Explore the vast range of titles available.

To meet the requirements of high accuracy in image edge localization and strong noise resistance for computer vision calibration and precise measurement, an improved Zernike moment sub-pixel high-precision measurement method for circular hole-like workpieces is proposed. Firstly, the Canny operator is used as a coarse edge detection algorithm, with the traditional Gaussian filter in the Canny operator replaced by an improved Laplacian edge-adaptive median filter. This approach demonstrates improved edge preservation compared to traditional and adaptive median filtering, especially under high-concentration noise. Then, a sub-pixel edge detection algorithm is applied to refine the edges, thus enhancing the edge localization accuracy. An improved Zernike moment sub-pixel detection algorithm is employed for precise edge point detection. The improved algorithm selects a Zernike moment parameter template with higher detection accuracy. Finally, the inner and outer diameters of the circular hole-like part are measured by fitting the profile using the least squares method. Experimental results on several different workpieces demonstrate that the proposed algorithm achieves higher accuracy than the traditional Zernike moment sub-pixel method, with an error reduction of 75.1%, meeting the precision requirements in modern industrial part manufacturing processes.

Double threshold method of traditional Canny operator detects the edge rely on the information of gradient magnitude, which has a lower edge connectivity and incomplete image information. Aiming at this problem, we proposed an edge detection algorithm based edge connection—the Hough Transform based Canny (HT-Canny) edge detection algorithm. HT-Canny algorithm guided by high threshold image, which obtains edge direction through calculating edge endpoint gradient and connects the edge by using the Hough Transform instead of traditional double threshold method. It avoids the limitation of traditional Canny algorithm, which must set the double threshold manually and protect the low intensity edge especially. The experimental results show that HT-Canny algorithm has stronger edge connectivity and can distinguish edge points and non-edge points effectively, which not only retain the advantages of the traditional Canny algorithm but also make the detection result more complete and comprehensive.

This study aims to identify the conveyor belt deviation. It presents a machine vision-based detection approach that uses the coordinates of the crossing point between the conveyor belt centerline and the laser line to determine whether the deviation fault occurs. In order to avoid the influence of the defects of the traditional Canny operator, an improved Canny edge detection algorithm combining hybrid filter and maximum inter-class variance method (OTSU) is used. Then the Hough transform is used to detect the straight line of the edge detected image and extract the laser centerline with the centerline extraction algorithm; finally, the Shi-Tomasi operator is used to detect the corners to get the intersection of the edge line and the laser line. The slope and center coordinates of the conveyor belt edges are calculated to determine whether the conveyor belt has run-off faults and calculate the offset amount. The results show that the proposed method can accurately determine the conveyor belt deviation and calculate the deviation amount.

The surface of semiconductor materials can produce defects such as scratches during use, significantly affecting their performance. In this paper, we use advanced machine learning techniques to detect defective regions on the surface of semiconductor materials by employing the Canny operator. The characteristics of defects on the surface of semiconductor materials, such as geometry, grayscale, and texture, are extracted. Based on the TensorFlow framework, a machine learning model for recognizing defects on the surface of semiconductor materials has been established. The model in this paper can achieve 94.53% accuracy in the comprehensive recognition of eight types of defects on the surface of semiconductor materials. In addition to random-type defects, the recognition accuracy of this paper’s model for the other 7 types of defects is above 94.59%. The model shows the best performance in the task of recognizing six types of semiconductor material surface defect patterns, namely center, torus, marginal local, edge ring, local, and random, and its F-value reaches 94.08 and 88.40 for the two types of defect patterns, namely nearly full and scratches. This is close to the highest F-value of all algorithms for the recognition of these two defects. In the five-fold cross-validation, the defect recognition accuracy of this paper’s model was as high as 96.82%, which fully demonstrates the advanced performance of this model in the task of recognizing defects on semiconductor material surfaces.

For overheating defects of power equipment, the use of infrared technology is widely popular at present, which is less costly and more efficient than the traditional manual detection of thermal defects of power equipment. However, infrared images have the nature of concentrated intensity and low contrast, and picture segmentation has always been a difficult point. This paper proposes a combination of K-mean clustering and improved region growing algorithm, compared with the traditional region growing algorithm, solves the need to manually select the seed point to produce uneven gray scale and over-segmentation and under-segmentation, etc., through the K-mean clustering algorithm to automatically select the number of seeds as well as the seed node, and the introduction of Canny operator to reduce the error in order to achieve a better segmentation effect. Finally compare other algorithms fuzzy C-mean segmentation and fuzzy threshold segmentation.

