Abstract
A convolutional neural network (CNN)-based image reconstruction algorithm for two-phase material imaging is presented and verified with experimental data from a capacitively coupled electrical resistance tomography (CCERT) sensor. As a contactless version of electrical resistance tomography (ERT), CCERT has advantages such as no invasion, low cost, no radiation, and rapid response for two-phase material imaging. Besides that, CCERT avoids contact error of ERT by imaging from outside of the pipe. Forward modeling was implemented based on the practical circular array sensor, and the inverse image reconstruction was realized by a CNN-based supervised learning algorithm, as well as the well-known total variation (TV) regularization algorithm for comparison. The 2D, monochrome, 2500-pixel image was divided into 625 clusters, and each cluster was used individually to train its own CNN to solve the 16 classes classification problem. Inherent regularization for the assumption of binary materials enabled us to use a classification algorithm with CNN. The iterative TV regularization algorithm achieved a close state of the two-phase material reconstruction by its sparsity-based assumption. The supervised learning algorithm established the mathematical model that mapped the simulated resistance measurement to the pixel patterns of the clusters. The training process was carried out only using simulated measurement data, but simulated and experimental tests were both conducted to investigate the feasibility of applying a multi-layer CNN for CCERT imaging. The performance of the CNN algorithm on the simulated data is demonstrated, and the comparison between the results created by the TV-based algorithm and the proposed CNN algorithm with the real-world data is also provided.
Highlights
Electrical impedance tomography (EIT) has been studied and widely applied in medical imaging and process tomography since it was introduced in the 1980s [1,2,3,4,5]
In late 1980s, when EIT was introduced to the process tomography field, electrical resistance tomography (ERT), a particular case of EIT, was proposed [8,9]
Experiments show that capacitively coupled electrical resistance tomography (CCERT) could have a larger excitation frequency domain than that of traditional ERT, which results in better imaging results [15,16]
Summary
Electrical impedance tomography (EIT) has been studied and widely applied in medical imaging and process tomography since it was introduced in the 1980s [1,2,3,4,5]. For ET techniques, DNN algorithms are suggested as a way to solve the inverse problem and reconstruct images. The cascaded end-to-end convolutional neural network (CEE-CNN) was built by Wei et al to apply the induced current learning method (ICLM) to solve the nonlinear reconstruction problem in EIT [29]. Fernández-Fuentes et al developed an ANN-based inverse problem solver for EIT, which takes the boundary measurements as the input and generates the conductivity value of each mesh of triangular elements of the image [32]. When the conductivity of the jth element changes from σ0 to σ1 while the remaining elements still have σ0 conductivity, the ith current and resistance measurements become Iij and Rij. After calculating the sensitivity matrix, the image reconstruction process can be conducted. The value range of the SSIM is 0–1, and the image with better quality should have a higher SSIM value
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
