentation detects regions that are denominated as ‘hypothetical defects’, which may be flaws or structural features of the object. Subsequently the feature extraction is centred principally around