Key Technologies of Steel Plate Surface Defect Detection System Based on Artificial Intelligence Machine Vision

Xue, Bin; Wu, Zhisheng

doi:10.1155/2021/5553470

Cited by 14 publications

(10 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…ere is some deviation between the origin and coordinate axes of {Hp} and {Hi}, but they are generally considered to be in the same plane [18,19]. Because the origin of {Hp} is in the center of the projected imaging image, and {Hi} is in pixels, it is used to read the picture in pixels into the computer for image processing.…”

Section: Graph and Pixel Coordinate Transformationmentioning

confidence: 99%

Design and Application of Art Education Communication Platform Based on Machine Vision

Chen

Tang

et al. 2022

Security and Communication Networks

View full text Add to dashboard Cite

There are some problems in the design and application of the art education exchange platform. In order to further analyze the relevant content of the art education exchange, based on machine vision theory, model calibration, and coordinate change are adopted to modify the original model, so as to obtain the optimized model. This model can be used to analyze the design and application of art education platform. Relevant studies show that, according to the coordinate parameter curve, the parameter α plays a promoting role on the coordinate value, while the parameter β plays a promoting role on the coordinate value first and then plays an inhibiting role. The parameter γ also promotes and inhibits coordinate values. The curve corresponding to parameter M1 shows a gradual decline, and the curve of parameter M2 has little influence on coordinate data. The curve corresponding to parameter M3 also shows a linear trend of change. Through analysis, it can be seen that M3 has the greatest influence on coordinate data. By using machine vision model to design and analyze the communication platform of art education, the changing trend of different indicators can be obtained. It can be seen from the analysis that both language and vocal music have obvious stability in the calculation process, which is an inherent attribute of communication platform. Finally, the accuracy of the optimization model is verified by analyzing and predicting the data. This research can provide theoretical support for the application of machine vision model in other fields.

show abstract

Section: Graph and Pixel Coordinate Transformationmentioning

confidence: 99%

Design and Application of Art Education Communication Platform Based on Machine Vision

Chen

Tang

et al. 2022

Security and Communication Networks

View full text Add to dashboard Cite

show abstract

“…Linear filtering includes mean filtering and Gaussian filtering, which has been widely used in steel surface defect image denoising [31–36]. The mean filtering is simple and fast, but it cannot protect the image details well.…”

Section: Image Processing Algorithmmentioning

confidence: 99%

Review of surface defect detection of steel products based on machine vision

Tang

Chen

Sun

et al. 2022

IET Image Processing

View full text Add to dashboard Cite

Steel plays an important role in industry, and the surface defect detection for steel products based on machine vision has been widely used during the last two decades. This paper attempts to review state‐of‐art of vision‐based surface defect inspection technology of steel products by investigating about 170 publications. This review covers the overall aspects of vision‐based surface defect inspection for steel products including hardware system, automated vision‐based inspection method, existing problems and latest development. The types of steel product surface defects composition of visual inspection system are briefly described, and image acquisition system is introduced as well. The image processing algorithms for surface defect detection of steel products are reviewed, including image pre‐processing, region of interest (ROI) detection, image segmentation for ROI, feature extraction and selection and defect classification. The important problems such as small sample and real time of steel surface defect detection are discussed. Finally, the challenge and development trend of steel surface defect detection are prospected.

show abstract

“…Several algorithms have been used for metal crack detection and texture feature extraction. Different edge detection operators have been used to obtain thin edge features on defective samples [19]. Similarly several machine learning based techniques,have been explored for classification of surface defects on rolled steel [3].…”

Section: Related Workmentioning

confidence: 99%

Taguchi based Design of Sequential Convolution Neural Network for Classification of Defective Fasteners

Kaur¹,

Chauhan²,

Aggarwal³

et al. 2022

Preprint

View full text Add to dashboard Cite

Fasteners play a critical role in securing various parts of machinery. Deformations such as dents, cracks, and scratches on the surface of fasteners are caused by material properties and incorrect handling of equipment during production processes. As a result, quality control is required to ensure safe and reliable operations. The existing defect inspection method relies on manual examination, which consumes a significant amount of time, money, and other resources; also, accuracy cannot be guaranteed due to human error. Automatic defect detection systems have proven impactful over the manual inspection technique for defect analysis. However, computational techniques such as convolutional neural networks (CNN) and deep learning-based approaches are evolutionary methods. By carefully selecting the design parameter values, the full potential of CNN can be realised. Using Taguchi based design of experiments and analysis, an attempt has been made to develop a robust automatic system in this study. The dataset used to train the system has been created manually for M14 size nuts having two labeled classes: Defective and Non-defective. There are a total of 264 images in the dataset. The proposed sequential CNN comes up with a 96.3% validation accuracy, 0.277 validation loss at 0.001 learning rate.

show abstract

Key Technologies of Steel Plate Surface Defect Detection System Based on Artificial Intelligence Machine Vision

Cited by 14 publications

References 37 publications

Design and Application of Art Education Communication Platform Based on Machine Vision

Design and Application of Art Education Communication Platform Based on Machine Vision

Review of surface defect detection of steel products based on machine vision

Taguchi based Design of Sequential Convolution Neural Network for Classification of Defective Fasteners

Contact Info

Product

Resources

About