Surface Defect Detection Method Based on Improved Semisupervised Multitask Generative Adversarial Network

Zhu, Lin; Du, B. X.; Zhao, Xiaomeng; Fang, Shaoliang; Che, Zhen; Zhou, Junjie; Chen, Shumin

doi:10.1155/2022/4481495

Cited by 8 publications

(5 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The technical realization route is shown in Figure 1: Firstly, training samples are constructed to provide a good database for machine learning. Secondly, building a reasonable generation countermeasure network model is the core to realize image generation and adjust the generation results [11]. Then configure the training environment, set the training parameters and train the model.…”

Section: Methodsmentioning

confidence: 99%

Product Design Process Based on GANs Model

Hu,

Chen

2024

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

In order to solve the difficulties and shortcomings when users use images to describe their requirements, a product design process based on GANs model is proposed. Build a generation countermeasure network and train an intelligent image generation model, so that the computer can quickly generate design cases, and can artificially control the generation results to realize the establishment of case base and the adjustment of image content. In addition, an image artistic style similarity measurement model is proposed to calculate the style differences between images. The results show that the measurement results of this method are consistent with the subjective evaluation of designers. The statistical results of 30 groups of data show that the probability that this method is consistent with the designer’s evaluation results is 90%. So far, in the above performance evaluation experiments, the similarity measurement results of the same/different style works are obviously different, which conforms to the rules of style similarity. In the task of ranking style similarity, this model is 90% consistent with the ranking results of designers. Conclusion: The model is effective in performance evaluation experiments, which lays a foundation for developing style-based design case retrieval and recommendation.

show abstract

Section: Methodsmentioning

confidence: 99%

Product Design Process Based on GANs Model

Hu,

Chen

2024

Frontiers in Artificial Intelligence and Applications

View full text Add to dashboard Cite

show abstract

“…The performance of RegNet has been demonstrated on several benchmark datasets, with results comparable to or better than other state-of-theart architectures while requiring fewer computational resources. RegNet has been used in surface defect detection [123], identi cation of sh species [124], and analysis of medical imagery [125].…”

Section: Regnetmentioning

confidence: 99%

Waste Reduction via Computer Vision-based Inspection: Towards Lean Systems in Metal Production

Shahin¹,

Chen

Hosseinzadeh³

et al. 2023

Preprint

View full text Add to dashboard Cite

The global steel demand continues to increase, with steel being used in various industries, including construction, automobile, national defense, and machinery. However, steel production is a delicate process that can result in different defects on the steel surface, negatively affecting the quality of the steel products. Therefore, recognizing metal surface defects is critical in the metal production industry. Manual detection of these defects is the standard method, but it is time-consuming, labor-intensive, and prone to subjective factors, leading to low accuracy and unreliable results. Automated defect detection using computer vision methods can replace or supplement manual detection. In recent years, machine learning algorithms, particularly Convolutional Neural Networks (CNNs), have shown great promise in achieving high accuracy rates in this task. In addition, image classification algorithms can contribute to Lean metal production by identifying defects or anomalies in the manufacturing process, which can be used to reduce waste and increase efficiency. However, the performance and cost of different CNN architectures can vary widely, making it challenging for decision-makers to select the most suitable model. This paper analyzes various CNN-based image classification algorithms, including MobileNet, ShuffleNet, DenseNet, RegNet, and NasNet, in classifying steel surface defects in the NEU-CLS-64 dataset. We evaluate their performance using metrics such as accuracy, precision, sensitivity, specificity, F1 score, and G-mean, and benchmark these models against each other. Our findings revealed that RegNet achieved the highest accuracy, precision, sensitivity, specificity, F1 score, and G-mean performance but at a higher cost than other models. Meanwhile, MobileNet had the lowest performance. The results provide decision-makers with valuable insights into selecting the most suitable CNN model for steel surface defect detection based on their performance.

show abstract

“…The method claims that it can reduce the misjudgment rate from 0.3 − 0.5% to 0.02 − 0.03%. Zhu et al [11] proposed defect detection method based on improved semisupervised multitask generative adversarial network.…”

Section: Related Workmentioning

confidence: 99%

Fast plug-in capacitors polarity detection with morphology and SVM fusion method in automatic optical inspection system

Jiang

Zhang

et al. 2023

SIViP

View full text Add to dashboard Cite

Defect detection is a critical element in the PCB manufacturing process. Different from surface mount PCB, the components on the plug-in PCB are usually installed manually, resulting in significant errors. Furthermore, because plug-in components have many different types and irregularities, it is difficult to detect their flaws. We make contributions in the following two aspects: (1) a framework and measurement method of a light source and make a cheap and efficient lighting system; (2) a fusion algorithm based on machine learning and morphology for polarity detection of plug-in capacitors. The capacitor is detected using SVM and fused with the polar coordinate expansion method. The AOI system and the proposed fusion algorithm have been applied to the production line, with an accuracy of 99.73% and a missed detection rate of only 0.12%, according to the field test of the production line.

show abstract

Surface Defect Detection Method Based on Improved Semisupervised Multitask Generative Adversarial Network

Cited by 8 publications

References 29 publications

Product Design Process Based on GANs Model

Product Design Process Based on GANs Model

Waste Reduction via Computer Vision-based Inspection: Towards Lean Systems in Metal Production

Fast plug-in capacitors polarity detection with morphology and SVM fusion method in automatic optical inspection system

Contact Info

Product

Resources

About