Image Preprocessing Method in Radiographic Inspection for Automatic Detection of Ship Welding Defects

被引:10
|
作者
Yun, Gwang-ho [1 ]
Oh, Sang-jin [1 ]
Shin, Sung-chul [1 ]
机构
[1] Pusan Natl Univ, Dept Naval Architecture & Ocean Engn, Busan 46241, South Korea
来源
APPLIED SCIENCES-BASEL | 2022年 / 12卷 / 01期
关键词
deep learning; CLAHE; denoising; thresholding; welding defect; ADAPTIVE HISTOGRAM EQUALIZATION; ALGORITHM;
D O I
10.3390/app12010123
中图分类号
O6 [化学];
学科分类号
0703 ;
摘要
Welding defects must be inspected to verify that the welds meet the requirements of ship welded joints, and in welding defect inspection, among nondestructive inspections, radiographic inspection is widely applied during the production process. To perform nondestructive inspection, the completed weldment must be transported to the nondestructive inspection station, which is expensive; consequently, automation of welding defect detection is required. Recently, at several processing sites of companies, continuous attempts are being made to combine deep learning to detect defects more accurately. Preprocessing for welding defects in radiographic inspection images should be prioritized to automatically detect welding defects using deep learning during radiographic nondestructive inspection. In this study, by analyzing the pixel values, we developed an image preprocessing method that can integrate the defect features. After maximizing the contrast between the defect and background in radiographic through CLAHE (contrast-limited adaptive histogram equalization), denoising (noise removal), thresholding (threshold processing), and concatenation were sequentially performed. The improvement in detection performance due to preprocessing was verified by comparing the results of the application of the algorithm on raw images, typical preprocessed images, and preprocessed images. The mAP for the training data and test data was 84.9% and 51.2% for the preprocessed image learning model, whereas 82.0% and 43.5% for the typical preprocessed image learning model and 78.0%, 40.8% for the raw image learning model. Object detection algorithm technology is developed every year, and the mAP is improving by approximately 3% to 10%. This study achieved a comparable performance improvement by only preprocessing with data.
引用
收藏
页数:17
相关论文
共 50 条
  • [21] Automated detection of welding defects in pipelines from radiographic images DWDI
    Boaretto, Neury
    Centeno, Tania Mezzadri
    NDT & E INTERNATIONAL, 2017, 86 : 7 - 13
  • [22] Surface inspection for automatic detection and classification of defects on hot strip
    Unilux, Inc, Hackensack, United States
    Steel Times Int, 5 (2pp):
  • [23] An easy method of image feature extraction for real-time welding defects detection
    Zhang, Zhifen
    Wen, Guangrui
    2016 13TH INTERNATIONAL CONFERENCE ON UBIQUITOUS ROBOTS AND AMBIENT INTELLIGENCE (URAI), 2016, : 615 - 619
  • [24] Automatic Image Inspection of Fabric Defects Based on Optimal Gabor Filter
    尉苗苗
    李岳阳
    蒋高明
    丛洪莲
    Journal of Donghua University(English Edition), 2016, 33 (04) : 545 - 548
  • [25] Automatic inspection of typical microstructure defects based on image processing techniques
    Chen, Xiaohui
    Liu, Xiaojun
    FRONTIERS OF MANUFACTURING AND DESIGN SCIENCE, PTS 1-4, 2011, 44-47 : 2622 - 2626
  • [26] Automatic detection of welding defects using radiography with a neural approach
    Yahia, N. B.
    Belhadj, T.
    Brag, S.
    Zghal, A.
    11TH INTERNATIONAL CONFERENCE ON THE MECHANICAL BEHAVIOR OF MATERIALS (ICM11), 2011, 10
  • [27] Automatic Detection of Welding Defects using Deep Neural Network
    Hou, Wenhui
    Wei, Ye
    Guo, Jie
    Jin, Yi
    Zhu, Chang'an
    10TH INTERNATIONAL CONFERENCE ON COMPUTER AND ELECTRICAL ENGINEERING, 2018, 933
  • [28] Automatic detection of welding defects using the convolutional neural network
    Sizyakin, Roman
    Voronin, Viacheslav
    Gapon, Nikolay
    Zelensky, Aleksandr
    Pizurica, Aleksandra
    AUTOMATED VISUAL INSPECTION AND MACHINE VISION III, 2019, 11061
  • [29] Underwater Image Target Detection with Cascade Classifier and Image Preprocessing Method
    Zeng, Lingcai
    Sun, Bing
    Zhang, Wei
    Zhu, Daqi
    INTELLIGENT ROBOTICS AND APPLICATIONS, ICIRA 2019, PT III, 2019, 11742 : 195 - 205
  • [30] Automatic detection method of a moving ship based on an HY-1/CZI satellite image
    Li H.
    Gong F.
    Zhu Q.
    He X.
    National Remote Sensing Bulletin, 2023, 27 (04) : 965 - 972