scholarly journals Research on Image Defect Detection of Silicon Panel Based on Prewitt and Canny Operator

2021 ◽  
Vol 9 ◽  
Author(s):  
Yifeng Zhang ◽  
Zhiwen Wang ◽  
Yuhang Wang ◽  
Canlong Zhang ◽  
Biao Zhao
Keyword(s):  
Power Generation ◽  
Edge Detection ◽  
Defect Detection ◽  
Gpu Computing ◽  
Image Data ◽  
Detection Algorithm ◽  
Detection Accuracy ◽  
Edge Detection Algorithm ◽  
Image Defect ◽  
The Impact

The silicon panel is the core component of photovoltaic power generation, whose surface quality is related to its service life and power generation efficiency. However, microcracks, fragments, incomplete welding, broken grids, and other defects often occur in industrial production. The edge detection algorithm is usually used to detect defects in silicon panels, but the common edge detection algorithm has an impact on defect detection because of the grid shadow of the panel. The current mainstream defect detection algorithm based on convolutional neural network requires a large number of positive and negative samples of image data sets for pretraining the model, which consumes a lot of time and GPU computing power, and the steps are cumbersome. To solve the problem, a defect detection method based on Prewitt and Canny operators is proposed in this article. In this method, Prewitt and Canny operators are combined to eliminate the effect of grids on the detection. The microcrack defects and their specific positions can be detected efficiently and intuitively, therefore improving the detection accuracy. The experimental results indicate that the purity and integrity of the defect profile of the image processed by the algorithm are greatly improved. The foreground edge is clear, and the defect recognition accuracy is higher, which effectively prevent the impact of grid shadow on weld testing.

scholarly journals A Novel Edge Detection Method Based on the Regularized Laplacian Operation

Symmetry ◽  
2018 ◽  
Vol 10 (12) ◽  
pp. 697
Author(s):  
Huilin Xu ◽  
Yuhui Xiao
Keyword(s):  
Edge Detection ◽  
Detection Method ◽  
Regularization Parameter ◽  
Image Data ◽  
Detection Algorithm ◽  
Edge Detector ◽  
Rotation Symmetry ◽  
Edge Detection Algorithm ◽  
Choice Strategy ◽  
Edge Detection Method

In this paper, an edge detection method based on the regularized Laplacian operation is given. The Laplacian operation has been used extensively as a second-order edge detector due to its variable separability and rotation symmetry. Since the image data might contain some noises inevitably, regularization methods should be introduced to overcome the instability of Laplacian operation. By rewriting the Laplacian operation as an integral equation of the first kind, a regularization based on partial differential equation (PDE) can be used to compute the Laplacian operation approximately. We first propose a novel edge detection algorithm based on the regularized Laplacian operation. Considering the importance of the regularization parameter, an unsupervised choice strategy of the regularization parameter is introduced subsequently. Finally, the validity of the proposed edge detection algorithm is shown by some comparison experiments.

An Improved Canny Edge Detection Algorithm

2013 ◽  
Vol 291-294 ◽  
pp. 2869-2873 ◽  
Author(s):  
Tao Sun ◽  
Chang Zhi Gao
Keyword(s):  
Edge Detection ◽  
Threshold Value ◽  
Detection Algorithm ◽  
Detection Accuracy ◽  
Threshold Method ◽  
Canny Edge Detection ◽  
Edge Detection Algorithm ◽  
Global Threshold ◽  
Canny Edge ◽  
Canny Edge Detection Algorithm

Traditional Canny edge detection algorithm uses a global threshold selection method, when large changes are in the background of the image and the target gray, global threshold method may lose some local edge information. For this problem, this paper therefore proposes an adaptive dynamic threshold improved Canny edge detection algorithm. The method uses image gradient variance as the criterion of the image block according to the four forks tree principle, then uses the Otsu method to get the corresponding sub-block threshold value for each sub-block, and obtains threshold value matrix by interpolation, finally, gets image edge with improved edge connected algorithm. Experimental results show that, the algorithm not only has good anti-noise performance, but also better detection accuracy.

Application of Bidimensional Empirical Mode Decomposition to Medical Liquid Opacity Detection

2011 ◽  
Vol 128-129 ◽  
pp. 530-533
Author(s):  
Jian Wan ◽  
Yuan Peng Diao ◽  
Dong Mei Yan ◽  
Qiang Guo ◽  
Zhen Shen Qu
Keyword(s):  
Edge Detection ◽  
Empirical Mode Decomposition ◽  
External Environment ◽  
Detection Algorithm ◽  
Detection Methods ◽  
Detection Accuracy ◽  
Edge Detection Algorithm ◽  
Mode Decomposition ◽  
Simulation Results ◽  
Bidimensional Empirical Mode Decomposition

A Robert operator edge detection algorithm based on Bidimensional Empirical Mode Decomposition (BEMD) to detect medical liquid opacity is proposed. This method can effectively resolve the problem that traditional Robert operator edge detection can be easily effected by noise, and it also has certain effects on restraining external environment influence. The simulation results show that, compare with traditional medical liquid opacity detection methods, the proposed method could achieve higher detection accuracy, and has a certain theory and application value.

