Attention mechanism and texture contextual information for steel plate defects detection

被引:7
|
作者
Zhang, Chi [1 ]
Cui, Jian [1 ]
Wu, Jianguo [1 ]
Zhang, Xi [1 ]
机构
[1] Peking Univ, Dept Ind Engn & Management, Beijing, Peoples R China
关键词
Statistical texture feature fusion; Contextual information mining; Attention mechanism; Steel surface defect detection; CLASSIFICATION;
D O I
10.1007/s10845-023-02149-6
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
In order to achieve rapid inference and generalization results, the majority of Convolutional Neural Network (CNN) based semantic segmentation models strive to mine high-level features that contain rich contextual semantic information. However, at steel plate defects detection scenario, some background textures' noises are similar to the foreground leading to hard distinguishment, which will significantly interfere with feature extraction. Texture features themselves often hold the most plentiful contextual information. Despite this, semantic segmentation tasks rarely take texture features into account when identifying surface defects on steel plates. In that case, the essential details, such as the edge texture and other intuitive low-level features, will generally cannot be included into the final feature map. To address the problems of inefficient accuracy and slow speed of existing detection, this study proposed a steel plate surface defect detection method using contextual information and attention mechanism, and utilizes a multi-layer feature extraction method and fusion framework based on low-level statistical textures. Through the identification of pixel-level spatial and correlation relationships, characteristics of low-level defects are extracted. Furthermore, to effectively incorporate statistical texture in CNN, a novel quantization technique has been developed. This quantization method allows for the conversion of continuous texture into various levels of intensity. The network parameters were iterated in a gradient direction, facilitating the defects division. Empirical results have demonstrated the feasibility of applying the proposed approach to practical steel plate testing. Additionally, ablation experiments have demonstrated that the method is capable of effectively enhancing surface defect detection for steel plates, resulting in industry-leading performance.
引用
收藏
页码:2193 / 2214
页数:22
相关论文
共 50 条
  • [21] Contextual texture based bottom-up visual attention
    Lang Congyan
    Xu De
    Li Ning
    ICSP: 2008 9TH INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING, VOLS 1-5, PROCEEDINGS, 2008, : 942 - 945
  • [22] The Mechanism of Attention in Texture Segmentation Processing
    Hao, Fang
    Liu, Changjiang
    CONFERENCE ON PSYCHOLOGY AND SOCIAL HARMONY (CPSH2011), 2011, : 222 - +
  • [23] A Pedestrian Detection Network Based on an Attention Mechanism and Pose Information
    Jiang, Zhaoyin
    Huang, Shucheng
    Li, Mingxing
    Applied Sciences (Switzerland), 2024, 14 (18):
  • [24] Combining Contextual Information by Self-attention Mechanism in Convolutional Neural Networks for Text Classification
    Wu, Xin
    Cai, Yi
    Li, Qing
    Xu, Jingyun
    Leung, Ho-fung
    WEB INFORMATION SYSTEMS ENGINEERING, WISE 2018, PT I, 2018, 11233 : 453 - 467
  • [25] Study on the Detection of Defects in Steel Plate Welds with. Eddy Current Probe
    Li, Xuemin
    Li, Donglin
    Guo, Juncheng
    ADVANCES IN MACHINERY, MATERIALS SCIENCE AND ENGINEERING APPLICATION, 2022, 24 : 343 - 350
  • [26] A Shallow Neural Network for Recognition of Strip Steel Surface Defects Based on Attention Mechanism
    Li, Dan
    Ge, Shiquan
    Zhao, Kai
    Cheng, Xing
    ISIJ INTERNATIONAL, 2023, 63 (03) : 525 - 533
  • [27] Strip Steel Surface Defects Classification Based on Generative Adversarial Network and Attention Mechanism
    Hao, Zhuangzhuang
    Li, Zhiyang
    Ren, Fuji
    Lv, Shuaishuai
    Ni, Hongjun
    METALS, 2022, 12 (02)
  • [28] Mechanism of edge seam defects of stainless steel generated during hot plate rolling
    Sun, Cheng-Gang
    Lee, Jong-Seog
    Lee, Jung-Hyeung
    Hwang, Sang-Moo
    ISIJ INTERNATIONAL, 2006, 46 (01) : 93 - 99
  • [29] PCB defects target detection combining multi-scale and attention mechanism
    Jiang, Wujin
    Li, Taifu
    Zhang, Shaolin
    Chen, Wenbin
    Yang, Jie
    ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2023, 123
  • [30] An Object Detection Algorithm Based on Contextual Self-Calibration And Dual-Attention Mechanism
    Luo Junkai
    Zhang Baohua
    Zhang Yanyue
    Gu Yu
    Wang Yueming
    Liu Xin
    Ren Yan
    Li Jianjun
    Zhang Ming
    LASER & OPTOELECTRONICS PROGRESS, 2021, 58 (12)