Automatic defect detection of texture surface with an efficient texture removal network

Liang, Ying; Xu, Ke; Zhou, Peng; Zhou, Dongdong

doi:10.1016/j.aei.2022.101672

Cited by 22 publications

(4 citation statements)

References 34 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The experimental findings yield the following conclusions: (1) The proposed model enhances the time efficiency of image denoising and computational efficiency compared to TGV-OGS with the ADMM solver. (2) The denoising efficacy of the proposed model outperforms state-of-the-art variational denoising models, especially for images marked by substantial noise and textured regions. One drawback of the proposed model is the manual determination required for the regularization parameter.…”

Section: Discussionmentioning

confidence: 90%

“…Automated recognition of these printed characters or writing enhances the level of automation in inspection processes and improves authentication accuracy. However, owing to the surface complexity of textured materials, printing conditions, the similarity of adjacent regions or patterns (e.g., guilloche patterns or watermarks), and variations in illumination, the segmentation of printed characters or writing remains a persistent challenge, potentially compromising the accuracy of character recognition [2], [3], [4]. Consequently, effective denoising becomes paramount before undertaking character segmentation and recognition.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Denoising on Textured Image Using Total Generalized Variation With Overlapping Group Sparsity Based on Fast Split Bregman Method

Zhang,

Yen

2024

IEEE Access

View full text Add to dashboard Cite

The Total Generalized Variation (TGV) model proves effective in removing texture and background patterns in natural images while suppressing the staircase effect introduced by traditional Total Variation (TV) regularization. Nevertheless, TGV falls short in preserving structural features due to its lack of consideration for such structural features. This paper introduces Overlapping Group Sparsity (OGS) regularization into the TGV model with the specific aim of enhancing denoising, particularly in textured images. By leveraging prior knowledge of sparse structures discernible from first-order and second-order gradients, this model surpasses the conventional TGV models in achieving superior denoising and staircase effect elimination. The model proposed employs a fast split Bregman iteration method to address the L1 regularization problem within the complex TGV model combined with OGS. The experimental results comparing various state-of-the-art denoising TV-and TGV-based models highlight a significant improvement in the denoising performance of the proposed model. Specifically, in comparison to the average values of peak signal-to-noise ratio (PSNR) and structural similarity index measure (SSIM) obtained from other state-of-the-art models, the proposed model demonstrated improvements of 3.5% in PSNR and 3.4% in SSIM.INDEX TERMS Total generalized variation, overlapping group sparsity, texture denoising, split Bregman.

show abstract

Section: Discussionmentioning

confidence: 90%

Section: Introductionmentioning

confidence: 99%

Denoising on Textured Image Using Total Generalized Variation With Overlapping Group Sparsity Based on Fast Split Bregman Method

Zhang,

Yen

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

“…Figure 3 illustrates online detection technologies used in China’s steel industry. The detection technology development direction is to use advanced modern detection technologies such as machine vision [ 86 , 87 , 88 , 89 , 90 , 91 , 92 , 93 ], laser-induced breakdown spectroscopy (LIBS) [ 94 , 95 , 96 , 97 , 98 ], ultrasonic microscopy technology, and others, in conjunction with deep-learning algorithms and statistical modeling theory; to apply or develop intelligent perception technology on the production line; and to conduct online or rapid detection of key parameters throughout the manufacturing process. The ultimate purposes of online detecting technologies are to provide intelligent management and process optimization in the steel industry, improve the quality of terminal products, increase labor productivity and reduce labor costs, and provide vital fundamental data for quality control and big data platforms.…”

Section: Key Technologies For Intelligent Manufacturing In Steel Indu...mentioning

confidence: 99%

Intelligent Manufacturing Technology in the Steel Industry of China: A Review

Zhou

et al. 2022

Sensors

Self Cite

View full text Add to dashboard Cite

Intelligent manufacturing, defined as the integration of manufacturing with modern information technologies such as 5G, digitalization, networking, and intelligence, has grown in popularity as a means of boosting the productivity, intelligence, and flexibility of traditional manufacturing processes. The steel industry is a necessary support for modern life and economic development, and the Chinese steel industry’s capacity has expanded to roughly half of global production. However, the Chinese steel industry is now confronted with high labor costs, massive carbon emissions, a low level of intelligence, low production efficiency, and unstable quality control. Therefore, China’s steel industry has launched several large-scale intelligent manufacturing initiatives to improve production efficiency, product quality, manual labor intensity, and employee working conditions. Unfortunately, there is no comprehensive overview of intelligent manufacturing in China’s steel industry. We began this research by summarizing the construction goals and overall framework for intelligent manufacturing of the steel industry in China. Following that, we offered a brief review of intelligent manufacturing for China’s steel industry, as well as descriptions of two typical intelligent manufacturing models. Finally, some major technologies employed for intelligent production in China’s steel industry were introduced. This research not only helps to comprehend the development model, essential technologies, and construction techniques of intelligent manufacturing in China’s steel industry, but it also provides vital inspiration for the manufacturing industry’s digital and intelligence updates and quality improvement.

show abstract

“…However, the simple classification algorithm cannot locate the specific location of the defect, nor can it judge the size of the defect, which is not conducive to the statistical analysis of the defect by the factory. Object detection, one of the major tasks in computer vision and pattern recognition, has been widely applied in industry with the great breakthrough of convolutional neural networks (CNNs), especially for automated defect inspection (ADI) [4][5][6] . Current state-of-the-art object detectors have achieved high accuracy on benchmark datasets when large-scale backbone networks had been applied [7][8][9] .…”

Section: Introductionmentioning

confidence: 99%

RDDPA: Real-time Defect Detection via Pruning Algorithm on Steel Surface

Lu,

Pan,

et al. 2024

ISIJ Int.

View full text Add to dashboard Cite

Real-time object detectors deployed on general-purpose graphics processing units (GPUs) or embedded devices allow their mass usage in industrial applications at an affordable cost. However, existing state-of-the-art object detectors are difficult to meet the requirements of high accuracy and low inference latency simultaneously in industrial applications on general-purpose devices. In this work, we propose RDDPA, a fast and accurate defect detection framework. RDDPA adopts a novel end-to-end pruning scheme, which can prune the detection network from scratch and achieve realtime detection on general-purpose devices. Additionally, we have developed a new training scheme to minimize the accuracy loss associated with the pruning process. Experimental results on a standard steel surface defect dataset indicate that our model achieves 79.2% mAP (mean Average Precision) at 103.7 FPS (Frames Per Second) on a single mid-end Titan X GPU as well as 40.1 FPS on a single low-end GTX 960M GPU, and outperforms the state-of-the-art defect detectors by about 20× speedup with considerable or higher accuracy.

show abstract

Automatic defect detection of texture surface with an efficient texture removal network

Cited by 22 publications

References 34 publications

Denoising on Textured Image Using Total Generalized Variation With Overlapping Group Sparsity Based on Fast Split Bregman Method

Denoising on Textured Image Using Total Generalized Variation With Overlapping Group Sparsity Based on Fast Split Bregman Method

Intelligent Manufacturing Technology in the Steel Industry of China: A Review

RDDPA: Real-time Defect Detection via Pruning Algorithm on Steel Surface

Contact Info

Product

Resources

About