High-speed railway in China has undergone rapid development in recent years. Technology for structure measurement is recognized as an important aspect of steel rail quality inspection. The shape of the rail welding base is mainly gauged using mechanical contact measurement technology. Matching this technology with the escalating demands for quality inspection of steel rails is a challenging task. In this paper, a structured light measurement approach is proposed and employed which intersects the rail through the structural light plane projected by inner and outer laser sensors. These sensors form a laser light stripe curve containing the profile information of the rail surface. By processing laser light bars using image analysis and contour reduction techniques, 3-D profiles of the rails are generated. The laser plane is fitted using the coordinate points of the laser light bars converted between the image and world coordinate systems. A new calibration method based on the parallel moving target for line-structured light is proposed to improve the calibration and address the issue caused by the limited number of the extracted calibration points during free target calibration. The rail profile, including the geometric dimension, straightness, and twist of the rail, are then measured. By comparing the measured profile with the standard contour of the rails, the rail wear can then be quantitatively assessed. The experimental results show that the proposed measurement system outperforms the traditional single index detection.

The surface quality of aluminum ingot is crucial for subsequent products, so it is necessary to adaptively detect different types of defects in milled aluminum ingots surfaces. In order to quickly apply the calculations to a real production line, a novel two-stage detection approach is proposed. Firstly, we proposed a novel mask gradient response-based threshold segmentation (MGRTS) in which the mask gradient response is the gradient map after the strong gradient has been eliminated by the binary mask, so that the various defects can be effectively extracted from the mask gradient response map by iterative threshold segmentation. In the region of interest (ROI) extraction, we combine the MGRTS and the Difference of Gaussian (DoG) to effectively improve the detection rate. In the aspect of the defect classification, we train the inception-v3 network with a data augmentation technology and the focal loss in order to overcome the class imbalance problem and improve the classification accuracy. The comparative study shows that the proposed method is efficient and robust for detecting various defects on an aluminum ingot surface with complex milling grain. In addition, it has been applied to the actual production line of an aluminum ingot milling machine, which satisfies the requirement of accuracy and real time very well.

The deep learning-based image segmentation approach has evolved into the mainstream of target detection and shape characterization in microscopic image analysis. However, the accuracy and generalizability of deep learning approaches are still hindered by the insufficient data problem that results from the high expense of human and material resources for microscopic image acquisition and annotation. Generally, image augmentation can increase the amount of data in a short time by means of mathematical simulation, and has become a necessary module for deep learning-based material microscopic image analysis. In this work, we first review the commonly used image augmentation methods and divide more than 60 basic image augmentation methods into eleven categories based on different implementation strategies. Secondly, we conduct experiments to verify the effectiveness of various basic image augmentation methods for the image segmentation task of two classical material microscopic images using evaluation metrics with different applicabilities. The U-Net model was selected as a representative benchmark model for image segmentation tasks, as it is the classic and most widely used model in this field. We utilize this model to verify the improvement of segmentation performance by various augmentation methods. Then, we discuss the advantages and applicability of various image augmentation methods in the material microscopic image segmentation task. The evaluation experiments and conclusions in this work can serve as a guide for the creation of intelligent modeling frameworks in the materials industry.

To address the problem of low detection rate caused by the close alignment and multi-directional position of text words in practical application and the need to improve the detection speed of the algorithm, this paper proposes a multi-directional text detection algorithm based on improved YOLOv3, and applies it to natural text detection. To detect text in multiple directions, this paper introduces a method of box definition based on sliding vertices. Then, a new rotating box loss function MD-Closs based on CIOU is proposed to improve the detection accuracy. In addition, a step-by-step NMS method is used to further reduce the amount of calculation. Experimental results show that on the ICDAR 2015 data set, the accuracy rate is 86.2%, the recall rate is 81.9%, and the timeliness is 21.3 fps, which shows that the proposed algorithm has a good detection effect on text detection in natural scenes.

Ultrasonic testing is an important means to detect defacing defects, such as scratches and cracks, but when the size of these defects is smaller than the wavelength of ultrasonic waves, it is difficult to detect them using traditional methods like the pulse-echo method and broadband ultrasound attenuation method for the diffraction of ultrasonic waves at the defects. Based on the non-contact characteristic of electromagnetic acoustic transducers (EMATs), a transducer for scanning inspection was developed in this paper. The transducer was utilized to detect and measure the depth of the defacing defects on an aluminium plate based on the near-field enhancement of ultrasonic Lamb waves. The results show that the amplitude of the S0 Lamb wave experiences a large enhancement when the transducer is passed over the scratch defects and the enhancement has a clearly positive correlation with the depth of the scratch defects. When the depth increases from 0.1 mm to 0.9 mm, the amplitude of S0 Lamb waves increases from 1.13 times to 2.27 times the S0 Lamb waves received on the aluminium plate without defects. The new method can be utilized to detect the defacing defects on the aluminium plate and get better detection effects than the traditional methods without analyzing the relatively small reflection waves.