Improving Image Quality in Electrical Capacitance Tomography using OTSU Thresholding

Abstract

Electrical Capacitance Tomography (ECT) is an imaging technique used in industrial process monitoring, particularly for monitoring and measuring the composition of multiphase flows. Despite its widespread application, the commonly used Linear Back Projection (LBP) algorithm often produces low-quality images due to its limited ability to handle high permittivity contrasts and nonlinearities. This study investigates the use of Otsu thresholding as a post-processing technique to enhance ECT image quality. By maximizing inter-class variance in the image histogram, Otsu thresholding improves contrast, clarity, and structural definition, enabling more effective segmentation of oil and gas components in multiphase flows. The proposed Otsu-based reconstruction method, LBPU, was developed and evaluated alongside the standard LBP and entropy-based thresholding methods (LBPS and LBPT) using static experiments with an 8-electrode ECT measurement system. The qualitative visual assessment showed that the images created by LBPU had a clearer structure and were more visually similar to the reference images than the images generated by LBP, LBPS and LBPT for both the annular and stratified flows. Quantitatively, LBPU produced images with improved reconstruction accuracy by generating images with distribution error (DE) values below the 10% threshold and higher the correlation coefficient (CC) compared to other methods across the entire fraction of components. In terms of computational efficiency, the LBP method had the fastest processing time compared to other methods. The LBPU method required slightly more time than LBP but faster than LBPT and LBPS. These findings indicate that the LBPU method can be more suitable in online industrial monitoring applications demanding both speed and accuracy like those found in the oil and gas industry since it ensures a DE value threshold of 10% or less for proper multiphase flow visualization.