Serious ice accretion will cause structural problems and ice flashover accidents, which result in outdoor insulator string operating problems in winter conditions. Previous investigations have revealed that the thicker and longer insulators are covered with ice, the icing degree becomes worse and icing accident probability increases. Therefore, an image processing method was proposed to extract the characteristics of the icicle length and Rg (ratio of the air gap length to the insulator length) of ice-covered insulators for monitoring the operation of iced outdoor insulator strings. The tests were conducted at the artificial climate room of CIGELE Laboratories recommended by IEEE Standard 1783/2009. The surface phenomena of the insulator during the ice accretion process were recorded by using a high-speed video camera. In the view of the ice in the background of the picture of fuzzy features and high image noise, a direct equalization algorithm is used to enhance the grayscale iced image contrast. The median filtering method is conducted for reducing image noise and sharpening the image edge. The maximum entropy threshold segmentation algorithm is put forward to extract the insulators and its surface ice from the background. Then, the modified Canny operator edge detection algorithm is selected to trace the boundaries of objects through the extraction of information about attributes of the endpoints of edges. After we obtained the improved Canny edge detection image for both of the ice-covered insulators and non-iced insulators, the icing thickness can be obtained by calculating the difference between the edge of the non-iced insulators image and the edge of the iced insulator image. Besides, in order to identify the icing degree of the insulators more accurately, this paper determines the location of icicles by using the region growth method. After that, the icicle length and Rg can be obtained to monitor the icing degree of the insulator. It will be helpful to improve the ability to judge the accident risk of insulators in power systems.

In order to achieve non-contact pipe thread detection with high-precision, high-efficiency and make the use of pipe threads safer, using machine vision and image processing technology to measure and analyze the geometric parameters of pipe threads. The projection matrix and distortion coefficient of the camera are obtained by Zhang Zhengyou’s calibration method, and the distortion coefficient is used to correct the distortion of the collected image. After that, grayscale processing is performed on the RGB (Red, Green, Blue) image obtained by the collection and correction, fusion filtering and denoising, threshold segmentation to obtain the binary image, and then the Canny operator is used to detect the thread edge information on the binary image. Then the pipe thread parameter measurement algorithm is proposed based on the extracted pipe thread image characteristics. Finally, the feasibility of the measurement algorithm is verified by using the measured data of 60 sets of pipe threads. The test results show that the measured values of tooth height and crest height obtained by this algorithm are concentrated near the standard value, with high accuracy and precision, and the overall data fluctuation is small.

In order to improve the accuracy of image edge detection, this paper studies the adaptive image edge detection technology based on discrete algorithm and classical Canny operator. First, the traditional sub-pixel edge detection method is illustrated based on the related literature research. Then, Canny operator is used for detection, the edge model of the quadric curve is established using discrete data, and the adaptive image edge parameters are obtained using one-dimensional gray moment. Experimental results show that the accuracy of feature detection is 99%, which can be applied to the practice of image edge detection to a certain extent.

The present work aims to reduce tunnel construction accidents to personnel. The threshold adaptive segmentation algorithm combined with the Canny operator is employed to extract and detect the cracks on the rock mass of the tunnel face from digital images of the tunnel face. Firstly, the gray change processing and histogram equalization technology of the image processing algorithm enhance the contrast of the digital image of rock mass on the tunnel face. Then, the Canny operator and OTSU method construct a threshold adaptive segmentation algorithm to segment the rock mass crevice image after increasing the contrast and to classify crevices on the tunnel face into streak cracks and irregular cracks. Secondly, the segmented image is corrupted, extended, and refined; meanwhile, boundary fitting, separation, merging, and filtering are carried out to form a relatively complete rock boundary recognition result. Finally, the streak crevices and irregular crevices are detected according to the crevice geometry and pixel distribution characteristics to determine the crack direction. The experimental results show that this method can extract complete rock cracks with less than a 2% extraction error rate. Besides, the detection rates of the algorithm for the streak crevices and irregular crevices are 97% and 94%, respectively, and the detection accuracy of the crevice direction is 98%. This indicates that the algorithm proposed here is applicable to geological sketch and provides a reference for the classification of surrounding rock on the tunnel face.

Accurate detection of interlayer distress based on ground-penetrating radar has been widely adopted for in-service asphalt pavement condition assessment to improve maintenance efficiency and reduce costs. However, accurate interlayer distress locating is challenging with limited adaptability to their large-scale variations, which significantly weakens the detection performance. This study proposed a novel automatic detection network based on YOLOv5s to detect interlayer distresses in asphalt pavement named OEM-HWNet. Firstly, an object enhancement module based on prior knowledge was designed to locate the regions of interlayer distress and enhance their characteristics. Then, wavelet convolution was added to increase the receptive field of the network and enhance the ability to capture low-frequency information. Finally, an additional detection head was added to improve the detection capability of interlayer distress with different sizes. Experiments demonstrated that the proposed network achieves a mean average precision (mAP) of 89.6%, outperforming other advanced models, such as YOLOv5s, YOLOv8s, YOLOv11s, and Faster R-CNN. Incorporating prior knowledge into deep learning networks could provide an effective solution to detect interlayer distress of asphalt pavement.