Search

Dental caries is a bacterial infectious disease that destroys the structure of teeth. It is one of the main diseases that endanger human health [R. H. Selwitz, A. I. Ismail, and N. B. Pitts, Lancet 369(9555), 51–59 (2007)]. At present, dentists use both visual exams and radiographs for the detection of caries. Affected by the patient's dental health and the degree of caries demineralization, it is sometimes difficult to accurately identify some dental caries in x-ray images with the naked eye. Therefore, dentists need an intelligent and accurate dental caries recognition system to assist diagnosis, reduce the influence of doctors' subjective factors, and improve the efficiency of dental caries diagnosis. Therefore, this paper combines the U-Net model verified in the field of biomedical image segmentation with the convolution block attention module, designs an Attention U-Net model for caries image segmentation, and discusses the feasibility of deep learning technology in caries image recognition so as to prepare for the next clinical verification. After testing, the Dice similarity coefficient, mean pixel accuracy, mean intersection over union, and frequency-weighted intersection over the union of teeth segmentation with Attention U-Net are 95.30%, 94.46%, 93.10%, and 93.54%, respectively. The Dice similarity coefficient, mean pixel accuracy, mean intersection over union, and frequency-weighted intersection over the union of dental caries segmentation with Attention U-Net are 85.36%, 91.84%, 82.22%, and 97.08%, respectively. As a proof of concept study, this study was an initial evaluation of technology to assist dentists in the detection of caries. There is still more work needed before this can be used clinically. [ABSTRACT FROM AUTHOR]

In the intelligent production process of wood products, the classification system of wood knot defects is a very practical solution. However, traditional image processing methods cannot handle it well due to the uncertainty of manually extracted features. Therefore, a lightweight and reliable artificial neural network model is proposed to classify and identify our objective. To solve this problem, a wood knot defect recognition model named SE-ResNet18 combining convolutional neural network, attention mechanism, and transfer learning is proposed in this paper. First, the Sequence-and-Exception (SE) module is combined with Basicblock and is constructed as two modules called RBBSE-1 and RBBSE-2. These modules learn to enhance features that are useful for the current task, suppress useless features, and fuse the output features with the original features. Then, the fully connected layer is replaced with a global average pooling layer, which can effectively reduce the parameters of the fully connected layer in the model. Finally, a SE-ResNet18 was constructed by one convolutional layer, five RBBSE-1 modules, and three RBBSE-2 modules of different channels. The SE-ResNet18 has a higher accuracy (98.85%) in the test set compared to the unimproved model ResNet-18. Compared with the previously proposed ReSENet-18, more SE modules are used in SE-ResNet18 to provide a basis for future training on a larger-scale dataset. Based on the same test set, a comparison with other classical models (such as LeNet-5, AlexNet, etc.) was conducted, and the results validated the superiority of the proposed model. The proposed model achieves the expected objective and provides a new way of thinking for non-destructive testing of wood. [ABSTRACT FROM AUTHOR]

Digital fringe projection profilometry based on phase-shifting technology is a reliable method for complex shape measurement, and the phase is one of the most important factors affecting measurement accuracy. The calculation of the absolute phase depends on the calculation of the wrapped phase and encoding technology. In this paper, a technique of obtaining the absolute phase of multi-frequency heterodyne fringe images using the Hilbert transform is presented. Since the wrapped phase can be calculated from only one fringe image of each frequency, the method does not need phase-shifting. The absolute phase can be obtained from the wrapped phase by applying the heterodyne method. The measurement time and computational complexity are dramatically reduced, the measurement efficiency is greatly improved, and this benefit from the number of images is greatly reduced. The experimental results show that the method presented in this paper performs well in the application, and the accuracy is no different from that of the phase-shifting method while the efficiency is greatly improved. [ABSTRACT FROM AUTHOR]

