Quality evaluation of insulating parts by fusion of classifiers issued from tomographic images

The industrial manufacturing of insulating parts must meet strict requirements in order to be used in disturbed environments. Experts know that the moulding process has an impact on the final product quality. However, the phenomenon is so complicated that the relation between the manufacturing process and the product quality is difficult to identify. Some non-destructive methods are nowadays used in the industry to obtain information from inside the parts. In this paper, 3D tomographic acquisitions are used in order to analyse the parts. From the huge set of data obtained, several attributes have been computed to characterize images. A fusion system based on the Decision Templates method is proposed in this paper. Adaptations of the initial method are proposed to be more effective for image segmentation. The fusion approach capabilities are analysed on real data in the context of insulating part analysis.