The image reconstruction of electrical impedance tomography (EIT) is highly ill-posed and nonlinear. Because of the poor nonlinear fitting ability of analytical algorithms, reconstructed images of these algorithms are blurry and lack detailed features. Although high-quality EIT images can be obtained by applying deep learning networks to image reconstruction, the interpretability and generalization ability of the network are difficult to guarantee. A deep learning structure namely conditional wasserstein generative adversarial network with attention mechanism (CWGAN-AM) is proposed for EIT image reconstruction. CWGAN-AM consists of imaging module, generator and discriminator. The initial conductivity image obtained by the imaging module is added to both the generator and discriminator as a constraint to improve the stability of reconstruction. The enhanced residual blocks (ERBs), structure of residual in residual (RIR) and attention unit are used in the generator to further improve the reconstruction accuracy for the inclusion boundary. The imaging results indicate that CWGAN-AM can accurately recover the irregular boundaries of inclusions, and effective reconstruction can be accomplished for the new conductivity distribution (inclusions with size/shape variations) and noisy samples.

As a new generation of noninvasiveness imaging modality, electrical impedance tomography (EIT) has broad application prospects to perform functional evaluation for human tissues and organs. Deep learning makes great breakthrough in recent years, and many different neural networks (NNs) have been applied to EIT image reconstruction for obtaining high resolution reconstruction images. However, the NN is hard to interpret, and the robustness and generalization ability of the network model cannot be guaranteed. In this study, a deep learning scheme namely error-constraint network (Ec-Net) is designed to remove the error of reconstruction images obtained by traditional reconstruction algorithm. By establishing the residual mapping between image and error, Ec-Net achieves more robust reconstruction performance and faster learning. Feature fusion module, dilated convolution block, and the structure of residual in residual are used to further improve the reconstruction accuracy for the inclusion boundary. The reconstruction results show that the proposed method can accurately reconstruct the irregular and sharp boundary of inclusions while showing good anti-noise ability for measurement noise higher than 30 dB. Even effective reconstruction can be obtained for new inclusions that have size/shape variations, which proves the generalization ability of Ec-Net model.

Motion tracking is an effective approach for the management of respiratory motion during the medical imaging process, which has always been a major concern in diagnostic imaging, interventional, and noninvasive therapy. However, the low imaging speed of traditional medical imaging techniques limits the practical application of real-time motion tracking. Electrical impedance tomography (EIT) is proved to be an effective tool for continuous monitoring of lung activity/status. However, the respiratory motion has never been studied in the medical EIT field before. In this article, preliminary research of lung movement during the respiratory process is first studied based on EIT. Multiring electrode thorax models under different respiratory statuses were constructed to obtain simulation data of EIT. A modified TV algorithm is used for the estimation of lung volume and movement based on 3-D EIT images, which improve the quality of reconstruction by approximately 30% and 20% compared with the traditional Tikhonov method and the total variation (TV) method, respectively. Both simulations and experiments were conducted to show the potential of respiratory motion tracking through 3-D EIT reconstruction.

Electrical impedance tomography (EIT) has been applied in the field of human-computer interaction due to its advantages including the fact that it is non-invasive and has both low power consumption and a low cost. Previous work has focused on static gesture recognition based on EIT. Compared with static gestures, dynamic gestures are more informative and can achieve more functions in human-machine collaboration. In order to verify the feasibility of dynamic gesture recognition based on EIT, a traditional excitation drive pattern is optimized in this paper. The drive pattern of the fixed excitation electrode is tested for the first time to simplify the measurement process of the dynamic gesture. To improve the recognition accuracy of the dynamic gestures, a dual-channel feature extraction network combining a convolutional neural network (CNN) and gated recurrent unit (GRU), namely CG-SVM, is proposed. The new center distance loss is designed in order to simultaneously supervise the intra-class distance and inter-class distance. As a result, the discriminability of the confusing data is improved. With the new excitation drive pattern and classification network, the recognition accuracy of different interference data has increased by 2.7~14.2%. The new method has stronger robustness, and realizes the dynamic gesture recognition based on EIT for the first time.

A three-dimensional (3D) measurement method of color fringe projection based on an improved three-step phase-shifting method is proposed. The color fringe pattern is encoded by two cosine fringe patterns with the same frequency but different shifting phase and a uniform gray flat image into three color channels R, G, and B. Although the measurement speed of the traditional three-step phase-shifting method can meet the requirements of measuring 3D objects, it makes the noise and inaccuracy of the captured images increase, and each image will cause measurement error. Therefore, we improve the three-step phase-shifting method and introduce the Hilbert transform into the three-step phase-shift method. The DC component of the fringe pattern is obtained by using the Hilbert transform principle, and the third fringe pattern in the three-step phase-shift method is replaced by the captured light intensity distribution of the DC component. The phase difference of the other two fringe patterns is fixed as π / 2 by the Hilbert transform. The improved three-step phase-shifting method is used to obtain the phase information of the deformed color fringe image, and then the phase-unwrapping algorithm is used to obtain the phase distribution information of the whole field. The results show that the improved method can not only accurately calculate the phase information but also greatly improve the measurement speed and quality.

Cylindrical components are widely used in industry machinery and equipment, and quality control of their diameter is very critical in some special applications. In the paper, we focus on the problem of high precision detection of cylindrical objects diameter by machine vision. We suppose the cylindrical object is placed on a datum plane, which has a fixed distance to the camera and is utilized to do camera calibration. To improve the precision of the measurement results, a correction model is proposed to remove the error causing by the height difference between the central axis and the datum plane. Finally, To verify the error correction model we designed and implemented a cylindrical objects diameter measurement system. The experimental results show that the method can achieve high precision measurement of diameter of cylindrical machinery parts.