Clustering mechanism for electric tomography imaging

Electrical tomography (ET) imaging, developed in the 1980s, has attracted much industrial and research attentions owing to its low cost, quick response, lack of radiation exposure, and non-intrusiveness compared to other tomography modalities. However, to date applications thereof have been limited owing to its low imaging resolution. The issue with space resolution in existing ET imaging reconstruction methods is that they employ a mathematical approach based on an ill-posed equation with inconsistent solutions. In this paper, we propose a novel ET imaging method based on a data-driven approach. By recovering the cluster structures hidden in the ET imaging process followed by the application of a fuzzy clustering algorithm to identify the cluster structures, there is no need to study the ill-posed mathematical formulation. The proposed method has been tested by means of three experiments, including image reconstructions of a human lung image and plastic rode shape, as well as two simulations executed on the Comsol platform. The results show that the proposed method can reconstruct ET images with much higher space resolution more quickly than the existing algorithms.