Defects, such as delamination and debonding, are critical to the performance of carbon fiber-reinforced polymer (CFRP) composites. In recent years, non-destructive testing techniques have been improved for the inspection of these defects among CFRPs. In this study, an all-optical and non-destructive laser ultrasonic technique with an optical microphone detection module has been presented to detect the artificial subsurface defects among the CFRP composites. A finite element simulation based on the thermo-mechanical coupling model was used to study the process of nanosecond pulsed laser excitation of the CFRP laminate to produce ultrasound and the propagation behavior of ultrasound among the CFRP laminate. A series of non-contact laser ultrasonic testing experiments were carried out to study the flat bottom holes of different sizes via a laser ultrasonic detection system. The artificial subsurface defects were reliably identified by the presented all-optical laser ultrasonic system imbedded in the optical microphone using four feature images. [ABSTRACT FROM AUTHOR]

Laser-induced ultrasound scanning imaging is proposed and utilized for the detection of the printed circuit board (PCB) delamination defect in this present study. Initially, based on the principle of laser-induced ultrasound scanning imaging, a three-dimensional mathematical model of the ultrasonic excitation by pulsed laser acting on the surface of PCB is established and analyzed. Furthermore, based on the established laser ultrasonic nondestructive testing system, single-point testing is investigated on the PCB specimen. A-scan experiments were carried out by transmission and reflection approaches, respectively. Moreover, the influence of the signal receiving position on the discrimination of defective signals and the effect of wavelet transform denoising parameters on the signal-to-noise ratio were investigated. Eventually, based on the laser-induced ultrasound scanning imaging inspection system, the defects of simulated debonding flat bottom holes are detected and studied. The different algorithms or parameters (Fast Fourier Transform, variance, extremum, and principal component analysis, etc.) are employed to extract the characteristic information are analyzed. The experimental results are compared with the traditional infrared thermal wave imaging (lock-in thermography). The experimental results indicate that laser-induced ultrasound scanning imaging has the advantages of high-resolution imaging for the defect with a small diameter. Therefore, it is of great significance to study a set of feasible laser-induced ultrasound scanning imaging for PCB delamination defect detection. [ABSTRACT FROM AUTHOR]

Carrier transport and electrical properties are relevant to the performance of semiconductor materials and photovoltaic devices. In recent years, various kinds of high-resolution luminescence-based methods have been proposed to image these properties. Lock-in carrierography (LIC), as a dynamic photoluminescence-based method, has the advantages of self-calibration, higher signal to noise ratio than dc or transient modalities, and high-frequency imaging ability. At the present stage of development, LIC has evolved into homodyne lock-in carrierography and heterodyne lock-in carrierography. In this Perspective, we discuss the principles and theoretical background of both LIC modalities and review experimental systems and methods. In addition, we also provide a brief overview of key LIC applications and future outlook. [ABSTRACT FROM AUTHOR]

Simulations were carried out to study the uniqueness range of Heterodyne Lock-in Carrierography (HeLIC) imaging measurements of carrier transport parameters (bulk lifetime, diffusion coefficient, and front and back surface recombination velocities) of silicon wafers. Theoretically, HeLIC can resolve all four transport parameters; however, in practice, the presence of experimental noise does not allow all those parameters to be measured reliably and uniquely from HeLIC images alone. An extended range of simultaneously determined unique transport parameters was attained through the combination of HeLIC camera pixel and photocarrier radiometry (PCR) experimental frequency response data via a multi-parameter fitting procedure. Two n- and p-type wafers with different surface recombination velocities were used to illustrate the simulation results. Quantitative HeLIC images of diffusion coefficients and surface recombination velocities were obtained, with bulk lifetime values determined from PCR frequency scan measurements. The combined approach was shown to be able to resolve all four transport parameters uniquely and thus reliably. [ABSTRACT FROM AUTHOR]

A combined theoretical and experimental approach is reported using spectrally windowed lock-in carrierography imaging (lock-in photoluminescence) under variable illumination intensity to provide quantitative contactless measurements of key electrical parameters (photogenerated current density, Jg, open circuit voltage, VOC, and maximum power voltage, Vm) of multicrystalline silicon (m-Si) solar cells in very good agreement with standard electrical measurements. The method is based on a recently developed photocarrier radiative recombination current flux relation which links the optical and electrical characteristics of solar cells. In addition, this approach is shown to yield non-contact all-optical estimates of the solar-cell current-voltage characteristics with the conventional variable load resistance replaced by variable laser intensity. [ABSTRACT FROM AUTHOR]