Edge Detection for Noise Image by Wavelet Transform and Mathematical Morphology

2011 ◽  
Vol 121-126 ◽  
pp. 4441-4445
Author(s):  
Hai Long Huang ◽  
Hong Wang
Keyword(s):  
Wavelet Transform ◽  
Edge Detection ◽  
Mathematical Morphology ◽  
Linear Structure ◽  
Detection Algorithm ◽  
Good Time ◽  
Detection Accuracy ◽  
Edge Detection Algorithm ◽  
Time Frequency ◽  
Noise Image

It is much more complex and difficult for edge detection of noise image compared to edge detection of normal image，the analysis and study of edge detection of noise image has universal significance and practical value. Wavelet transform possesses good time-frequency localization characteristic and multi-scale analytical ability, mathematical morphology is a new subject based on set theory, which is very suitable for analyzing and describing geometrical feature of signal. Combining the advantages of wavelet transform and mathematical morphology, the paper proposes an edge detection algorithm, which mainly focused on noise image. For edge detection based on mathematical morphology, constructs an anti-noise operator of edge detection by improving existing operators and employs different direction linear structure elements; edge detection based on mathematical morphology can reserve details of edge effectively, ensure the continuity and integrity of edge detected. Experimental results show the proposed algorithm can suppress the interference of different density and different types of noise more effectively in comparison with several classical edge detection algorithm, thus improving the detection accuracy and robustness for different images.

scholarly journals Edge Detection Algorithm of a Symmetric Difference Kernel SAR Image Based on the GAN Network Model

Symmetry ◽  
2019 ◽  
Vol 11 (4) ◽  
pp. 557 ◽  
Author(s):  
Zhang ◽  
Liu ◽  
Liu ◽  
Li ◽  
Ye
Keyword(s):  
Edge Detection ◽  
Network Model ◽  
Detection Algorithm ◽  
Symmetric Difference ◽  
Detection Accuracy ◽  
Sar Image ◽  
Data Generation ◽  
Edge Detection Algorithm ◽  
Difference Kernel ◽  
Image Edge

The symmetrical difference kernel SAR image edge detection algorithm based on the Canny operator can usually achieve effective edge detection of a single view image. When detecting a multi-view SAR image edge, it has the disadvantage of a low detection accuracy. An edge detection algorithm for a symmetric difference nuclear SAR image based on the GAN network model is proposed. Multi-view data of a symmetric difference nuclear SAR image are generated by the GAN network model. According to the results of multi-view data generation, an edge detection model for an arbitrary direction symmetric difference nuclear SAR image is constructed. A non-edge is eliminated by edge post-processing. The Hough transform is used to calculate the edge direction to realize the accurate detection of the edge of the SAR image. The experimental results show that the average classification accuracy of the proposed algorithm is 93.8%, 96.85% of the detection edges coincide with the correct edges, and 97.08% of the detection edges fall into the buffer of three pixel widths, whichshows that the proposed algorithm has a high accuracy of edge detection for kernel SAR images.

scholarly journals High-Speed Lightweight Ship Detection Algorithm Based on YOLO-V4 for Three-Channels RGB SAR Image

2021 ◽  
Vol 13 (10) ◽  
pp. 1909
Author(s):  
Jiahuan Jiang ◽  
Xiongjun Fu ◽  
Rui Qin ◽  
Xiaoyan Wang ◽  
Zhifeng Ma
Keyword(s):  
Deep Learning ◽  
Gpu Computing ◽  
Hot Spot ◽  
Detection Algorithm ◽  
Detection Methods ◽  
Detection Accuracy ◽  
Processing Unit ◽  
Sar Image ◽  
Marine Monitoring ◽  
Ship Detection

Synthetic Aperture Radar (SAR) has become one of the important technical means of marine monitoring in the field of remote sensing due to its all-day, all-weather advantage. National territorial waters to achieve ship monitoring is conducive to national maritime law enforcement, implementation of maritime traffic control, and maintenance of national maritime security, so ship detection has been a hot spot and focus of research. After the development from traditional detection methods to deep learning combined methods, most of the research always based on the evolving Graphics Processing Unit (GPU) computing power to propose more complex and computationally intensive strategies, while in the process of transplanting optical image detection ignored the low signal-to-noise ratio, low resolution, single-channel and other characteristics brought by the SAR image imaging principle. Constantly pursuing detection accuracy while ignoring the detection speed and the ultimate application of the algorithm, almost all algorithms rely on powerful clustered desktop GPUs, which cannot be implemented on the frontline of marine monitoring to cope with the changing realities. To address these issues, this paper proposes a multi-channel fusion SAR image processing method that makes full use of image information and the network’s ability to extract features; it is also based on the latest You Only Look Once version 4 (YOLO-V4) deep learning framework for modeling architecture and training models. The YOLO-V4-light network was tailored for real-time and implementation, significantly reducing the model size, detection time, number of computational parameters, and memory consumption, and refining the network for three-channel images to compensate for the loss of accuracy due to light-weighting. The test experiments were completed entirely on a portable computer and achieved an Average Precision (AP) of 90.37% on the SAR Ship Detection Dataset (SSDD), simplifying the model while ensuring a lead over most existing methods. The YOLO-V4-lightship detection algorithm proposed in this paper has great practical application in maritime safety monitoring and emergency rescue.

Sign in / Sign up

Export Citation Format

Share Document