Enhancement of Images from Industrial X-Ray Computed Tomography Systems by Hybrid Approach

Abstract

Application of the computed tomography (CT) within industry has been rising in recent years due to its non-destructive abilities and accuracy. Nevertheless, there are some challenges related to CT scanning, such as pres- ence of artefacts. The aim of this research is to investigate to what extent the application of some advanced algorithms can influence the accuracy of the X-ray CT images. In this paper, after a brief overview of different existing methods used for reduction of different types of artefacts, preliminary research of a new approach for CT image enhancement is presented. It is based on a hybrid methodology using two different methods - Fuzzy Clustering and Region Growing - joined in order to exploit their advantages. Results show that the proposed methodology contributes to CT image enhancement, with borders of segmented objects on CT images more easily extracted.