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.

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.

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.

This report is on convolution neural network (CNN) fusion lock-in thermography, which can implement the intelligent identification of defects for aviation honeycomb sandwich composites (HSCs). First, HSCs specimens with subsurface delamination defects were fabricated and stimulated by halogen lamps according to sinusoidal modulation, and the defects were reliably inspected using lock-in thermography. The amplitude and phase images (commonly referred to as feature images) were obtained by using a digital lock-in correlation algorithm. Furthermore, these feature images were changed into gray or color-level image formalism datasets, which is pre-processed in ways including contrast enhancement, threshold segmentation as well as mosaic data augmentation. Finally, the four-layer feature pyramid structure and ransformer are combined and introduced to the popular YOLOv5 CNN model, and a YOLOLT CNN model is formed to realize the defect identification. The average precision (AP) in the defect identification of HSCs in complex environments (contains noise and other objects) reached 93.2% and achieved an average recognition speed of 0.6 s/image.